Longitudinal displacement and locking rail temperature image monitoring and detecting method and device for continuously welded rail track

Abstract

The invention relates to a method and a device for monitoring and detecting longitudinal displacement and locking rail temperature images of a seamless track steel rail. The method comprises the following steps of: acquiring a plurality of steel rail images of a seamless track unit rail section by using a track detection vehicle; constructing an image splicing model to obtain a fused steel rail image; constructing a longitudinal displacement monitoring model, and inputting the fused steel rail image into the longitudinal displacement monitoring model to obtain the longitudinal displacement of the steel rail; and according to the longitudinal displacement of the steel rail, the actual locking rail temperature of the seamless track unit rail section is calculated. The method does not depend on observation point monitoring equipment or manual field measurement, the detection cost is reduced, and the detection convenience and applicability are improved.

Description

Technical Field

[0001] The present application relates to the field of seamless rail displacement and locked rail temperature measurement, and in particular to a method and device for image monitoring and detection of seamless line rail longitudinal displacement and locked rail temperature. Background Art

[0002] A seamless rail is a long rail without joints. It uses welding technology to connect shorter rails into continuous tracks of several kilometers. This design can reduce the number of rail joints, improve the stability and comfort of the rail, and reduce maintenance workload. The actual locking rail temperature of a seamless rail refers to the ambient temperature when the seamless rail is laid and locked to the sleeper. It determines the initial thermal state of the rail and is the benchmark for evaluating the thermal expansion and contraction behavior of the rail.

[0003] Measuring the actual locked rail temperature is crucial to the safety and efficiency of railway transportation. Excessively high temperatures may cause the rails to expand, causing deformation, cracking, bending, and even derailment accidents. When the temperature is too low, the rails are susceptible to frost heave and other effects, which will also have a negative impact on the safety of the line. By locking the rail temperature on a seamless line, the rail temperature can be monitored and adjusted in a timely manner to ensure the safe operation of the line. Moreover, changes in rail temperature can cause the line to expand and contract, which in turn affects the geometry and position of the rail. If the rail temperature changes too much, the gap between the rail and other facilities will be too large or too small, increasing the workload of maintenance and adjustment, and may also cause increased wear on the line.

[0004] In the method of measuring the actual locking rail temperature, the displacement of the rail can be used for calculation. However, traditional measurement methods such as the manual wire pulling method of the displacement observation pile, the optical instrument observation method of the displacement observation pile, and the laser measurement of the longitudinal displacement of the rail have the problem of poor measurement accuracy and cannot meet the needs of high-speed railway high-efficiency and high-precision measurement work. At the same time, each measuring point needs to be installed with monitoring equipment. The number of monitoring equipment directly affects the cost, which is relatively high. Moreover, on the kilometer-level span bridge, due to the complexity of the seamless line and the large additional force, the existing testing methods cannot obtain the real and accurate actual locking rail temperature of the line.

[0005] Therefore, designing an accurate and convenient seamless line rail longitudinal displacement and locked rail temperature image monitoring and detection method is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0006] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method and device for monitoring and detecting the longitudinal displacement and locked rail temperature of a seamless line rail. A track inspection vehicle is used to collect images of seamless line rails, and the longitudinal displacement of the rails is obtained by splicing and analyzing the rail images. The actual locked rail temperature is determined by the longitudinal displacement of the rails, thereby improving the accuracy of the actual locked rail temperature detection of the rails, achieving convenience in detection, and reducing the cost of detection.

[0007] The present application first discloses a method for monitoring and detecting the longitudinal displacement of a seamless rail and the locked rail temperature image, and the specific steps are as follows: Step 1: Use a track inspection vehicle to collect multiple rail images of a seamless track unit section; Step 2, constructing an image stitching model, inputting the multiple rail images into the image stitching model, the image stitching model includes a feature extraction module, a feature description module, a feature matching module and a feature fusion module, the feature fusion module divides the overlapping area of ​​the stitching image into a plurality of units of equal size, calculates the weight coefficient of the center point of each unit, and processes each pixel in the unit using the weight coefficient to obtain a fused rail image; Step 3, construct a longitudinal displacement monitoring model, input the fused rail image into the longitudinal displacement monitoring model, and obtain the longitudinal displacement of the rail. The longitudinal displacement monitoring model includes an encoder and a decoder. The fused rail image and the reference rail image are respectively input into two channels of the encoder, each of which includes a feature extraction layer, a first encoding layer, and a second encoding layer connected in sequence. The outputs of the two channels are input into the mutual information layer to obtain a mutual information feature map. The mutual information feature map is input into the interactive enhancement layer after passing through the third encoding layer and the fourth encoding layer. The decoder includes a first decoding layer, a second decoding layer, a third decoding layer, and a fourth decoding layer connected in sequence. The output of the interactive enhancement layer and the output of the third encoding layer are input into the first decoding layer, and the mutual information feature map is input into the second decoding layer. The outputs of the first encoding layers of the two channels are merged and input into the second decoding layer. The outputs of the feature extraction layers of the two channels are merged and input into the first decoding layer. The output of the first decoding layer passes through a 1×1 convolution layer and outputs the longitudinal displacement of the rail. Step 4: Calculate the actual locking rail temperature of the seamless line unit rail section according to the longitudinal displacement of the rail.

[0008] Preferably, the feature extraction module uses the SURF algorithm to extract feature points of the multiple rail images, the feature description module uses the BRISK algorithm to generate feature point descriptors, the feature matching module uses the NNDR algorithm to perform bidirectional coarse matching on the feature point descriptors, and uses the MSAC algorithm to eliminate erroneous matching points to obtain a spliced ​​image.

[0009] Preferably, the feature fusion module divides the overlapping area of ​​the spliced ​​image into a plurality of units of equal size, calculates the weight coefficient of the center point of each unit, and processes each pixel in the unit using the weight coefficient, including: The feature fusion module divides the overlapping area into a plurality of units of equal size, and calculates the weight coefficient of the center point of each unit, and the weight coefficient is: in, is the weight coefficient, x is the coordinate of the center point, and They are the starting and ending coordinates of the overlapping area respectively; Use the weight coefficient of the center point as the weight coefficient of each pixel in the entire unit, and perform separate weight coefficient calculations or appropriately sized units for pixels that are close to the edge of the overlapping area and have not entered the unit; The feature fusion module processes each pixel in the unit of the overlapping area, which is expressed as: in, is the weight coefficient, is the overlapping area image, and are the two images to be stitched.

[0010] Preferably, the feature extraction layer includes a 7×7 convolutional layer and two 3×3 convolutional layers connected in sequence, and the 7×7 convolutional layer and the two 3×3 convolutional layers are spliced ​​to output a multi-level feature map; The mutual information layer uses a local window of a preset size to slide on the feature maps output by the two channels with a preset step length and extracts local feature vectors, calculates the mutual information of the local feature vector pairs corresponding to the same position of the local window on the two feature maps, and forms a matrix of the mutual information values ​​between all the local feature vector pairs to obtain the mutual information feature map; The interactive enhancement layer includes two parallel branches, wherein the first branch includes a linear layer, a depth-separable convolutional layer, a selection scanning module and an activation layer connected in sequence, and the second branch includes a channel attention layer and a spatial attention layer connected in sequence. The feature maps output by the fourth encoding layer are respectively input to the two branches, and the outputs of the two branches are subjected to aggregation and linear layers to obtain enhanced feature maps.

[0011] Preferably, the first encoding layer, the second encoding layer, the third encoding layer and the fourth encoding layer are composed of a depth-separable convolution layer, an activation layer, a two-dimensional convolution layer, a batch normalization layer and a maximum pooling layer, and the first decoding layer, the second decoding layer, the third decoding layer and the fourth decoding layer are composed of a deconvolution layer, a splicing layer, a two-dimensional convolution layer, an activation layer and a batch normalization layer.

[0012] Preferably, the calculating the actual locking rail temperature of the seamless line unit rail section according to the longitudinal displacement of the rail includes: The actual locking rail temperature calculation formula is: Among them, Ts is the actual locked rail temperature, T is the on-site measured rail temperature, Δl is the longitudinal displacement of the rail, l is the length of the seamless line unit rail section, and α is the rail expansion coefficient.

[0013] On the other hand, the present application also provides a seamless line rail longitudinal displacement and locked rail temperature image monitoring and detection device, the device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned seamless line rail longitudinal displacement and locked rail temperature image monitoring and detection method.

[0014] The present application proposes a method and device for monitoring and detecting the longitudinal displacement and locked rail temperature of a seamless line rail. A rail inspection vehicle is used to collect rail images, which does not rely on observation point monitoring equipment or manual on-site measurement, thereby reducing the cost of detection and improving the convenience and applicability of detection; an image stitching model is constructed to improve the accuracy of image stitching and the image quality of the overlapping area of ​​image stitching, thereby providing accurate data for subsequent longitudinal displacement analysis; a longitudinal displacement monitoring model is constructed to improve the performance of displacement measurement by using mutual information layers and interactive enhancement layers, thereby improving the accuracy of measured displacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart of a method for monitoring and detecting longitudinal displacement of a seamless railway rail and locked rail temperature images provided by an exemplary embodiment of the present invention; Figure 2 A schematic structural diagram of a longitudinal displacement monitoring model provided by an exemplary embodiment of the present invention; Figure 3 A schematic diagram of the structure of an interactive enhancement layer provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0016] The detailed description set forth below in conjunction with the accompanying drawings is intended to be a description of various exemplary embodiments of the present invention, and is not intended to represent the only embodiment that can practice the present invention. For the purpose of providing a thorough understanding of the present invention, the detailed description includes specific details. However, it is apparent to those skilled in the art that the present invention can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid blurring the concept of the present invention.

[0017] Example 1 This embodiment provides a method for monitoring and detecting the longitudinal displacement of a seamless rail and the locked rail temperature image. Figure 1 As shown, the method provided in this embodiment includes the following steps: Step 1: Use a track inspection vehicle to collect multiple rail images of a seamless line unit track section.

[0018] Among them, the existing rail longitudinal displacement monitoring usually uses visual acquisition equipment fixedly installed at the monitoring point to collect rail images. Due to the huge scale of the railway network, the number of visual acquisition equipment will be huge, which will bring huge monitoring costs. At the same time, manual on-site measurements can also be used, which also brings a lot of manpower consumption and reduced inspection efficiency and accuracy. The track inspection vehicle is a special type of railway vehicle, mainly used to detect the track status to evaluate the track quality. The track inspection vehicle can quickly and accurately obtain the image data of the rail. Therefore, using the track inspection vehicle to collect rail images as the basis for the longitudinal displacement of the rail and the actual locked rail temperature will reduce the use of fixed monitoring point equipment and manpower consumption, thereby reducing monitoring costs and improving detection accuracy.

[0019] Step 2: construct an image stitching model, input the multiple rail images into the image stitching model, the image stitching model includes a feature extraction module, a feature description module, a feature matching module and a feature fusion module, the feature fusion module divides the overlapping area of ​​the stitching image into a plurality of units of equal size, calculates the weight coefficient of the center point of each unit, and processes each pixel in the unit using the weight coefficient to obtain a fused rail image.

[0020] Among them, the track inspection vehicle is limited by the installation position of its CCD camera. It can only collect partial images of the seamless line unit rail section at a time, and cannot collect the image of the entire rail section at one time. Therefore, the track inspection vehicle will collect multiple continuous rail images, and these rail images are spliced ​​together to form the image of the entire track section.

[0021] Step 3: Construct a longitudinal displacement monitoring model, such as Figure 2As shown, the fused rail image is input into the longitudinal displacement monitoring model to obtain the longitudinal displacement of the rail. The longitudinal displacement monitoring model includes an encoder and a decoder. The fused rail image and the reference rail image are respectively input into two channels of the encoder. Each channel includes a feature extraction layer, a first encoding layer and a second encoding layer connected in sequence. The outputs of the two channels are input into the mutual information layer to obtain a mutual information feature map. The mutual information feature map is input into the interactive enhancement layer after passing through the third encoding layer and the fourth encoding layer. The decoder includes a first decoding layer, a second decoding layer, a third decoding layer and a fourth decoding layer connected in sequence. The output of the interactive enhancement layer and the output of the third encoding layer are input into the first decoding layer, the mutual information feature map is input into the second decoding layer, the outputs of the first encoding layers of the two channels are merged and input into the second decoding layer, the outputs of the feature extraction layers of the two channels are merged and input into the first decoding layer, and the output of the first decoding layer passes through a 1×1 convolution layer to output the longitudinal displacement of the rail.

[0022] Step 4: Calculate the actual locking rail temperature of the seamless line unit rail section according to the longitudinal displacement of the rail.

[0023] In step 2, the feature extraction module uses a SURF algorithm to extract feature points of the multiple rail images.

[0024] Among them, the SURF algorithm is an algorithm used for feature detection and matching in the field of computer vision. It has the characteristics of scale-invariance, rotation-invariance, robustness and efficiency, and is widely used in image stitching, object recognition, image registration and other fields.

[0025] The feature description module generates feature point descriptors using the BRISK algorithm to generate binary descriptors to reduce memory usage and improve matching efficiency.

[0026] Among them, the BRISK algorithm is a feature detection and description algorithm for computer vision and image processing. It was proposed by Stefan Leutenegger et al. in 2011 and is widely used in applications that require fast and robust feature matching.

[0027] The feature matching module uses the NNDR algorithm to perform bidirectional rough matching on the feature point descriptors. Since there are still some wrong matching pairs after the preliminary screening, in order to improve the matching accuracy, a bidirectional matching method is used to eliminate the wrong matching point pairs. Specifically, first, the matching pairs are saved after the one-way matching, and then the relationship between the matching image and the original image is exchanged, and reverse matching is performed. The common matching pairs are selected as the final matching results, and the one-way matching point pairs are deleted.

[0028] Among them, the NNDR (Nearest Neighbor Distance Ratio) algorithm is a strategy for feature point matching. It screens matching pairs based on the distance ratio between the nearest neighbor and the second nearest neighbor. The core idea of ​​this method is that if the ratio of the nearest neighbor distance to the second nearest neighbor distance of a feature point is less than a certain threshold, the match is considered reliable.

[0029] The MSAC algorithm is used to eliminate incorrect matching points and obtain a stitched image.

[0030] Among them, the MSAC (Minimum Sample Algorithm for Consensus) algorithm is a robust estimation algorithm for estimating mathematical model parameters from a set of data. It was proposed by Fischler and Bolles in 1981 and is mainly used for geometric estimation problems in computer vision, such as feature point matching, camera calibration, and 3D reconstruction. The core idea of ​​the MSAC algorithm is to find the best model parameters from a set of data that may contain outliers, so as to maximize the consistency between the model and the data.

[0031] In step 2, the traditional image fusion algorithm directly fuses the registered images, which will produce very obvious seams and color differences and seriously cause excessive color unevenness or artifacts. The existing weighted fusion algorithm improves the traditional fusion algorithm. The weight is determined by the distance between the pixel points in the overlapping area and the boundary of the overlapping area, so as to achieve a smooth transition and eliminate seams, as shown below: in, and is the weight coefficient, is the overlapping area image, and are the two images to be stitched, and are the starting and ending coordinates of the overlapping area respectively.

[0032] However, since the intersection of the two weight functions and the inflection point of the fusion function are the same, the overlapping area will have shadows after registration. In addition, the proposed method does not work well when the brightness difference between the two stitched images is large.

[0033] Therefore, in this embodiment, the weight function is adjusted to adapt to the change trend from 1 to 0, and the weight function is optimized by parabolic properties. At the same time, in order to improve the fusion efficiency, a unit-based integrated acceleration strategy is proposed, the overlapping area is divided into multiple units, and the weight coefficient of the center point of each unit is calculated to represent the weight of all pixels in the entire unit. Thus, in the image fusion stage, better effects are shown in the image fusion of different brightness, angles, resolutions and scales, and the ghost and seam problems are effectively solved, thereby providing accurate data for subsequent longitudinal displacement analysis.

[0034] The feature fusion module divides the overlapping area of ​​the stitched image into a plurality of units of equal size, calculates the weight coefficient of the center point of each unit, and processes each pixel in the unit using the weight coefficient, including: The feature fusion module divides the overlapping area into a plurality of units of equal size, and calculates the weight coefficient of the center point of each unit, and the weight coefficient is: in, is the weight coefficient, x is the coordinate of the center point, and They are the starting and ending coordinates of the overlapping area respectively; Use the weight coefficient of the center point as the weight coefficient of each pixel in the entire unit, and perform separate weight coefficient calculations or appropriately sized units for pixels that are close to the edge of the overlapping area and have not entered the unit; The feature fusion module processes each pixel in the unit of the overlapping area, which is expressed as: in, is the weight coefficient, is the overlapping area image, and are the two images to be stitched.

[0035] In step 3, the longitudinal displacement monitoring model contains dual-channel input and mutual information layers, which are used to extract deep feature information of the two rail images and perform fusion and matching. In addition, in order to enhance the feature extraction capability of the network in the encoding stage, a feature extraction module is introduced to extract displacement features of different scales and depths through depthwise separable convolutions of different sizes. At the same time, interactive enhancement layers are added to the longitudinal displacement monitoring model, including a selective scanning module, a channel attention module, and a spatial attention module, to enhance the model's ability to represent feature maps, especially the attention to channels containing rich displacement field information.

[0036] The feature extraction layer includes a 7×7 convolutional layer and two 3×3 convolutional layers connected in sequence, and the 7×7 convolutional layer and the two 3×3 convolutional layers are spliced ​​to output a multi-level feature map.

[0037] The mutual information layer uses a local window of a preset size to slide on the feature maps output by the two channels with a preset step size and extracts local feature vectors, calculates the mutual information of the local feature vector pairs corresponding to the same position of the local window on the two feature maps, and constructs a matrix of the mutual information values ​​between all the local feature vector pairs to obtain the mutual information feature map.

[0038] Among them, mutual information is a concept in information theory that is used to measure the mutual dependence between two random variables. Specifically, mutual information describes the amount of information one random variable contains about another random variable. The larger the value of mutual information, the stronger the dependence between the two variables; the smaller the value of mutual information, the weaker the dependence between the two variables.

[0039] The interactive enhancement layer includes two parallel branches, such as Figure 3 As shown, the first branch includes a linear layer, a depth-separable convolutional layer, a selection scanning module and an activation layer connected in sequence, the second branch includes a channel attention layer and a spatial attention layer connected in sequence, the feature maps output by the fourth encoding layer are respectively input to the two branches, and the outputs of the two branches are subjected to aggregation and linear layers to obtain enhanced feature maps.

[0040] Among them, the interaction enhancement layer aims to integrate global and local information processing capabilities, screen features through channel and spatial attention mechanisms, highlight important features and suppress unimportant information, and achieve efficient feature extraction at a lower computational cost.

[0041] The selective scanning module is the SSM (Selective Scan Module), which is a two-dimensional state-space model in the Mamba architecture. It can capture the dependency between any two points in the image by performing selective scanning in four directions. It has linear time complexity when capturing dependencies, which means it can process large-scale image data while maintaining computational efficiency.

[0042] Preferably, the first encoding layer, the second encoding layer, the third encoding layer and the fourth encoding layer are composed of a depth-separable convolution layer, an activation layer, a two-dimensional convolution layer, a batch normalization layer and a maximum pooling layer, and the first decoding layer, the second decoding layer, the third decoding layer and the fourth decoding layer are composed of a deconvolution layer, a splicing layer, a two-dimensional convolution layer, an activation layer and a batch normalization layer.

[0043] In step 4, thermal expansion and contraction of rails refers to the phenomenon that rails expand when the temperature rises and contract when the temperature drops. This physical property of rails can be quantified by the linear expansion coefficient (α), which represents the change in length of a unit length of rail when the temperature changes by 1°C. For rails, the linear expansion coefficient is usually around 12 μm / m·°C, which means that the length of each meter of rail changes by about 12 μm when the temperature changes by 1°C.

[0044] The locked rail temperature refers to the temperature of the rail when it is laid, at which time the length of the rail is considered to be the standard length. When the actual temperature deviates from the locked rail temperature, the rail will move longitudinally.

[0045] Calculating the actual locking rail temperature of the seamless line unit rail section according to the longitudinal displacement of the rail includes: The actual locking rail temperature calculation formula is: Among them, Ts is the actual locked rail temperature, T is the on-site measured rail temperature, Δl is the longitudinal displacement of the rail, l is the length of the seamless line unit rail section, and α is the rail expansion coefficient.

[0046] Example 2 This embodiment provides a seamless railway rail longitudinal displacement and locked rail temperature image monitoring and detection device, the device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned seamless line rail longitudinal displacement and locked rail temperature image monitoring and detection method.

[0047] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for monitoring and detecting the longitudinal displacement and locked rail temperature of a seamless railway rail, characterized in that: The method comprises: Step 1: Use a track inspection vehicle to collect multiple rail images of a seamless track unit section; Step 2, constructing an image stitching model, inputting the multiple rail images into the image stitching model, the image stitching model includes a feature extraction module, a feature description module, a feature matching module and a feature fusion module, the feature fusion module divides the overlapping area of ​​the stitching image into a plurality of units of equal size, calculates the weight coefficient of the center point of each unit, and processes each pixel in the unit using the weight coefficient to obtain a fused rail image; Step 3, construct a longitudinal displacement monitoring model, input the fused rail image into the longitudinal displacement monitoring model, and obtain the longitudinal displacement of the rail. The longitudinal displacement monitoring model includes an encoder and a decoder. The fused rail image and the reference rail image are respectively input into two channels of the encoder, each of which includes a feature extraction layer, a first encoding layer, and a second encoding layer connected in sequence. The outputs of the two channels are input into the mutual information layer to obtain a mutual information feature map. The mutual information feature map is input into the interactive enhancement layer after passing through the third encoding layer and the fourth encoding layer. The decoder includes a first decoding layer, a second decoding layer, a third decoding layer, and a fourth decoding layer connected in sequence. The output of the interactive enhancement layer and the output of the third encoding layer are input into the first decoding layer, and the mutual information feature map is input into the second decoding layer. The outputs of the first encoding layers of the two channels are merged and input into the second decoding layer. The outputs of the feature extraction layers of the two channels are merged and input into the first decoding layer. The output of the first decoding layer passes through a 1×1 convolution layer and outputs the longitudinal displacement of the rail. Step 4: Calculate the actual locking rail temperature of the seamless line unit rail section according to the longitudinal displacement of the rail.

2. The method according to claim 1, characterized in that The feature extraction module uses the SURF algorithm to extract feature points of the multiple rail images, the feature description module uses the BRISK algorithm to generate feature point descriptors, the feature matching module uses the NNDR algorithm to perform bidirectional rough matching on the feature point descriptors, and uses the MSAC algorithm to eliminate erroneous matching points to obtain a spliced ​​image.

3. The method according to claim 1, characterized in that The feature fusion module divides the overlapping area of ​​the stitched image into a plurality of units of equal size, calculates the weight coefficient of the center point of each unit, and processes each pixel in the unit using the weight coefficient, including: The feature fusion module divides the overlapping area into a plurality of units of equal size, and calculates the weight coefficient of the center point of each unit, and the weight coefficient is: in, is the weight coefficient, x is the coordinate of the center point, and They are the starting and ending coordinates of the overlapping area respectively; Use the weight coefficient of the center point as the weight coefficient of each pixel in the entire unit, and perform separate weight coefficient calculations or appropriately sized units for pixels that are close to the edge of the overlapping area and have not entered the unit; The feature fusion module processes each pixel in the unit of the overlapping area, which is expressed as: in, is the weight coefficient, is the overlapping area image, and are the two images to be stitched.

4. The method according to claim 1, characterized in that The feature extraction layer includes a 7×7 convolutional layer and two 3×3 convolutional layers connected in sequence, and the 7×7 convolutional layer and the two 3×3 convolutional layers are spliced ​​to output a multi-level feature map; The mutual information layer uses a local window of a preset size to slide on the feature maps output by the two channels with a preset step length and extracts local feature vectors, calculates the mutual information of the local feature vector pairs corresponding to the same position of the local window on the two feature maps, and forms a matrix of the mutual information values ​​between all the local feature vector pairs to obtain the mutual information feature map; The interactive enhancement layer includes two parallel branches, wherein the first branch includes a linear layer, a depth-separable convolutional layer, a selection scanning module and an activation layer connected in sequence, and the second branch includes a channel attention layer and a spatial attention layer connected in sequence. The feature maps output by the fourth encoding layer are respectively input to the two branches, and the outputs of the two branches are subjected to aggregation and linear layers to obtain enhanced feature maps.

5. The method according to claim 1, characterized in that The first encoding layer, the second encoding layer, the third encoding layer and the fourth encoding layer are composed of a depthwise separable convolution layer, an activation layer, a two-dimensional convolution layer, a batch normalization layer and a maximum pooling layer, and the first decoding layer, the second decoding layer, the third decoding layer and the fourth decoding layer are composed of a deconvolution layer, a splicing layer, a two-dimensional convolution layer, an activation layer and a batch normalization layer.

6. The method according to claim 1, characterized in that Calculating the actual locking rail temperature of the seamless line unit rail section according to the longitudinal displacement of the rail includes: The actual locking rail temperature calculation formula is: Among them, Ts is the actual locked rail temperature, T is the on-site measured rail temperature, Δl is the longitudinal displacement of the rail, l is the length of the seamless line unit rail section, and α is the rail expansion coefficient.

7. A seamless railway rail longitudinal displacement and locked rail temperature image monitoring and detection device, characterized in that: The device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a method for monitoring and detecting the longitudinal displacement and locked rail temperature of a seamless line rail as described in any one of claims 1 to 6.

Images