Railway insulation joint detection method and device

Abstract

The embodiment of the present invention provides a railway insulation joint detection method and device, which determines the image segmentation path corresponding to the target insulation joint through the position information, and generates a current segmented image set based on the image segmentation path of the target insulation joint and the current image of the target insulation joint; determines the first difference between each segmented image in the current segmented image set and each segmented image corresponding to the historical segmented image set closest to the current acquisition time point; and confirms the current deformation of the target insulation joint based on the first difference and / or the second difference and / or the third difference. The deformation of the insulation joint is detected by the monitoring device installed on the train, so that the detection of the insulation joint has low labor intensity and short inspection cycle. Once the section equipment is damaged, it is easy to find it in time, and reduces the interference of personnel to driving and the probability of personal injury accidents.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to a railway insulation joint detection method and device. Background Art

[0002] The insulation joint in the non-insulated track circuit system is used to achieve electrical isolation between adjacent track circuits, ensure the effective transmission of signals in this section, and achieve the balance of the power frequency traction return current. It is a very critical component in the non-insulated track circuit system. At present, the non-insulated track circuits used in my country's large railway lines are generally tuned non-insulated track circuits.

[0003] The main method for detecting railway insulation joints is manual inspection. Inspectors not only have to walk dozens of kilometers at night, but also have to inspect signal equipment. The inspection cycle is half a year and one month.

[0004] However, the manual inspection method is labor-intensive and has a long inspection cycle. Once the equipment in the section is damaged, it is not easy to discover it in time. In addition, increasing the number of people on the road will interfere with driving and increase the probability of personal injury accidents. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide a railway insulation joint detection method and device that overcomes the above problems or at least partially solves the above problems, including:

[0006] A railway insulation joint detection method, the method is used to determine the deformation of a target insulation joint through a real-time image obtained by a monitoring device loaded on a train; wherein the deformation condition includes to be repaired or normal, including:

[0007] Acquire current state data of the target insulation joint, wherein the current state data includes a current image of the target insulation joint, a time point of acquisition of the current state data, location information of the current state data, and a current audio signal generated by tapping the target insulation joint;

[0008] Determine an image segmentation path corresponding to the target insulation node according to the position information, and generate a current segmented image set according to the image segmentation path of the target insulation node and a current image of the target insulation node;

[0009] Determine a first difference between each segmented image in the current segmented image set and each corresponding segmented image in the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determine a second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; determine a third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times;

[0010] Determine a standard audio signal corresponding to the target isolation node according to the position information, and determine an audio difference degree according to the current audio signal and the standard audio signal;

[0011] The total difference value is determined based on the first difference situation and / or the second difference situation and / or the third difference situation and the audio difference, and when the total difference value exceeds a preset threshold, the current deformation condition of the target insulation joint is set to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, the weight of the audio difference is set to 20% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation is set to 80%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation; when the audio difference is greater than the audio threshold, the weight of the audio difference is set to 80% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation is set to 20%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation.

[0012] Preferably, the step of obtaining the current status data of the target insulation node includes:

[0013] Acquire a real-time image of the target insulation node, and generate a current image of the target insulation node according to the real-time image, a foreground model corresponding to the target insulation node, and a background model corresponding to the target insulation node;

[0014] The position information of the target insulation node is acquired, and the current state data of the target insulation node is generated according to the position information of the target insulation node and the current image of the target insulation node.

[0015] Preferably, it also includes:

[0016] Acquire a standard image of the target insulating joint, and determine a target area corresponding to the target insulating joint in the standard image of the target insulating joint;

[0017] Acquire pixel points in the target area in the standard image, and generate the foreground model according to the pixel points in the target area;

[0018] Pixel points outside the target area in the standard image are acquired, and the background model is generated according to the pixel points outside the target area.

[0019] Preferably, the step of generating the current image of the target insulation node according to the real-time image and the foreground model corresponding to the target insulation node and the background model of the target insulation node comprises:

[0020] Determining a first probability that each pixel point in the real-time image belongs to the target area according to the foreground model and the real-time image;

[0021] Determining a second probability that each pixel in the real-time image belongs to outside the target area according to the background model and the real-time image;

[0022] A current image of the target insulation node is generated according to the first probability, the second probability and the real-time image.

[0023] Preferably, the current audio signal is: a first audio signal and a second audio signal generated by tapping the target insulating joint; wherein the time interval between the first audio signal and the second audio signal is a preset time; the first audio signal and the second audio signal are averaged to obtain an average audio signal; the average audio signal is amplified and noise-reduced to obtain the current audio signal.

[0024] Preferably, the step of generating a current segmented image set according to the image segmentation path of the target insulation node and the current image of the target insulation node comprises:

[0025] Segmenting the current image of the target insulation joint into a preset number of current segmented images according to the image segmentation path, and numbering the current segmented images;

[0026] The current segmented image set is generated according to the numbered current segmented images.

[0027] Preferably, the step of determining a first difference between each segmented image in the current segmented image set and each segmented image corresponding to a historical segmented image set closest to the current acquisition time point comprises:

[0028] respectively determining image difference values ​​between the historical segmented images with corresponding numbers in the historical segmented image set closest to the current acquisition time point and in the current segmented image set and the current segmented image;

[0029] The image difference values ​​are superimposed to generate the first difference condition.

[0030] Preferably, the step of determining a second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets comprises:

[0031] respectively determining image difference values ​​between historical segmented images corresponding to numbers in a single historical segmented image set and in the current segmented image set and the current segmented image;

[0032] Superimposing all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set, respectively generating the second comparison difference values;

[0033] The second comparison differences in all historical segmentation image sets are compared, and the second comparison difference with the largest value is taken as the second difference situation.

[0034] Preferably, the step of determining the third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times comprises:

[0035] respectively determining image difference values ​​between historical segmented images corresponding to numbers in a single historical segmented image set and in the current segmented image set and the current segmented image;

[0036] Superimposing all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set, respectively generating the third comparison difference values;

[0037] The third comparison differences in each historical segmented image set within a preset number of times are superimposed as a third difference situation.

[0038] Matching the above method, the present invention also provides a railway insulation joint detection device, which is used to determine the deformation of the target insulation joint through the real-time image obtained by the monitoring device loaded on the train; wherein the deformation condition includes to be repaired or normal, including:

[0039] A current state data acquisition module, used to acquire the current state data of the target insulation joint, wherein the current state data includes a current image of the target insulation joint, a time point of acquiring the current state data, location information of the current state data, and a current audio signal generated by tapping the target insulation joint;

[0040] A current segmented image set generating module, used to determine an image segmentation path corresponding to the target insulation node according to the position information, and to generate a current segmented image set according to the image segmentation path of the target insulation node and a current image of the target insulation node;

[0041] A difference determination module is used to determine a first difference between each segmented image in the current segmented image set and each corresponding segmented image in the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determine a second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; determine a third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times;

[0042] an audio difference determination module, configured to determine a standard audio signal corresponding to the target isolation node according to the position information, and determine an audio difference according to the current audio signal and the standard audio signal;

[0043] A current deformation condition confirmation module is used to determine the total difference value based on the first difference condition and / or the second difference condition and / or the third difference condition and the audio difference, and when the total difference value exceeds a preset threshold, set the current deformation condition of the target insulation joint to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, the weight of the audio difference is set to 20% and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition is set to 80%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition; when the audio difference is greater than the audio threshold, the weight of the audio difference is set to 80% and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition is set to 20%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition.

[0044] This application has the following advantages:

[0045] In an embodiment of the present application, by acquiring the current state data of the target insulation joint, wherein the current state data includes the current image of the target insulation joint, the acquisition time point of the current state data, the location information of the current state data, and the current audio signal generated by tapping the target insulation joint; determining the image segmentation path corresponding to the target insulation joint based on the location information, and generating a current segmented image set based on the image segmentation path of the target insulation joint and the current image of the target insulation joint; determining the first difference between each segmented image in the current segmented image set and each segmented image corresponding to the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determining the second difference between each segmented image in the current segmented image set and each segmented image corresponding to all historical segmented image sets; and / or; determining the third difference between each segmented image in the current segmented image set and each segmented image corresponding to each historical segmented image set within a preset number of times; according to Determine a standard audio signal corresponding to the target insulation joint according to the position information, and determine an audio difference according to the current audio signal and the standard audio signal; determine a total difference value according to the first difference situation and / or the second difference situation and / or the third difference situation and the audio difference, and when the total difference value exceeds a preset threshold, set the current deformation situation of the target insulation joint to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, set the weight of the audio difference to 20% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 80%, and calculate the total difference value according to the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation; when the audio difference is greater than the audio threshold, set the weight of the audio difference to 80% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 20%, and calculate the total difference value according to the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation. The deformation of the insulating joint is detected by the monitoring device installed on the train, which makes the detection of the insulating joint less labor-intensive and the inspection cycle shorter. Once the section equipment is damaged, it is easy to find it in time, and the interference of people on the road to driving and the probability of personal injury accidents are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 It is a flowchart of the steps of a railway insulation joint detection method provided by an embodiment of the present application;

[0048] Figure 2 This is a structural block diagram of a railway insulation joint detection device provided by an embodiment of the present application;

[0049] Figure 3 It is a schematic diagram of an image segmentation path of a railway insulation joint detection method provided by an embodiment of the present invention;

[0050] Figure 4 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0052] It should be noted that the railway insulating joint detection method in any embodiment of the present invention determines the deformation condition of the target insulating joint through a real-time image obtained by a monitoring device loaded on a train; wherein the deformation condition includes to be repaired or normal.

[0053] Reference Figure 1 , shows a flow chart of a method for detecting railway insulation joints provided by an embodiment of the present application, which specifically includes the following steps:

[0054] S110, obtaining current state data of the target insulation joint, wherein the current state data includes a current image of the target insulation joint, a time point of obtaining the current state data, location information of the current state data, and a current audio signal generated by tapping the target insulation joint;

[0055] S120, determining an image segmentation path corresponding to the target insulation node according to the position information, and generating a current segmented image set according to the image segmentation path of the target insulation node and a current image of the target insulation node;

[0056] S130, determining a first difference between each segmented image in the current segmented image set and each corresponding segmented image in the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determining a second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; determining a third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times;

[0057] S140, determining a standard audio signal corresponding to the target isolation node according to the position information, and determining an audio difference degree according to the current audio signal and the standard audio signal;

[0058] S150. Determine a total difference value based on the first difference situation and / or the second difference situation and / or the third difference situation and the audio difference, and when the total difference value exceeds a preset threshold, set the current deformation condition of the target insulation joint to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, set the weight of the audio difference to 20% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 80%, and calculate the total difference value based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation; when the audio difference is greater than the audio threshold, set the weight of the audio difference to 80% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 20%, and calculate the total difference value based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation.

[0059] In an embodiment of the present application, by acquiring the current state data of the target insulation joint, wherein the current state data includes the current image of the target insulation joint, the acquisition time point of the current state data, the location information of the current state data, and the current audio signal generated by tapping the target insulation joint; determining the image segmentation path corresponding to the target insulation joint based on the location information, and generating a current segmented image set based on the image segmentation path of the target insulation joint and the current image of the target insulation joint; determining the first difference between each segmented image in the current segmented image set and each segmented image corresponding to the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determining the second difference between each segmented image in the current segmented image set and each segmented image corresponding to all historical segmented image sets; and / or; determining the third difference between each segmented image in the current segmented image set and each segmented image corresponding to each historical segmented image set within a preset number of times; according to Determine a standard audio signal corresponding to the target insulation joint according to the position information, and determine an audio difference according to the current audio signal and the standard audio signal; determine a total difference value according to the first difference situation and / or the second difference situation and / or the third difference situation and the audio difference, and when the total difference value exceeds a preset threshold, set the current deformation situation of the target insulation joint to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, set the weight of the audio difference to 20% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 80%, and calculate the total difference value according to the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation; when the audio difference is greater than the audio threshold, set the weight of the audio difference to 80% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 20%, and calculate the total difference value according to the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation. The deformation of the insulating joint is detected by the monitoring device installed on the train, which makes the detection of the insulating joint less labor-intensive and the inspection cycle shorter. Once the section equipment is damaged, it is easy to find it in time, and the interference of people on the road to driving and the probability of personal injury accidents are reduced.

[0060] Next, the railway insulation joint detection method in this exemplary embodiment will be further described.

[0061] As described in the above step S110, the current status data of the target insulation joint is obtained, wherein the current status data includes the current image of the target insulation joint, the time point of obtaining the current status data, the location information of the current status data, and the current audio signal generated by tapping the target insulation joint.

[0062] In one embodiment of the present invention, the specific process of "obtaining the current status data of the target insulation joint, wherein the current status data includes the current image of the target insulation joint, the time point of obtaining the current status data, the location information of the current status data, and the current audio signal generated by tapping the target insulation joint" described in step S110 can be further explained in combination with the following description.

[0063] As described in the following steps, a real-time image of the target insulation node is acquired, and a current image of the target insulation node is generated based on the real-time image, a foreground model corresponding to the target insulation node, and a background model corresponding to the target insulation node.

[0064] In one embodiment of the present invention, the specific process of the step of "generating the current image of the target insulation node based on the real-time image and the foreground model corresponding to the target insulation node and the background model corresponding to the target insulation node" can be further explained in combination with the following description.

[0065] As described in the following steps, a first probability that each pixel point in the real-time image belongs to the target area is determined according to the foreground model and the real-time image.

[0066] In an embodiment of the present invention, the method further includes acquiring a standard image of the target insulation node, and determining a target area corresponding to the target insulation node in the standard image of the target insulation node.

[0067] As an example, the target area can be implemented by obtaining the outer contour identification points of the target area corresponding to the target insulation node in the standard image, and constructing the target area based on the outer contour identification points; wherein the outer contour identification points are identified using artificial intelligence recognition technology.

[0068] It should be noted that the artificial intelligence recognition technology is to establish an outer contour identification point model using an artificial neural network method, and to train the outer contour identification point model using a standard image. The outline identification point is an inflection point, which can be set according to the user's range.

[0069] As an example, constructing the target area based on the outer contour identification points can be implemented through the following steps: establishing a pixel coordinate system based on the standard image, and taking the point in the upper left corner of the standard image as the origin; assigning a first function to each of the outer contour identification points to obtain a first parameter; identifying the maximum value and the minimum value among multiple first parameters as the contour starting point and the contour end point of the target image respectively; taking the contour starting point and the contour end point as the starting point and the pixel coordinates of the contour identification points and sorting them in a clockwise direction; connecting two adjacent contour identification points after sorting to form the target area.

[0070] As an example, the first function may be:

[0071] (point.y*imgW)+(point.x+1)

[0072] Among them, point.y represents the coordinate of the pixel point along the Y axis in the pixel coordinate system, point.x represents the coordinate of the pixel point along the X axis in the pixel coordinate system, and imgW represents the width of the original image.

[0073] In an embodiment of the present invention, the method further includes acquiring pixel points in the target area in the standard image, and generating the foreground model according to the pixel points in the target area.

[0074] In an embodiment of the present invention, the specific process of the step of "obtaining pixel points in the target area in the standard image, and generating the foreground model according to the pixel points in the target area" can be further explained in combination with the following description.

[0075] As an example, the background model can be obtained by obtaining the pixel points in the target area in the standard image as the first pixel point set, performing cluster analysis according to the color value of each pixel point in the first pixel point set, and obtaining at least one first category. For each first category, the first weight corresponding to the first category is obtained, and the first Gaussian distribution model is determined according to the color value of each pixel point in the first category; and the foreground model is determined by weighted summation according to the determined first Gaussian distribution models and the obtained first weights.

[0076] As an example, the first category can be implemented by classifying pixels with color differences less than a preset color difference into one category, or dividing the first pixel set into a preset number of first categories. The clustering analysis method can be determined according to the prior art, and the present invention does not limit this.

[0077] As an optional example, the first weight may be determined according to one of the following methods; for example, the ratio of the number of pixels included in the first category to the number of pixels in the first pixel set is used as the first weight corresponding to the first category.

[0078] In a specific implementation, the first category A includes 10 pixels, and the first pixel set includes 100 pixels, and the first weight corresponding to the first category A is 0.1 (ie, 10 / 100).

[0079] As another optional example, the first weight may be determined according to one of the following methods; such as calculating the average color difference of the pixels included in each first category, and calculating the sum of the average color differences of all first categories; for each first category, subtracting the average color difference of the first category from the sum to obtain a difference, and using the ratio of the difference to the sum as the first weight corresponding to the first category.

[0080] In a specific implementation, after cluster analysis of the first pixel set, three first categories are obtained, which are numbered as category 1, category 2 and category 3. The average color difference of the pixels included in category 1 is a; the average color difference of the pixels included in category 2 is b; the average color difference of the pixels included in category 3 is c; then the sum is (a+b+c) (that is, H), and for category 1, its corresponding first weight is (Ha) / H. Similarly, for category 2, its corresponding first weight is (Hb) / H; for category 3, its corresponding first weight is (Hc) / H.

[0081] As an example, the Gaussian distribution model can be implemented using the maximum likelihood estimation method, specifically by determining the Gaussian distribution model, that is, determining the mean and variance of the Gaussian distribution. The maximum likelihood estimation method is used to determine the mean and variance of the Gaussian distribution model. It can also be determined according to the existing technical methods, and the present invention is not limited to this.

[0082] As an example, the foreground module may be determined according to the following formula:

[0083]

[0084] In the formula, f represents the foreground model; i represents the i-th first category; λ i represents the first weight corresponding to the i-th first category; Represents the Gaussian distribution model corresponding to the i-th first category.

[0085] In one embodiment of the present invention, the specific process of the step of "generating the current image of the target insulation node based on the real-time image and the foreground model corresponding to the target insulation node and the background model corresponding to the target insulation node" can be further explained in combination with the following description.

[0086] As described in the following steps, a second probability that each pixel point in the real-time image belongs to outside the target area is determined according to the background model and the real-time image.

[0087] In one embodiment of the present invention, the method further includes acquiring pixel points outside the target area in the standard image, and generating the background model according to the pixel points outside the target area.

[0088] In one embodiment of the present invention, the specific process of the step of "obtaining pixel points outside the target area in the standard image, and generating the background model based on the pixel points outside the target area" can be further explained in combination with the following description.

[0089] As an example, the background model can be implemented by the following steps, specifically obtaining pixel points outside the target area in the standard image as a second pixel point set, performing cluster analysis based on the color values ​​of each pixel point in the second pixel point set, and obtaining at least one second category. For each second category, obtain the second weight corresponding to the second category, and determine the second Gaussian distribution model based on the color value of each pixel point in the second category. According to the determined second Gaussian distribution models and the obtained second weights, the background model is determined by weighted summation. Since the construction methods of the foreground model and the background model are the same, they will not be repeated here.

[0090] In one embodiment of the present invention, the specific process of the step of "generating the current image of the target insulation node based on the real-time image and the foreground model corresponding to the target insulation node and the background model corresponding to the target insulation node" can be further explained in combination with the following description.

[0091] As described in the following steps, a current image of the target insulation node is generated according to the first probability, the second probability and the real-time image.

[0092] As an example, for any pixel in the real-time image, if the first probability that the pixel belongs to the target area is greater than the second probability that the pixel belongs to outside the target area, the pixel is regarded as a pixel belonging to the target area; or, for any pixel in the real-time image, if the first probability that the pixel belongs to the target area is greater than a preset probability, the pixel is regarded as a pixel belonging to the target area; or, for any pixel in the real-time image, if the ratio of the first probability that the pixel belongs to the target area to the second probability that the pixel belongs to outside the target area is greater than a preset ratio, the pixel is regarded as a pixel belonging to the target area; or, for any pixel in the real-time image, if the difference between the first probability that the pixel belongs to the target area and the second probability that the pixel belongs to outside the target area is greater than a preset difference, the pixel is regarded as a pixel belonging to the target area, and the pixel belonging to the target area is used as the current image of the target insulation node.

[0093] In one embodiment of the present invention, the specific process of "obtaining the current status data of the target insulation joint, wherein the current status data includes the current image of the target insulation joint, the time point of obtaining the current status data, the location information of the current status data, and the current audio signal generated by tapping the target insulation joint" described in step S110 can be further explained in combination with the following description.

[0094] As described in the following steps, the position information of the target insulation node is acquired, and the current state data of the target insulation node is generated according to the position information of the target insulation node and the current image of the target insulation node.

[0095] It should be noted that the timestamp of the current image of the target insulation node is the acquisition time point, that is, the acquisition time point of the current status data, and the location information is the longitude and latitude coordinates of the target insulation node.

[0096] In one embodiment of the present invention, the specific process of "obtaining the current status data of the target insulation joint, wherein the current status data includes the current image of the target insulation joint, the time point of obtaining the current status data, the location information of the current status data, and the current audio signal generated by tapping the target insulation joint" described in step S110 can be further explained in combination with the following description.

[0097] As described in the following steps, a first audio signal and a second audio signal are generated by tapping the target insulating joint; wherein the time interval between the first audio signal and the second audio signal is a preset time.

[0098] As an example, a first audio signal generated by tapping the target insulating joint is acquired through an audio receiving device, and a second audio signal generated by tapping the target insulating joint is acquired again at a preset time interval of 2s.

[0099] It should be noted that audio signals are regular carriers of frequency and amplitude changes in sound waves. Audio is a continuously changing analog signal that can be represented by a continuous curve, called a sound wave.

[0100] As described in the following steps, the first audio signal and the second audio signal are averaged to obtain an average audio signal.

[0101] As an example, the first audio signal and the second audio signal are respectively graphed, and then the two graphs are overlapped, and the average value of two points is selected to generate a new graph, which is then converted into an average audio signal.

[0102] As described in the following steps, the average audio signal is amplified and subjected to noise reduction processing to obtain the current audio signal.

[0103] As an example, the average audio signal is amplified and then denoised, and the specific steps are: obtaining the amplified average audio signal, the amplified average audio signal includes transient noise; obtaining estimated amplitude data of the current frame signal in the amplified average audio signal, the estimated amplitude data is used to characterize the amplitude estimated for the current frame signal after removing the transient noise; when the estimated amplitude data is less than the minimum amplitude data, adjusting the estimated amplitude data to obtain target amplitude data whose amplitude exceeds the minimum amplitude data, the target amplitude data is used to characterize the amplitude of the target audio signal expected to be obtained after removing the transient noise from the noisy audio signal; the minimum amplitude data is used to characterize the minimum value of the amplitude of the noisy audio signal in each frequency band within the preset time length; and obtaining the current audio signal based on the target amplitude data.

[0104] As described in the above step S120, the image segmentation path corresponding to the target insulation joint is determined according to the position information, and the current segmented image set is generated according to the image segmentation path of the target insulation joint and the current image of the target insulation joint.

[0105] In an embodiment of the present invention, the specific process of "determining the image segmentation path corresponding to the target insulation node according to the position information" in step S120 can be further explained in combination with the following description.

[0106] As described in the following steps, the identification of the target insulation node is determined according to the position information.

[0107] It should be noted that, based on the location information of the current state data, i.e. the latitude and longitude coordinates of the target insulating node, i.e. the location information of the target insulating node, the insulating node at the specific location pre-input into the system is a specific model, thereby obtaining the identification of the target insulating node.

[0108] In an embodiment of the present invention, the specific process of "determining the image segmentation path corresponding to the target insulation node according to the position information" in step S120 can be further explained in combination with the following description.

[0109] As described in the following steps, the image segmentation path of the target insulation node is determined according to the identifier of the target insulation node.

[0110] It should be noted that the image segmentation path of the target insulating node, that is, how to segment the target insulating node, is determined based on the identification of the target insulating node; specifically, each identification represents a different segmentation path of the insulating node, and the segmentation path is segmented based on the component shape of the target insulating node.

[0111] In an embodiment of the present invention, the specific process of "generating a current segmented image set according to the image segmentation path of the target insulation node and the current image of the target insulation node" in step S120 can be further explained in combination with the following description.

[0112] As described in the following steps, the current image of the target insulation joint is segmented into a preset number of current segmented images according to the image segmentation path, and the current segmented images are numbered;

[0113] As described in the following steps, the current segmented image set is generated according to the numbered current segmented images.

[0114] Reference Figure 3 In a specific implementation, the current image of the target insulation node is divided into five segmented images, and they are numbered from top to bottom, 1, 2, 3, 4, and 5 in the figure; and the numbered segmented images are used as the current segmented image set. And the numbered segmented images are stored in the form of an image set (the stored image set is the current segmented image set).

[0115] As described in the above step S130, determine the first difference between each segmented image in the current segmented image set and each corresponding segmented image in the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determine the second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; determine the third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times.

[0116] In one embodiment of the present invention, the specific process of "determining the first difference between each segmented image in the current segmented image set and each segmented image corresponding to the historical segmented image set closest to the current acquisition time point" in step S130 can be further explained in combination with the following description.

[0117] As described in the following steps, image difference values ​​between the current segmented image and the historical segmented image with corresponding numbers in the historical segmented image set closest to the current acquisition time point are determined respectively.

[0118] It should be noted that the image difference value is the difference value of image parameters, and the image parameters include contrast, exposure compensation, color, and appearance characteristics. The image difference obtains the parameter difference value for each image parameter, that is, the contrast difference value, exposure compensation difference value, color difference value, and appearance characteristic difference value are obtained respectively, and then superimposed as the image difference value. And the user can set the image parameters in different application scenarios according to their own needs, which is not limited here.

[0119] In one embodiment of the present invention, the specific process of "determining the first difference between each segmented image in the current segmented image set and each segmented image corresponding to the historical segmented image set closest to the current acquisition time point" in step S130 can be further explained in combination with the following description.

[0120] As described in the following steps, the image difference values ​​are superimposed to generate the first difference situation.

[0121] In a specific implementation, the current segmented image set at the previous acquisition time point is used as the historical segmented image set closest to the current acquisition time point, that is, the current segmented image set when the target insulation node was last acquired by the train is used as the historical segmented image set closest to the current acquisition time point; each segmented image in the historical segmented image set closest to the current acquisition time point is compared one by one with each segmented image in the corresponding current segmented image set to generate five image difference values, that is, these five image difference values ​​are weightedly superimposed as the first difference situation; wherein the weight is the different weights taken in the adjustment calculation.

[0122] As described in the above step S130, the second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets is determined.

[0123] In one embodiment of the present invention, the specific process of "determining the second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets" in step S130 can be further explained in combination with the following description.

[0124] As described in the following steps, image difference values ​​between the historical segmented images corresponding to the numbers in a single historical segmented image set and in the current segmented image set and the current segmented image are determined respectively.

[0125] It should be noted that the image difference value is the difference value of image parameters, and the image parameters include contrast, exposure compensation, color, and appearance characteristics. The image difference obtains the parameter difference value for each image parameter, that is, the contrast difference value, exposure compensation difference value, color difference value, and appearance characteristic difference value are obtained respectively, and then superimposed as the image difference value. And the user can set the image parameters in different application scenarios according to their own needs, which is not limited here.

[0126] In one embodiment of the present invention, the specific process of "determining the second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets" in step S130 can be further explained in combination with the following description.

[0127] As described in the following steps, all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set are superimposed to generate the second comparison difference values ​​respectively.

[0128] In a specific implementation, the current segmented image set of all previous acquisition time points is used as the historical segmented image set, that is, the current segmented image set of all target insulation nodes acquired by the train is used as all historical segmented image sets; in this embodiment, there are twenty previous acquisition time points, that is, there are twenty historical segmented image sets; each segmented image in the twenty historical segmented image sets is compared one by one with each segmented image in the corresponding current segmented image set to generate twenty groups of image difference values, each group of image difference values ​​has five image difference values, that is, these five image difference values ​​are weightedly superimposed as the second difference situation.

[0129] In one embodiment of the present invention, the specific process of "determining the second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets" in step S130 can be further explained in combination with the following description.

[0130] As described in the following steps, the second comparison differences in all historical segmentation image sets are compared, and the second comparison differences with the largest value are taken as the second difference situation.

[0131] In a specific implementation, the twenty historical segmentation image sets, that is, the twenty second comparison difference values, are compared, and the second comparison difference value with the largest value is selected as the second difference situation.

[0132] In one embodiment of the present invention, the specific process of "determining the third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times" in step S130 can be further explained in combination with the following description.

[0133] As described in the following steps, image difference values ​​between the historical segmented images corresponding to the numbers in a single historical segmented image set and in the current segmented image set and the current segmented image are determined respectively.

[0134] It should be noted that the image difference value is the difference value of image parameters, and the image parameters include contrast, exposure compensation, color, and appearance characteristics. The image difference obtains the parameter difference value for each image parameter, that is, the contrast difference value, exposure compensation difference value, color difference value, and appearance characteristic difference value are obtained respectively, and then superimposed as the image difference value. And the user can set the image parameters in different application scenarios according to their own needs, which is not limited here.

[0135] In one embodiment of the present invention, the specific process of "determining the third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times" in step S130 can be further explained in combination with the following description.

[0136] As described in the following steps, all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set are superimposed to generate the third comparison difference values ​​respectively.

[0137] In a specific implementation, the current segmented image set obtained at the previous preset number of acquisition time points, that is, the three preset number of acquisition time points, is used as the historical segmented image set, that is, the current segmented image set of all the first three target insulation nodes obtained by the train is used as each historical segmented image set within the preset number of times, that is, there are three historical segmented image sets; each segmented image in a single historical segmented image set is first compared one by one with each segmented image in the corresponding current segmented image set to generate five image difference values, and these five image difference values ​​are superimposed as the third comparison difference.

[0138] In one embodiment of the present invention, the specific process of "determining the third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times" in step S130 can be further explained in combination with the following description.

[0139] As described in the following steps, the third comparison difference values ​​in each historical segmentation image set within a preset number of times are superimposed as the third difference situation.

[0140] In a specific implementation, the preset number of times is set to three, and the segmented images at the two acquisition time points before the current acquisition time point and the current segmented image at the current acquisition time point are taken together as the historical segmented image set, that is, there are three third comparison differences, and the three third comparison differences are superimposed as the third difference situation.

[0141] As described in the above step S140, a standard audio signal corresponding to the target isolation node is determined according to the position information, and an audio difference is determined according to the current audio signal and the standard audio signal.

[0142] As described in the above step S150, the total difference value is determined based on the first difference situation and / or the second difference situation and / or the third difference situation and the audio difference, and when the total difference value exceeds the preset threshold, the current deformation condition of the target insulation joint is set to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, the weight of the audio difference is set to 20% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation is set to 80%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation; when the audio difference is greater than the audio threshold, the weight of the audio difference is set to 80% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation is set to 20%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation.

[0143] In one embodiment of the present invention, the following description can be combined to further illustrate the specific process of step S150 of "determining the total difference value based on the first difference situation and / or the second difference situation and / or the third difference situation and the audio difference, and when the total difference value exceeds the preset threshold, setting the current deformation condition of the target insulation joint to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, setting the weight of the audio difference to 20% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 80%, and calculating the total difference value based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation; when the audio difference is greater than the audio threshold, setting the weight of the audio difference to 80% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation to 20%, and calculating the total difference value based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation."

[0144] In a first specific implementation, when the audio difference is less than or equal to the audio threshold, if the audio threshold is set to 50 and the audio difference is 40, the weight of the audio difference is set to 20%, and the weight of the first difference situation is set to 80%, and the total difference value is calculated based on the weight of the audio difference and the weight of the first difference situation; and when the total difference value exceeds a preset threshold, the current deformation condition of the target insulation joint is set to be repaired.

[0145] In a second specific implementation, when the audio difference is less than or equal to the audio threshold, if the audio threshold is set to 50 and the audio difference is 60, the weight of the audio difference is set to 80%, and the weight of the first difference situation is set to 20%, and the total difference value is calculated based on the weight of the audio difference and the weight of the first difference situation; and when the total difference value exceeds a preset threshold, the current deformation condition of the target insulation joint is set to be repaired.

[0146] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0147] Reference Figure 2 , shows a railway insulation joint detection device provided by an embodiment of the present application, which specifically includes the following modules:

[0148] Current state data acquisition module 210: used to acquire current state data of the target insulation joint, wherein the current state data includes a current image of the target insulation joint, a time point of acquiring the current state data, location information of the current state data, and a current audio signal generated by tapping the target insulation joint;

[0149] The current segmented image set generating module 220 is used to determine the image segmentation path corresponding to the target insulation node according to the position information, and generate the current segmented image set according to the image segmentation path of the target insulation node and the current image of the target insulation node;

[0150] The difference determination module 230 is used to determine the first difference between each segmented image in the current segmented image set and each corresponding segmented image in the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determine the second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; determine the third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times;

[0151] An audio difference determination module 240, configured to determine a standard audio signal corresponding to the target isolation node according to the position information, and determine an audio difference according to the current audio signal and the standard audio signal;

[0152] The current deformation condition confirmation module 250 is used to determine the total difference value based on the first difference condition and / or the second difference condition and / or the third difference condition and the audio difference, and when the total difference value exceeds the preset threshold, the current deformation condition of the target insulation joint is set to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, the weight of the audio difference is set to 20% and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition is set to 80%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition; when the audio difference is greater than the audio threshold, the weight of the audio difference is set to 80% and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition is set to 20%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition.

[0153] In one embodiment of the present invention, the current state data acquisition module 210 includes:

[0154] A current image generation submodule, used to obtain a real-time image of the target insulation node, and generate a current image of the target insulation node according to the real-time image and a foreground model corresponding to the target insulation node and a background model corresponding to the target insulation node;

[0155] The current state data generating submodule is used to obtain the position information of the target insulation node, and generate the current state data of the target insulation node according to the position information of the target insulation node and the current image of the target insulation node.

[0156] In a specific implementation, it also includes:

[0157] A target region determination submodule, used to obtain a standard image of the target insulation joint, and determine a target region corresponding to the target insulation joint in the standard image of the target insulation joint;

[0158] A foreground model generation submodule, used to obtain pixel points in the target area in the standard image, and generate the foreground model according to the pixel points in the target area;

[0159] The background model generation submodule is used to obtain pixel points outside the target area in the standard image and generate the background model according to the pixel points outside the target area.

[0160] In a specific implementation, the current image generation submodule includes:

[0161] A first probability determination submodule, configured to determine a first probability that each pixel point in the real-time image belongs to the target area according to the foreground model and the real-time image;

[0162] A second probability determination submodule, configured to determine a second probability that each pixel in the real-time image belongs to outside the target area according to the background model and the real-time image;

[0163] The current image generation submodule of the target insulation node is used to generate the current image of the target insulation node according to the first probability, the second probability and the real-time image.

[0164] An audio signal acquisition submodule is used to generate a first audio signal and a second audio signal by tapping the target insulating joint; wherein the time interval between the first audio signal and the second audio signal is a preset time;

[0165] an average audio signal processing submodule, performing average processing on the first audio signal and the second audio signal to obtain an average audio signal;

[0166] The current audio signal determination submodule obtains the current audio signal after amplifying and noise reduction processing the average audio signal.

[0167] In one embodiment of the present invention, the current segmented image set generating module 220 includes:

[0168] A target insulation node identification determination submodule, used to determine the identification of the target insulation node according to the position information;

[0169] The image segmentation path determination submodule is used to determine the image segmentation path of the target insulation node according to the identifier of the target insulation node.

[0170] An image numbering submodule, used to segment the current image of the target insulation joint into a preset number of current segmented images according to the image segmentation path, and to number the current segmented images;

[0171] The current segmented image set generating submodule is used to generate the current segmented image set according to the numbered current segmented images.

[0172] In one embodiment of the present invention, the difference determination module 230 includes:

[0173] A first image difference value determination submodule, used to respectively determine image difference values ​​between the historical segmented images with corresponding numbers in the historical segmented image set closest to the current acquisition time point and in the current segmented image set and the current segmented image;

[0174] The first difference situation superimposing submodule is used to superimpose the image difference values ​​to generate the first difference situation.

[0175] A second image difference value determination submodule, used to respectively determine image difference values ​​between a historical segmented image corresponding to a number in a single historical segmented image set and in the current segmented image set and the current segmented image;

[0176] A second comparison difference value generating submodule is used to superimpose all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set to generate the second comparison difference values ​​respectively;

[0177] The second difference situation generating submodule is used for comparing the second comparison difference values ​​in all the historical segmentation image sets, and taking the second comparison difference value with the largest value as the second difference situation.

[0178] A third image difference value determination submodule, used to respectively determine image difference values ​​between a historical segmented image corresponding to a number in a single historical segmented image set and in the current segmented image set and the current segmented image;

[0179] A third comparison difference value generating submodule is used to superimpose all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set to generate the third comparison difference values ​​respectively;

[0180] The third difference situation generating submodule is used to superimpose the third comparison difference values ​​in each historical segmentation image set within a preset number of times as the third difference situation.

[0181] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0182] There are repeated operation steps in this specific embodiment and the above specific embodiment, and this specific embodiment is only briefly described. For other solutions, refer to the description of the above specific embodiment.

[0183] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0184] Reference Figure 4, shows a computer device of a railway insulation joint detection method of the present application, which may specifically include the following:

[0185] The computer device 12 is in the form of a general-purpose computing device, and the components of the computer device 12 may include but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 connecting different system components (including the memory 28 and the processing unit 16).

[0186] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, an Audio Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0187] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0188] Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of the various embodiments of the present application.

[0189] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0190] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable an operator to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through the I / O interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) through a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0191] The processing unit 16 executes various functional applications and data processing by running the programs stored in the memory 28, such as implementing a railway insulation joint detection method provided in an embodiment of the present application.

[0192] That is, when the processing unit 16 executes the program, the following is achieved: obtaining the current state data of the target insulation node, wherein the current state data includes the current image of the target insulation node, the acquisition time point of the current state data, and the location information of the current state data; determining the image segmentation path corresponding to the target insulation node based on the location information, and determining to generate the current segmented image set based on the image segmentation path of the target insulation node and the current image of the target insulation node; determining the first difference between each segmented image in the current segmented image set and each segmented image corresponding to the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the image corresponding to the previous acquisition time point. the current segmented image set; and / or; a second difference situation determination module, used to determine the second difference situation of each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; a third difference situation determination module, used to determine the third difference situation of each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times; confirm the current deformation situation of the target insulation joint based on the first difference situation and / or the second difference situation and / or the third difference situation; specifically, when the first difference situation and / or the second difference situation and / or the third difference situation exceeds a preset threshold, the current deformation situation of the target insulation joint is set to be repaired.

[0193] In an embodiment of the present application, the present application further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a railway insulation joint detection method as provided in all embodiments of the present application is implemented.

[0194] That is, when the program is executed by the processor, it is implemented as follows: obtaining the current state data of the target insulation node, wherein the current state data includes the current image of the target insulation node, the acquisition time point of the current state data, and the location information of the current state data; determining the image segmentation path corresponding to the target insulation node based on the location information, and determining to generate the current segmented image set based on the image segmentation path of the target insulation node and the current image of the target insulation node; determining the first difference between each segmented image in the current segmented image set and each segmented image corresponding to the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the segmented image set corresponding to the previous acquisition time point. A current segmented image set; and / or; a second difference situation determination module, used to determine the second difference situation of each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; a third difference situation determination module, used to determine the third difference situation of each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times; confirming the current deformation situation of the target insulation joint based on the first difference situation and / or the second difference situation and / or the third difference situation; specifically, when the first difference situation and / or the second difference situation and / or the third difference situation exceeds a preset threshold, setting the current deformation situation of the target insulation joint to be repaired.

[0195] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0196] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0197] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the operator's computer, partially on the operator's computer, as an independent software package, partially on the operator's computer, partially on the remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the operator's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0198] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0199] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0200] The above is a detailed introduction to a railway insulation joint detection method and device provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A railway insulation joint detection method, the method is used to determine the deformation of the target insulation joint through the real-time image obtained by the monitoring device loaded on the train; wherein, The deformation condition includes needing maintenance or normal, and is characterized by including: Acquire current state data of the target insulation joint, wherein the current state data includes a current image of the target insulation joint, a time point of acquisition of the current state data, location information of the current state data, and a current audio signal generated by tapping the target insulation joint; Determine an image segmentation path corresponding to the target insulation node according to the position information, and generate a current segmented image set according to the image segmentation path of the target insulation node and a current image of the target insulation node; Determine a first difference between each segmented image in the current segmented image set and each corresponding segmented image in the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; determine a second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; determine a third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times; Determine a standard audio signal corresponding to the target isolation node according to the position information, and determine an audio difference degree according to the current audio signal and the standard audio signal; The total difference value is determined based on the first difference situation and / or the second difference situation and / or the third difference situation and the audio difference, and when the total difference value exceeds a preset threshold, the current deformation condition of the target insulation joint is set to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, the weight of the audio difference is set to 20% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation is set to 80%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation; when the audio difference is greater than the audio threshold, the weight of the audio difference is set to 80% and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation is set to 20%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference situation and / or the second difference situation and / or the third difference situation.

2. The railway insulation joint detection method according to claim 1 is characterized in that: The step of obtaining the current status data of the target insulation node includes: Acquire a real-time image of the target insulation node, and generate a current image of the target insulation node according to the real-time image, a foreground model corresponding to the target insulation node, and a background model corresponding to the target insulation node; The position information of the target insulation node is acquired, and the current state data of the target insulation node is generated according to the position information of the target insulation node and the current image of the target insulation node.

3. The railway insulation joint detection method according to claim 2 is characterized in that: Also includes: Acquire a standard image of the target insulating joint, and determine a target area corresponding to the target insulating joint in the standard image of the target insulating joint; Acquire pixel points in the target area in the standard image, and generate the foreground model according to the pixel points in the target area; Pixel points outside the target area in the standard image are acquired, and the background model is generated according to the pixel points outside the target area.

4. The railway insulation joint detection method according to claim 3 is characterized in that: The step of generating a current image of the target insulation node according to the real-time image and a foreground model corresponding to the target insulation node and a background model of the target insulation node comprises: Determining a first probability that each pixel point in the real-time image belongs to the target area according to the foreground model and the real-time image; Determining a second probability that each pixel in the real-time image belongs to outside the target area according to the background model and the real-time image; A current image of the target insulation node is generated according to the first probability, the second probability and the real-time image.

5. The railway insulation joint detection method according to claim 1, characterized in that: The current audio signal is: a first audio signal and a second audio signal generated by striking the target insulating joint; wherein the time interval between the first audio signal and the second audio signal is a preset time; Averaging the first audio signal and the second audio signal to obtain an average audio signal; The average audio signal is amplified and subjected to noise reduction processing to obtain the current audio signal.

6. The railway insulation joint detection method according to claim 1, characterized in that: The step of generating a current segmented image set according to the image segmentation path of the target insulation node and the current image of the target insulation node comprises: Segmenting the current image of the target insulation joint into a preset number of current segmented images according to the image segmentation path, and numbering the current segmented images; The current segmented image set is generated according to the numbered current segmented images.

7. The railway insulation joint detection method according to claim 6, characterized in that: The step of determining a first difference between each segmented image in the current segmented image set and each segmented image corresponding to a historical segmented image set closest to the current acquisition time point comprises: respectively determining image difference values ​​between the historical segmented images with corresponding numbers in the historical segmented image set closest to the current acquisition time point and in the current segmented image set and the current segmented image; The image difference values ​​are superimposed to generate the first difference condition.

8. The railway insulation joint detection method according to claim 6, characterized in that: The step of determining the second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets comprises: determining the image difference value between the historical segmented image in a single historical segmented image set and the current segmented image set with the corresponding number; Superimposing all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set, respectively generating second comparison difference values; The second comparison differences in all historical segmentation image sets are compared, and the second comparison difference with the largest value is taken as the second difference situation.

9. The railway insulation joint detection method according to claim 6, characterized in that: The step of determining a third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times comprises: respectively determining image difference values ​​between historical segmented images corresponding to numbers in a single historical segmented image set and in the current segmented image set and the current segmented image; Superimposing all image difference values ​​of each historical segmented image in a single historical image set and each current segmented image in a current segmented image set, respectively generating third comparison difference values; The third comparison differences in each historical segmented image set within a preset number of times are superimposed as a third difference situation.

10. A railway insulation joint detection device, the device is used to determine the deformation of the target insulation joint through the real-time image obtained by the monitoring device loaded on the train; wherein, The deformation condition includes needing maintenance or normal, and is characterized by including: A current state data acquisition module, used to acquire the current state data of the target insulation joint, wherein the current state data includes a current image of the target insulation joint, a time point of acquiring the current state data, location information of the current state data, and a current audio signal generated by tapping the target insulation joint; A current segmented image set generating module, used to determine an image segmentation path corresponding to the target insulation joint according to the position information, and to generate a current segmented image set according to the image segmentation path of the target insulation joint and a current image of the target insulation joint; a difference determination module, for determining a first difference between each segmented image in the current segmented image set and each corresponding segmented image in the historical segmented image set closest to the current acquisition time point; wherein the historical segmented image set closest to the current acquisition time point is the current segmented image set corresponding to the previous acquisition time point; and / or; a second difference determination module, for determining a second difference between each segmented image in the current segmented image set and each corresponding segmented image in all historical segmented image sets; and / or; a third difference determination module, for determining a third difference between each segmented image in the current segmented image set and each corresponding segmented image in each historical segmented image set within a preset number of times; an audio difference determination module, configured to determine a standard audio signal corresponding to the target isolation node according to the position information, and determine an audio difference according to the current audio signal and the standard audio signal; A current deformation condition confirmation module is used to determine the total difference value based on the first difference condition and / or the second difference condition and / or the third difference condition and the audio difference, and when the total difference value exceeds a preset threshold, set the current deformation condition of the target insulation joint to be repaired; specifically, when the audio difference is less than or equal to the audio threshold, the weight of the audio difference is set to 20% and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition is set to 80%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition; when the audio difference is greater than the audio threshold, the weight of the audio difference is set to 80% and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition is set to 20%, and the total difference value is calculated based on the weight of the audio difference and the sum of the weights of the first difference condition and / or the second difference condition and / or the third difference condition.

Images