CN112132227B - Bridge train load action time course extraction method and device and terminal equipment - Google Patents
Bridge train load action time course extraction method and device and terminal equipment Download PDFInfo
- Publication number
- CN112132227B CN112132227B CN202011064690.9A CN202011064690A CN112132227B CN 112132227 B CN112132227 B CN 112132227B CN 202011064690 A CN202011064690 A CN 202011064690A CN 112132227 B CN112132227 B CN 112132227B
- Authority
- CN
- China
- Prior art keywords
- matching
- image
- image data
- target
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000009471 action Effects 0.000 title claims abstract description 60
- 238000000605 extraction Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000006471 dimerization reaction Methods 0.000 claims abstract description 27
- 238000004590 computer program Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 10
- 230000000877 morphologic effect Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 5
- 229910000831 Steel Inorganic materials 0.000 description 12
- 230000003068 static effect Effects 0.000 description 12
- 239000010959 steel Substances 0.000 description 12
- 230000036541 health Effects 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 11
- 238000006073 displacement reaction Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000036449 good health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000013077 target material Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Abstract
The invention provides a method, a device and terminal equipment for extracting a bridge train load action time course, wherein the method comprises the following steps: acquiring first image data corresponding to a first target and second image data corresponding to a second target; determining the starting moment of the train load according to the second image data, and respectively determining a first template image of the first target and a second template image of the second target based on the starting moment of the train load; matching the first image data with the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence; matching the second image data with the second template image, and performing dimerization processing on the matching result to obtain a second matching sequence; and determining the time course of the bridge train loading action based on the first matching sequence and the second matching sequence. The method, the device and the terminal equipment for extracting the time course of the bridge train loading effect can reduce the time course extraction cost of the train loading effect and improve the time course extraction precision.
Description
Technical Field
The invention belongs to the technical field of bridge structure health monitoring, and particularly relates to a bridge train load action time course extraction method, device and terminal equipment.
Background
The bridge is used as a large-scale structure on a traffic line, and has important significance on ensuring the safety and smoothness of line transportation by ensuring that the bridge maintains a good health state in an operation period. In order to ensure the safe operation of the bridge and avoid serious accidents, a bridge health monitoring system for health monitoring of bridge structures has been developed. The existing bridge health monitoring system comprises a large number of data acquisition devices, and in the bridge service process, the data acquisition devices can acquire a large number of monitoring data at any time, and the bridge health monitoring system analyzes various responses of a bridge structure under the action of train load according to the acquired monitoring data under the action of train load so as to evaluate the health state of the bridge structure. How to extract the bridge train load action time course is an important precondition for analyzing the health state of the bridge structure.
At present, in a bridge health monitoring system, the most commonly used train load action time course extraction technology is magnetic steel triggering, and the basic principle is as follows: the magnetic steel is arranged on the train guide rail, when a train passes through the magnetic steel, the magnetic steel is excited to output positive pulses, and when the train is far away from the magnetic steel, the output of the magnetic steel is 0V, and the bridge health monitoring system determines the time course of the train load action by judging the change of the pulse signals output by the magnetic steel. However, the existing magnetic steel triggering technology is simple in principle, direct and effective, but in practical application, because the magnetic steel needs workers to be installed on a train guide rail, and a magnetic steel signal cable paved on site is easily damaged in later operation and maintenance, the cost of manpower and material resources is high.
Disclosure of Invention
The invention aims to provide a bridge train loading time course extraction method, device and terminal equipment, which are used for solving the problem of higher extraction cost of the bridge train loading time course in the prior art.
In a first aspect of the embodiment of the present invention, a method for extracting a bridge train load action time course is provided, including:
acquiring first image data corresponding to a first target and second image data corresponding to a second target, wherein the first target and the second target are respectively arranged at two ends of a target beam body, the first target corresponds to one end of a fixed support of the target beam body, and the second target corresponds to one end of a movable support of the target beam body;
determining the starting moment of the train load according to the second image data, determining a first template image based on the starting moment of the train load and the first image data, and determining a second template image based on the starting moment of the train load and the second image data;
matching the first image data with the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence; matching the second image data with the second template image, and performing dimerization processing on the matching result to obtain a second matching sequence;
and determining the time course of the bridge train loading action based on the first matching sequence and the second matching sequence.
In a second aspect of the embodiment of the present invention, there is provided a bridge train load action schedule extraction apparatus, including:
the data acquisition module is used for acquiring first image data corresponding to a first target and second image data corresponding to a second target, wherein the first target and the second target are respectively arranged at two ends of a target beam body, the first target corresponds to one end of a fixed support of the target beam body, and the second target corresponds to one end of a movable support of the target beam body;
the template determining module is used for determining the starting moment of the train load according to the second image data, determining a first template image based on the starting moment of the train load and the first image data, and determining a second template image based on the starting moment of the train load and the second image data;
the image matching module is used for matching the first image data with the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence; matching the second image data with the second template image, and performing dimerization processing on the matching result to obtain a second matching sequence;
and the time course determining module is used for determining the time course of the bridge train load action based on the first matching sequence and the second matching sequence.
In a third aspect of the embodiment of the present invention, a terminal device is provided, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the steps of the bridge train load action time interval extraction method described above are implemented when the processor executes the computer program.
In a fourth aspect of the embodiments of the present invention, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the bridge train loading time course extraction method described above.
The bridge train load action time course extraction method, the device and the terminal equipment provided by the embodiment of the invention have the beneficial effects that:
1) The bridge train load action time course extraction method provided by the embodiment of the invention does not need to install magnetic steel on site to extract the time course of train load action, and can be realized only by means of the data acquisition device in the existing bridge health monitoring system, so that the cost of manpower and material resources is effectively reduced.
2) The method for extracting the bridge train load action time course provided by the embodiment of the invention determines the movement condition of the target in a clustering processing mode, and has higher accuracy compared with the method for judging the movement condition of the target by using a simple threshold analysis method.
3) According to the embodiment of the invention, the bridge train load action time course extraction is performed through the image data of the two targets, so that the robustness is better.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for extracting a bridge train loading action time course according to an embodiment of the invention;
FIG. 2 is a block diagram of a bridge train loading time course extraction device according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of a terminal device according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a red target mark according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating the installation of a red target mark according to an embodiment of the present invention;
FIG. 6 is a schematic diagram showing the relative positions of a target and a camera according to an embodiment of the present invention;
fig. 7 is a schematic drawing illustrating extraction of a single frame target image according to an embodiment of the invention.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a flow chart of a method for extracting a bridge train loading action time course according to an embodiment of the invention, the method includes:
s101: first image data corresponding to the first target and second image data corresponding to the second target are obtained.
In this embodiment, before the bridge train loading time course extraction is performed, a red square target mark may be first set, and as shown in fig. 4 and 5, the mark is formed by two parts, a central area is a red opaque Fang Biaoba 41, and a black opaque large square target 42 surrounding the red square target is provided. In order to avoid the reflection interference of the target surface, a frosted acrylic plate can be selected as the target material. In the embodiment of the invention, two targets, namely a first target and a second target, can be arranged, and each target is fixed at two ends of the bridge beam body shown in fig. 5. In this embodiment, bridge supports are correspondingly installed below each target on the bridge beam body, wherein the triangular shape is a fixed support, and the circular shape is a movable support. When train load acts on the bridge beam body, the test mark can displace in the horizontal direction and the vertical direction at the same time. That is, in this embodiment, the first target and the second target are respectively disposed at two ends of the target beam body, where the first target corresponds to one end of the fixed support of the target beam body, and the second target corresponds to one end of the movable support of the target beam body.
In this embodiment, before the bridge train loading schedule extraction is performed, a camera is placed a distance in front of the red square target as shown in fig. 6. The mounting conditions of the camera are as follows: 1) Ensuring that the lens surface of the camera is parallel to the red square target surface as much as possible; 2) The central axis of the lens is as collinear as possible with the central axis of Fang Biaoba. The 2 conditions can ensure that the red square target image shot by the camera is as much as possible in the whole image center, and the imaging probability of the red square target is square. Because the camera is installed and fixed on the bridge pier, when the train load acts on the bridge girder body, the general bridge pier can not take place displacement change. Therefore, the displacement change of the two ends of the bridge beam body in the x direction and the y direction in the plane can be determined by analyzing the displacement of the target image shot by the camera.
In the implementation process, 2 cameras shoot video images of targets at two ends of the bridge in real time, and video image sequences are stored locally. And when the video image sequences of the targets are shot and stored, the local video image sequences are read in real time, video image contents of the targets at the two ends of the bridge are analyzed through cooperative processing, and time interval information of train load acting on the bridge body is extracted.
In this embodiment, before acquiring the first image data corresponding to the first target and the second image data corresponding to the second target, the method may further include:
acquiring first video data corresponding to a first target and second video data corresponding to a second target, and extracting images of the first video data and the second video data to obtain first image data and second image data.
In this embodiment, when the locally stored red target video data is read, the video data mainly includes a video file name, a video data file header, a data block, and an index block. The video file name contains the initial acquisition time of the video file, the video data file head has video frame number, each frame of image data format and size, camera acquisition frame frequency parameter f and the like, the data block contains all the shot image data streams, and the index block comprises a data block list and the positions of the data blocks in the file. Through the above, each frame of image content of the red target video data can be accessed at will, and the acquisition time corresponding to each frame of image can be determined.
S102: and determining the starting moment of the train load according to the second image data, determining the first template image based on the starting moment of the train load and the first image data, and determining the second template image based on the starting moment of the train load and the second image data.
In this embodiment, the arrival time point of the train load, that is, the start time of the train load may be determined by processing the second image data corresponding to the second target based on the moving window average detection method. After the initial moment of the train load is determined, the first image data and the second image data which are shot by the cameras of the bridge Liang Tishi and are not acted on by the train are extracted based on the initial moment, the first template image is determined based on the initial moment and the first image data, and the second template image is determined based on the initial moment and the second image data.
S103: matching the first image data with the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence; and matching the second image data with the second template image, and performing dimerization processing on the matching result to obtain a second matching sequence.
In this embodiment, the matching results corresponding to the first image data and the first template image, the matching results corresponding to the second image data and the second template image may be determined through matching calculation of the images, and a dimerization type analysis may be performed on the two sets of matching results based on a dimerization type method, so as to obtain a plurality of cluster identifiers, that is, a first matching sequence and a second matching sequence, respectively.
S104: and determining the time course of the bridge train loading action based on the first matching sequence and the second matching sequence.
In this embodiment, the first matching sequence and the second matching sequence may be fused, and the time interval of the bridge train load action may be determined according to the result of the fusion.
It can be obtained from the above that, firstly, the method for extracting the time course of the bridge train load action provided by the embodiment of the invention does not need to install magnetic steel on site to extract the time course of the train load action, and can be realized only by means of the data acquisition device in the existing bridge health monitoring system, so that the cost of manpower and material resources is effectively reduced. Secondly, the method for extracting the bridge train load action time course provided by the embodiment of the invention determines the movement condition of the target in a clustering processing mode, and compared with the method for judging the movement condition of the target by using a simple threshold analysis method, the method is higher in accuracy. In addition, the embodiment of the invention also extracts the bridge train load action time course through the image data of the two targets, and has better robustness.
Optionally, as a specific implementation manner of the bridge train load action time interval extraction method provided by the embodiment of the present invention, determining the starting time of the train load according to the second image data includes:
s1: setting the frame number of the current initial detection image as n, the width of the moving window as w, and the moving step length as d, wherein n=1, and d is smaller than or equal to w.
S2: and extracting the nth to nth+w frame images from the second image data, and determining Euclidean norms of the nth+w frame images relative to the previous w frame images based on the nth to nth+w frame images.
S3: and if the Euclidean norm is larger than the preset threshold, taking the moment corresponding to the n+w frame image as the initial moment of the train load. If the euclidean norm is not greater than the preset threshold, let n=n+d, and return to step S2.
In this embodiment, the middle line data of the second image data may be extracted first, as shown in fig. 7, and the middle line data 4 in the second image data may be extracted first, and the start time of the train load may be determined based on the moving window average detection method.
In this embodiment, d and w are integers, and specific values thereof may be set according to actual requirements, for example, w may be set to 5f, where f is an acquisition frame frequency of the camera.
In this embodiment, considering that the fixed mounting points of the 2 cameras are different, when the train load acts on the bridge girder body, the displacement change condition of the image target photographed by each camera is also different. The image corresponding to the second target at the movable end has the largest displacement change in the x direction, so that the starting moment of the train load can be determined according to the second image data.
In this embodiment, the preset threshold value can be set according to actual requirements, for example, the preset threshold value can be set to 10 5 。
Optionally, as a specific implementation manner of the bridge train load acting time interval extraction method provided by the embodiment of the present invention, determining euclidean norms of the n+w frame image relative to the previous w frame image based on the n+w frame images includes:
where p is the Euclidean norm of the n+w frame image with respect to its previous w frame image,represents the L2 norm, (a) n ,a n+1 ,…,a n+w-1 ,a n+w ) Intermediate line data representing n-th to n+w-th frame images.
In this embodiment, p may reflect the variation of the average data of the n+w frame image with respect to the previous w frame image.
Optionally, as a specific implementation manner of the bridge train load action time interval extraction method provided by the embodiment of the present invention, determining the first template image based on the start time of the train load and the first image data includes:
and if the starting time is t, taking a frame image corresponding to the t-m seconds in the first image data as a first template image. Wherein m is a preset time interval.
In this embodiment, m may be set according to actual requirements, for example, m may be 10. That is, in the present embodiment, the time t may be the time reference point, the frame number of 10 seconds before the time reference point is extracted, and the frame image in the first image data corresponding to the frame number is used as the first template image.
In this embodiment, the method for determining the second template image based on the start time of the train load and the second image data is the same as the method for determining the first template image based on the start time of the train load and the first image data, and will not be described here again.
Optionally, as a specific implementation manner of the bridge train load action time interval extraction method provided by the embodiment of the present invention, matching the first image data and the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence, where the method includes:
respectively extracting middle column data of the first template image and middle column data of continuous Mxf frame images after the frame number T in the first image data; wherein T is the frame number of the first template image, M is the maximum duration of train load action, and f is the acquisition frame frequency.
And determining a matching difference value between the continuous Mxf frame image and the first template image based on the middle column data of the continuous Mxf frame image and the middle column data of the first template image, so as to obtain a first difference value sequence.
And carrying out dimerization treatment on the first difference sequence to obtain a first matching sequence.
In this embodiment, the method for determining the matching difference between the continuous mxf frame image and the first template image in the first image data is:
wherein,intermediate column data for the (T+i) -th frame image, u T For the middle column data of the first template image, < >>Is L2 norm>And the matching difference value of the (T+i) th frame image and the first template image. The implementation isIn the example, a->The degree of matching of the t+i frame image with the first template image may be reflected.
Similarly, the method for determining the matching difference value between the continuous Mxf frame image and the second template image in the second image data is as follows:
wherein,intermediate column data for the (T+i) -th frame image, u T For the middle column data of the second template image, < >>Is L2 norm>And the matching difference value of the (T+i) th frame image and the second template image. In this embodiment, <' > a->The degree of matching of the t+i frame image with the second template image may be reflected.
In this embodiment, the dimerization-type method may be a k-means clustering method. Within the sequence of first difference values,the numerical variations of (2) can be largely classified into 2 categories: when the train load acts on the bridge, the load is added>The numerical value is relatively large; and when the train load is not acting on the bridge +.>The values are relatively small. Therefore, the embodiment of the invention adopts a K-means dimerization method to carry out dimerization analysis on the first difference value sequence and obtains a plurality of clustering identification sequences of the matching result, namely a first matching sequence. Alternatively, cluster identification may be represented using 1 and 0, with 1 representing the presence of train loading and 0 representing the absence of train loading.
In this embodiment, the method for determining the second matching sequence is the same as that of the first matching sequence, and will not be described here again.
Optionally, as a specific implementation manner of the bridge train loading action time interval extraction method provided by the embodiment of the present invention, before determining the time interval of the bridge train loading action based on the first matching sequence and the second matching sequence, the method further includes:
morphological processing is performed on the first matching sequence and the second matching sequence.
In this embodiment, the target images captured by the 2 cameras will vibrate continuously when the actual train load is applied to the bridge Liang Tishi. Considering that during the vibration of the target image, the partial frame images of the target image may coincide with or be close to the initial static target template image, so that the matching result of the frame image sequences may be marked as 0 by the K-means dimerization method. To solve this problem, the present invention introduces morphological operations to process these potentially noisy cluster labeling results. Specifically, a morphological closing operation (i.e., an expansion operation is performed first and then a corrosion operation) operator may be selected to process the first matching sequence and the second matching sequence. Since the marking result of the original K-means is one line of binary data, the binary structural element matrix SE adopted in the morphological closing operation of the present invention is: SE= [1, … 1,1], wherein the SE matrix is an all-1 vector with the size of 1 xw, and morphological processing analysis is performed by using the SE matrix, so that the situation that target images of continuous (w-1) frames coincide with or are close to an initial static target template in the train loading process can be processed.
In the embodiment, the problem that the vibration of the on-site target is overlapped with the target template area is solved by using morphological closed operation analysis, and the extraction precision of the train load action time course can be effectively improved.
Optionally, as a specific implementation manner of the bridge train loading action time interval extraction method provided by the embodiment of the present invention, determining the time interval of the bridge train loading action based on the first matching sequence and the second matching sequence includes:
and performing OR operation on the first matching sequence and the second matching sequence to obtain a third matching sequence.
And taking the change time period of the numerical value in the third matching sequence as the time course of the bridge train load action.
In this embodiment, after morphological closed operation analysis, a first matching sequence and a second matching sequence including dynamic and static identifiers can be obtained. I.e. the
Wherein g 1i Dynamic and static identification corresponding to the first matching sequence g 2i And (5) dynamic and static identification corresponding to the second matching sequence.
The invention is characterized in that camera measuring devices are arranged at two ends of a bridge, and the displacement of the left side end of the bridge in the y direction is calculated by using middle column data 1 of a first target, and the displacement of the right side end of the bridge in the y direction is calculated by using middle column data 3 of a second target. In the process that the train load acts on the bridge beam body, the displacement change of the target in the y direction can be measured at the two ends of the bridge. Therefore, the invention proposes to use logical OR operation to fuse the matching sequences monitored and analyzed by the 2 cameras to obtain a third matching sequence, wherein the dynamic and static identifications g of the third matching sequence i The following are provided:
g i ＝g 1i OR g 2i
in this embodiment, the dynamic and static identification of the k1 frame is changed to 1, and the dynamic and static identification of the k2 frame is changed to 0, so that the time elapsed by k2-k1 is the time interval of the bridge train load action.
Wherein, the initial acquisition time τ of the target video data can be determined by reading the file name of the target video data file in step S101 0 . The dynamic and static identification of the bridge body under the action of the train load can be obtained through the method, the dynamic and static identification of the bridge body under the action of the train load is set to be 1 in the k1 frame, and the dynamic and static identification of the bridge body under the action of the train load is set to be 0 in the k2 frame, so that the starting time tau of the train load action time interval can be calculated according to the following method 1 And a termination time tau 2 (where f is the acquisition frame rate of the camera).
τ 1 ＝τ 0 +k1/f
τ 2 ＝τ 0 +k2/f
That is, in the present embodiment, the time course of the train load action, that is, the period in which the dynamic and static marks become 1.
Corresponding to the method for extracting the loading time course of the bridge train in the above embodiment, fig. 2 is a block diagram of a device for extracting the loading time course of the bridge train according to an embodiment of the present invention. For convenience of explanation, only portions relevant to the embodiments of the present invention are shown. Referring to fig. 2, the bridge train loading time course extraction device 20 includes: a data acquisition module 21, a template determination module 22, an image matching module 23, a time course determination module 24.
The data acquisition module 21 is configured to acquire first image data corresponding to a first target and second image data corresponding to a second target, where the first target and the second target are respectively disposed at two ends of the target beam body, and the first target corresponds to one end of a fixed support of the target beam body, and the second target corresponds to one end of a movable support of the target beam body.
The template determining module 22 is configured to determine a start time of the train load according to the second image data, determine a first template image based on the start time of the train load and the first image data, and determine a second template image based on the start time of the train load and the second image data.
The image matching module 23 is configured to match the first image data with the first template image, and perform dimerization processing on the matching result to obtain a first matching sequence. And matching the second image data with the second template image, and performing dimerization processing on the matching result to obtain a second matching sequence.
A time course determination module 24 is configured to determine a time course of the bridge train loading based on the first matching sequence and the second matching sequence.
Optionally, as a specific implementation manner of the bridge train load acting time interval extracting device provided by the embodiment of the present invention, determining the starting time of the train load according to the second image data includes:
s1: setting the frame number of the current initial detection image as n, the width of the moving window as w, and the moving step length as d, wherein n=1, and d is smaller than or equal to w.
S2: and extracting the nth to nth+w frame images from the second image data, and determining Euclidean norms of the nth+w frame images relative to the previous w frame images based on the nth to nth+w frame images.
S3: and if the Euclidean norm is larger than the preset threshold, taking the moment corresponding to the n+w frame image as the initial moment of the train load. If the euclidean norm is not greater than the preset threshold, let n=n+d, and return to step S2.
Optionally, as a specific implementation manner of the bridge train load acting time interval extraction device provided by the embodiment of the present invention, determining euclidean norms of the n+w frame image relative to the previous w frame image based on the n+w frame images includes:
where p is the Euclidean norm of the n+w frame image with respect to its previous w frame image,represents the L2 norm, (a) n ,a n+1 ,…,a n+w-1 ,a n+w ) Intermediate line data representing n-th to n+w-th frame images.
Optionally, as a specific implementation manner of the bridge train load acting time interval extracting device provided by the embodiment of the present invention, determining the first template image based on the starting time of the train load and the first image data includes:
and if the starting time is t, taking a frame image corresponding to the t-m seconds in the first image data as a first template image. Wherein m is a preset time interval.
Optionally, as a specific implementation manner of the bridge train load action time interval extraction device provided by the embodiment of the present invention, matching the first image data and the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence, where the method includes:
respectively extracting middle column data of the first template image and middle column data of continuous Mxf frame images after the frame number T in the first image data; wherein T is the frame number of the first template image, M is the maximum duration of train load action, and f is the acquisition frame frequency.
And determining a matching difference value between the continuous Mxf frame image and the first template image based on the middle column data of the continuous Mxf frame image and the middle column data of the first template image, so as to obtain a first difference value sequence.
And carrying out dimerization treatment on the first difference sequence to obtain a first matching sequence.
Optionally, as a specific implementation manner of the bridge train loading time interval extracting device provided by the embodiment of the present invention, before determining the time interval of the bridge train loading based on the first matching sequence and the second matching sequence, the bridge train loading time interval extracting device further includes:
morphological processing is performed on the first matching sequence and the second matching sequence.
Optionally, as a specific implementation manner of the bridge train loading action time interval extracting device provided by the embodiment of the present invention, determining the time interval of the bridge train loading action based on the first matching sequence and the second matching sequence includes:
and performing OR operation on the first matching sequence and the second matching sequence to obtain a third matching sequence.
And taking the change time period of the numerical value in the third matching sequence as the time course of the bridge train load action.
Referring to fig. 3, fig. 3 is a schematic block diagram of a terminal device according to an embodiment of the present invention. The terminal 300 in the present embodiment as shown in fig. 3 may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processor 301, the input device 302, the output device 303, and the memory 304 communicate with each other via a communication bus 305. The memory 304 is used to store a computer program comprising program instructions. The processor 301 is configured to execute program instructions stored in the memory 304. Wherein the processor 301 is configured to invoke program instructions to perform the following functions of the modules/units in the above described device embodiments, such as the functions of the modules 21 to 24 shown in fig. 2.
It should be appreciated that in embodiments of the present invention, the processor 301 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 302 may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.
The memory 304 may include read only memory and random access memory and provides instructions and data to the processor 301. A portion of memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information of device type.
In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present invention may execute the implementation manners described in the first embodiment and the second embodiment of the bridge train load action time course extraction method provided in the embodiments of the present invention, and may also execute the implementation manner of the terminal described in the embodiments of the present invention, which is not described herein again.
In another embodiment of the present invention, a computer readable storage medium is provided, where the computer readable storage medium stores a computer program, where the computer program includes program instructions, where the program instructions, when executed by a processor, implement all or part of the procedures in the method embodiments described above, or may be implemented by instructing related hardware by the computer program, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by the processor, implements the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The computer readable storage medium may be an internal storage unit of the terminal of any of the foregoing embodiments, such as a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store a computer program and other programs and data required for the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working procedures of the terminal and the unit described above may refer to the corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In several embodiments provided in the present application, it should be understood that the disclosed terminal and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via some interfaces or units, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. The method for extracting the bridge train load action time course is characterized by comprising the following steps of:
acquiring first image data corresponding to a first target and second image data corresponding to a second target, wherein the first target and the second target are respectively arranged at two ends of a target beam body, the first target corresponds to one end of a fixed support of the target beam body, and the second target corresponds to one end of a movable support of the target beam body;
determining the starting moment of the train load according to the second image data, determining a first template image based on the starting moment of the train load and the first image data, and determining a second template image based on the starting moment of the train load and the second image data;
matching the first image data with the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence; matching the second image data with the second template image, and performing dimerization processing on the matching result to obtain a second matching sequence;
determining a time course of bridge train loading action based on the first matching sequence and the second matching sequence;
the determining a first template image based on the starting time of the train load and the first image data includes:
if the starting time is t, taking a frame image corresponding to the t-m seconds in the first image data as a first template image; wherein m is a preset time interval;
the matching of the first image data and the first template image, and the dimerization processing of the matching result, the obtaining of a first matching sequence, includes:
respectively extracting middle column data of the first template image and middle column data of continuous Mxf frame images after the frame number T in the first image data; wherein T is the frame number of the first template image, M is the maximum duration of train load action, and f is the acquisition frame frequency of the camera;
determining a matching difference value between the continuous Mxf frame images and the first template image based on the middle column data of the continuous Mxf frame images and the middle column data of the first template image to obtain a first difference value sequence;
performing dimerization treatment on the first difference sequence to obtain a first matching sequence;
the determining the time course of the bridge train load action based on the first matching sequence and the second matching sequence comprises the following steps:
performing OR operation on the first matching sequence and the second matching sequence to obtain a third matching sequence;
and taking the change time period of the numerical value in the third matching sequence as the time course of the bridge train load action.
2. The bridge train loading time course extraction method according to claim 1, wherein determining the start time of the train loading based on the second image data comprises:
s1: setting the frame number of the current initial detection image as n, the width of the moving window as w, and the moving step length as d, wherein n=1, and d is smaller than or equal to w;
s2: extracting n+w-th frame images from the second image data, and determining euclidean norms of the n+w-th frame images with respect to the previous w-th frame images based on the n+w-th frame images;
s3: if the Euclidean norm is larger than a preset threshold, taking the moment corresponding to the n+w frame image as the initial moment of the train load; if the euclidean norm is not greater than the preset threshold, n=n+d, and the step S2 is executed again.
3. The bridge train loading time course extraction method according to claim 2, wherein the determining euclidean norms of the n+w frame image with respect to the previous w frame image based on the n+w frame images includes:
where p is the Euclidean norm of the n+w frame image with respect to its previous w frame image,represents the L2 norm, (a) n ,a n+1 ,…,a n+w-1 ,a n+w ) Intermediate line data representing n-th to n+w-th frame images.
4. The bridge train loading time course extraction method of claim 1, further comprising, prior to determining the time course of the bridge train loading based on the first matching sequence and the second matching sequence:
morphological processing is performed on the first matching sequence and the second matching sequence.
5. Bridge train load action time course extraction element, characterized by that includes:
the data acquisition module is used for acquiring first image data corresponding to a first target and second image data corresponding to a second target, wherein the first target and the second target are respectively arranged at two ends of a target beam body, the first target corresponds to one end of a fixed support of the target beam body, and the second target corresponds to one end of a movable support of the target beam body;
the template determining module is used for determining the starting moment of the train load according to the second image data, determining a first template image based on the starting moment of the train load and the first image data, and determining a second template image based on the starting moment of the train load and the second image data;
the image matching module is used for matching the first image data with the first template image, and performing dimerization processing on the matching result to obtain a first matching sequence; matching the second image data with the second template image, and performing dimerization processing on the matching result to obtain a second matching sequence;
the time course determining module is used for determining the time course of the bridge train load action based on the first matching sequence and the second matching sequence;
the determining a first template image based on the starting time of the train load and the first image data includes:
if the starting time is t, taking a frame image corresponding to the t-m seconds in the first image data as a first template image; wherein m is a preset time interval;
the matching of the first image data and the first template image, and the dimerization processing of the matching result, the obtaining of a first matching sequence, includes:
respectively extracting middle column data of the first template image and middle column data of continuous Mxf frame images after the frame number T in the first image data; wherein T is the frame number of the first template image, M is the maximum duration of train load action, and f is the acquisition frame frequency of the camera;
determining a matching difference value between the continuous Mxf frame images and the first template image based on the middle column data of the continuous Mxf frame images and the middle column data of the first template image to obtain a first difference value sequence;
performing dimerization treatment on the first difference sequence to obtain a first matching sequence;
the determining the time course of the bridge train load action based on the first matching sequence and the second matching sequence comprises the following steps:
performing OR operation on the first matching sequence and the second matching sequence to obtain a third matching sequence;
and taking the change time period of the numerical value in the third matching sequence as the time course of the bridge train load action.
6. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 4 when the computer program is executed.
7. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011064690.9A CN112132227B (en) | 2020-09-30 | 2020-09-30 | Bridge train load action time course extraction method and device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011064690.9A CN112132227B (en) | 2020-09-30 | 2020-09-30 | Bridge train load action time course extraction method and device and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112132227A CN112132227A (en) | 2020-12-25 |
| CN112132227B true CN112132227B (en) | 2024-04-05 |
Family
ID=73843891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011064690.9A Active CN112132227B (en) | 2020-09-30 | 2020-09-30 | Bridge train load action time course extraction method and device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132227B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033891B (en) * | 2021-03-19 | 2022-01-18 | 河北水熠木丰工程技术有限责任公司 | High pier bridge health monitoring method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106710242A (en) * | 2017-02-20 | 2017-05-24 | 广西交通科学研究院有限公司 | Method for recognizing vehicle quantity of motorcade based on dynamic strain of bridge |
| CN106895900A (en) * | 2017-02-20 | 2017-06-27 | 广西交通科学研究院有限公司 | The method that the bicycle number of axle is recognized based on bridge dynamic strain |
| CN110034976A (en) * | 2019-04-08 | 2019-07-19 | Oppo广东移动通信有限公司 | A kind of method and device of data identification |
| WO2019237992A1 (en) * | 2018-06-15 | 2019-12-19 | Oppo广东移动通信有限公司 | Photographing method and device, terminal and computer readable storage medium |
| WO2020038109A1 (en) * | 2018-08-22 | 2020-02-27 | Oppo广东移动通信有限公司 | Photographing method and device, terminal, and computer-readable storage medium |
| CN111144039A (en) * | 2019-12-04 | 2020-05-12 | 东南大学 | Train dynamic weighing system and weighing method based on deep learning |
| CN111291736A (en) * | 2020-05-07 | 2020-06-16 | 南京景三医疗科技有限公司 | Image correction method and device and medical equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103063451B (en) * | 2012-12-26 | 2014-07-23 | 浙江大学 | Rail transit train wholly moving load analog loading method and device |
| US20150088428A1 (en) * | 2013-09-23 | 2015-03-26 | San Diego State University Research Foundation | Computationally efficient nonlinear structural analysis |
| US20180374237A1 (en) * | 2017-06-23 | 2018-12-27 | Canon Kabushiki Kaisha | Method, system and apparatus for determining a pose for an object |
| US20190377851A1 (en) * | 2018-06-07 | 2019-12-12 | Microsoft Technology Licensing, Llc | Efficient payload extraction from polynucleotide sequence reads |
-
2020
- 2020-09-30 CN CN202011064690.9A patent/CN112132227B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106710242A (en) * | 2017-02-20 | 2017-05-24 | 广西交通科学研究院有限公司 | Method for recognizing vehicle quantity of motorcade based on dynamic strain of bridge |
| CN106895900A (en) * | 2017-02-20 | 2017-06-27 | 广西交通科学研究院有限公司 | The method that the bicycle number of axle is recognized based on bridge dynamic strain |
| WO2019237992A1 (en) * | 2018-06-15 | 2019-12-19 | Oppo广东移动通信有限公司 | Photographing method and device, terminal and computer readable storage medium |
| WO2020038109A1 (en) * | 2018-08-22 | 2020-02-27 | Oppo广东移动通信有限公司 | Photographing method and device, terminal, and computer-readable storage medium |
| CN110034976A (en) * | 2019-04-08 | 2019-07-19 | Oppo广东移动通信有限公司 | A kind of method and device of data identification |
| CN111144039A (en) * | 2019-12-04 | 2020-05-12 | 东南大学 | Train dynamic weighing system and weighing method based on deep learning |
| CN111291736A (en) * | 2020-05-07 | 2020-06-16 | 南京景三医疗科技有限公司 | Image correction method and device and medical equipment |
Non-Patent Citations (2)
| Title |
|---|
| 根据响应识别桥上列车荷载的模糊模式识别方法;瞿伟廉;王仪;;噪声与振动控制(01);全文 * |
| 桥上列车移动荷载参数自动识别系统试验;王仪;虞婷婷;瞿伟廉;;噪声与振动控制(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112132227A (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229376B (en) | Method and device for detecting blinking | |
| CN112085952B (en) | Method and device for monitoring vehicle data, computer equipment and storage medium | |
| CN102004906A (en) | Face identification system and method | |
| CN109740590B (en) | ROI accurate extraction method and system based on target tracking assistance | |
| CN110516522B (en) | Inspection method and system | |
| CN111325988A (en) | Real-time red light running detection method, device and system based on video and storage medium | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN113096158A (en) | Moving object identification method and device, electronic equipment and readable storage medium | |
| CN113409587A (en) | Abnormal vehicle detection method, device, equipment and storage medium | |
| CN110084987A (en) | A kind of foreign matter inspecting system and method towards rail traffic | |
| CN112132227B (en) | Bridge train load action time course extraction method and device and terminal equipment | |
| CN108174198B (en) | Video image quality diagnosis analysis detection device and application system | |
| CN110298302B (en) | Human body target detection method and related equipment | |
| CN115830002A (en) | Infrared image quality evaluation method and device | |
| KR20160083465A (en) | Multilane camera recognition system and method for analysing image to learning type thereof | |
| CN109903308B (en) | Method and device for acquiring information | |
| CN112229586A (en) | Bridge support health state detection method and terminal equipment | |
| CN112215222A (en) | License plate recognition method, device, equipment and storage medium | |
| CN109215150A (en) | Face is called the roll and method of counting and its system | |
| Vijayan et al. | A survey on surface crack detection in concretes using traditional, image processing, machine learning, and deep learning techniques | |
| CN113837312B (en) | Method and device for evaluating running state of zinc oxide arrester | |
| CN115424253A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN107993446A (en) | A kind of traffic prohibition parking area domain parking offense monitoring device | |
| KR101984069B1 (en) | Image based intelligent vibration monitoring method | |
| CN117437792B (en) | Real-time road traffic state monitoring method, device and system based on edge calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |