CN111878174B - High-speed railway tunnel lining block dropping video monitoring method and device - Google Patents
High-speed railway tunnel lining block dropping video monitoring method and device Download PDFInfo
- Publication number
- CN111878174B CN111878174B CN202010866312.6A CN202010866312A CN111878174B CN 111878174 B CN111878174 B CN 111878174B CN 202010866312 A CN202010866312 A CN 202010866312A CN 111878174 B CN111878174 B CN 111878174B
- Authority
- CN
- China
- Prior art keywords
- information
- speed railway
- railway tunnel
- lining
- obtaining
- 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
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
Abstract
The invention discloses a video monitoring method and a video monitoring device for high-speed railway tunnel lining block dropping, wherein the method comprises the following steps: acquiring first image information, acquiring second image information, and acquiring deformation information of the inner wall of the high-speed railway tunnel according to the first image information and the second image information; obtaining the internal waveform information of the high-speed railway tunnel; inputting the deformation information and the waveform information into a training model to obtain output information of the training model, wherein the output information comprises a first output result and a second output result, and determining whether a first alarm instruction is obtained according to the first output result and the second output result, and the first alarm instruction is used for reminding that lining falling blocks exist on the inner wall of the high-speed railway tunnel; the problem of can't know and report to the police among the prior art, lead to high-speed railway tunnel lining to fall the piece and cause the accident is solved, realize the technical effect to the accurate warning of high-speed railway tunnel lining falling piece.
Description
Technical Field
The invention relates to the field of tunnel safety monitoring, in particular to a high-speed railway tunnel lining block dropping video monitoring method and device.
Background
As the scale of high-speed rail is continuously enlarged, the specific gravity of the tunnel is also continuously increased. After the tunnel is excavated, the original balance of the stratum around the tunnel is damaged, and the tunnel is deformed or collapsed. In order to protect the stability of the surrounding rock and ensure the driving safety, the tunnel must have a supporting structure with enough strength, namely a tunnel lining, which has the functions of: supporting and maintaining the stability of the tunnel; maintaining the space required for train operation; preventing the weathering of the surrounding rock; relieving the influence of underground water, etc.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
due to the influence of factors such as environment and quality, the phenomenon of block falling of the tunnel wall lining occurs at all times, and the method has the characteristics of burstiness and concealment, and brings great influence on the high-speed rail operation and the life safety of people.
Disclosure of Invention
The embodiment of the application provides a high-speed railway tunnel lining dropping video monitoring method and device, solves the problem that accidents are caused by the fact that high-speed railway tunnel lining dropping can not be known and reported to the police in the prior art, and achieves the technical effect of accurately reporting to the high-speed railway tunnel lining dropping.
The embodiment of the application provides a high-speed railway tunnel lining block dropping video monitoring method, wherein the method comprises the following steps: acquiring first image information, wherein the first image information is image information of the inner wall of the high-speed railway tunnel at the first time; obtaining second image information, wherein the second image information is image information of the inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time; according to the first image information and the second image information, deformation amount information of the inner wall of the high-speed railway tunnel is obtained; radar monitoring is carried out inside the high-speed railway tunnel, and waveform information inside the high-speed railway tunnel is obtained; inputting the deformation amount information and the waveform information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel; obtaining output information of the training model, wherein the output information comprises a first output result and a second output result, the first output result is the result that the wall lining in the high-speed railway tunnel is broken, and the second output result is the result that the wall lining in the high-speed railway tunnel is not broken; and determining whether a first alarm instruction is obtained or not according to the first output result and the second output result, wherein the first alarm instruction is used for reminding the lining and block falling phenomenon of the inner wall of the high-speed railway tunnel.
On the other hand, this application still provides a high-speed railway tunnel lining video monitoring devices that falls, wherein, the device includes: the first obtaining unit is used for obtaining first image information, and the first image information is image information of the wall inside the high-speed railway tunnel at the first time; a second obtaining unit, configured to obtain second image information, where the second image information is image information of an inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time; a third obtaining unit, configured to obtain deformation amount information of the inner wall of the high-speed railway tunnel according to the first image information and the second image information; a fourth obtaining unit, configured to obtain the internal waveform information of the high-speed railway tunnel; a first input unit, configured to input the deformation amount information and the waveform information into a training model, where the training model is obtained by training multiple sets of training data, and each set of training data in the multiple sets includes: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel; a fifth obtaining unit, configured to obtain output information of the training model, where the output information includes a first output result and a second output result, where the first output result is a result that a wall lining inside the high-speed railway tunnel has a block drop, and the second output result is a result that a wall lining inside the high-speed railway tunnel has no block drop; and the first determining unit is used for determining whether a first alarm instruction is obtained or not according to the first output result and the second output result, and the first alarm instruction is used for reminding the lining and block dropping phenomenon of the inner wall of the high-speed railway tunnel.
In another aspect, the present invention provides a high-speed railway tunnel lining block dropping video monitoring device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.
In another aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the steps of the method according to any one of the claims 1 to 7.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the method has the advantages that the method that the deformation information and the waveform information of the wall inside the tunnel are combined to be input into the training model as the input information is adopted, the effect of accurately judging the existing state of the wall lining of the railway tunnel is achieved, the problem that accidents are caused by the fact that the lining of the high-speed railway tunnel falls due to the fact that the lining of the high-speed railway tunnel falls and the alarm cannot be obtained is solved, and the technical effect of accurately alarming the lining of the high-speed railway tunnel falls is achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flow chart diagram illustrating a video monitoring method for lining dropping of a high-speed railway tunnel according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a logistic regression line coordinate system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a high-speed railway tunnel lining block-dropping video monitoring device according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application;
description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a first input unit 15, a fifth obtaining unit 16, a first determining unit 17, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 306.
Detailed Description
The embodiment of the application provides a high-speed railway tunnel lining dropping video monitoring method and device, solves the problem that accidents are caused by the fact that high-speed railway tunnel lining dropping can not be known and reported to the police in the prior art, and achieves the technical effect of accurately reporting to the high-speed railway tunnel lining dropping. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
As the scale of high-speed rail is continuously enlarged, the number of high-speed rail tunnels is gradually increased. After the tunnel is excavated, the original balance of the stratum around the tunnel is damaged, and the tunnel is deformed or collapsed. In order to protect the stability of the surrounding rock and ensure driving safety, the tunnel must have a supporting structure of sufficient strength, i.e. a tunnel lining. Because of the influence of factors such as environment, quality, tunnel wall lining cutting phenomenon takes place occasionally to have proruption, disguised characteristics, can't know, report to the police through prior art, all caused very big influence for high-speed railway operation and people's life safety.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
a high-speed railway tunnel lining block dropping video monitoring method comprises the following steps: acquiring first image information, wherein the first image information is image information of the inner wall of the high-speed railway tunnel at the first time; obtaining second image information, wherein the second image information is image information of the inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time; according to the first image information and the second image information, deformation amount information of the inner wall of the high-speed railway tunnel is obtained; obtaining the internal waveform information of the high-speed railway tunnel; inputting the deformation amount information and the waveform information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel; obtaining output information of the training model, wherein the output information comprises a first output result and a second output result, the first output result is the result that the wall lining in the high-speed railway tunnel has the block falling, and the second output result is the result that the wall lining in the high-speed railway tunnel has no block falling; and determining whether a first alarm instruction is obtained or not according to the first output result and the second output result, wherein the first alarm instruction is used for reminding that the lining and block dropping phenomenon exists on the inner wall of the high-speed railway tunnel.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in the first drawing, the embodiment of the application provides a high-speed railway tunnel lining block dropping video monitoring method, wherein the method includes:
step S110: acquiring first image information, wherein the first image information is image information of the inner wall of the high-speed railway tunnel at the first time;
specifically, one or more image capturing devices may be disposed within the high speed railway tunnel and may obtain clear image information in the tunnel environment. The obtained first image information is image information of the tunnel inner wall at the first time. The state of the lining in the tunnel at the first time is judged by analyzing the image information captured by the tunnel inner wall at the first time, and the contrast image information is provided for judging the deformation information of the inner wall in the subsequent process. Specifically, relative shooting is carried out at the left edge and the right edge of the tunnel at intervals of 25 meters according to the same set height and angle in the high-speed railway tunnel, so that no blind area exists in a monitoring area, video streams of all cameras are transmitted to a video analysis server through a wired network, and railway track images in the tunnel are collected through the method. Acquiring a tunnel monitoring image of each camera, marking a rectangle according to a rail to be detected and a rail surface area image extending from the rail to be detected to obtain parameter values of positions of four vertexes of the rectangle in the image, and taking a rectangular area drawn by the 4 vertexes as a monitoring area; the collected images are preprocessed, main interference elements of the images in the tunnel, such as shaking and illumination change caused by train passing, are processed, and noise interference in the images is reduced.
Step S120: obtaining second image information, wherein the second image information is image information of the inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time;
specifically, the second time is after the first time, for example, after one week or one month of the second time when the image is acquired at the first time, the specific interval between the second time and the first time may be set according to the actual situation, which is not limited in this application. Further, in order to obtain the clarity of an image, a shaking processing is carried out on a frame before the image is shot, mainly by using a Scale Invariant Feature Transform (SIFT) method, and a historical frame is firstly stored in the image; then calculating the SIFT characteristic value of the historical frame; then calculating the SIFT characteristic value of the current frame of the video image; matching the characteristic values of the first two, and calculating a matching angle and displacement; when the configuration angle and the displacement exceed the threshold set by the method, the vibration is judged; and carrying out affine transformation according to the displacement and angle change after the shaking, thereby ensuring the stability of the whole image. One or more image capturing devices arranged in the high-speed railway tunnel capture image information of the inner wall of the tunnel at a second time, and the second image information and the first image information are the same position information of the tunnel. The state of the tunnel lining at the second time is judged by analyzing and comparing the image information captured by the tunnel inner wall at the second time, and the image information is compared for judging the deformation information of the inner wall in the subsequent process.
Step S130: according to the first image information and the second image information, deformation amount information of the inner wall of the high-speed railway tunnel is obtained;
specifically, the deformation amount information of the inner wall of the railway tunnel is obtained by comparing and analyzing the first image information captured at the first time and the second image information captured at the second time and according to the difference between the first image and the second image. The image information of the same position of the tunnel at different time points is compared to obtain the deformation information of the wall inside the tunnel, and the wall lining falling block inside the high-speed railway tunnel is judged through the deformation of the wall inside the tunnel, so that the technical effect of accurately alarming the high-speed railway tunnel lining falling block is realized.
Step S140: obtaining the internal waveform information of the high-speed railway tunnel;
in particular, the inside of the high-speed railway tunnel is also provided with a device for obtaining waveform information, and the device can be a radar monitoring device and other devices capable of measuring the waveform inside the tunnel, and is not particularly limited here. And evaluating the broken blocks of the tunnel lining by judging the change of the waveform in the tunnel. Through the analysis of the waveform information in the tunnel, the condition that the inner wall lining of the high-speed railway tunnel falls blocks is judged, and the technical effect of alarming the falling blocks of the lining of the high-speed railway tunnel is further realized.
Step S150: inputting the deformation amount information and the waveform information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel;
specifically, the description is expanded with reference to the second drawing. The training model is a machine learning model, and the machine learning model takes the deformation information as an abscissa and takes the waveform information as an ordinate to construct a coordinate system; and the machine learning model adopts a logistic regression model, and a logistic regression line is obtained according to the constructed coordinate system. Specifically, the machine learning model judges the input real-time information according to a logistic regression line through the input deformation quantity information and waveform information, so as to output whether the risk of the wall lining dropping block inside the high-speed railway tunnel exceeds the critical value. And acquiring the lining dropping block of the high-speed railway tunnel according to the judged lining dropping block risk, solving the technical problem that the lining dropping block of the high-speed railway tunnel cannot be acquired, and achieving the technical effect of accurately acquiring the lining dropping block of the high-speed railway tunnel.
Furthermore, in the machine learning model, deformation information and waveform information are respectively used as horizontal and vertical coordinates to form a coordinate system, and a logistic regression line is constructed according to the coordinate system, wherein the logistic regression line comprises a first position and a first angle, and the first position and the first angle are used for adjusting the logistic regression line. Further, the machine learning model is obtained by training a plurality of sets of training data, each set of training data in the plurality of sets including: the deformation information, the waveform information and the identification information for identifying the lining falling blocks of the wall in the tunnel are obtained, and the logistic regression line adjusts a large amount of data input and output, so that the judgment of the machine learning model is more accurate, and the technical effect of accurately knowing the lining falling blocks of the high-speed railway tunnel is achieved.
Furthermore, in the machine learning model, the first position and the first angle of the logistic regression line can be automatically adjusted according to the tunnel building duration information, the weather information and the judgment result: adjust first angle through weather information, adjust first position through long information when the tunnel is built, through the continuous correction of first angle and first position, make the position of logistic regression line become more accurate according to actual conditions, make the judgement of machine learning model learn constantly, progress, promote, and then make after the learning model is inputed through deformation variable information and waveform information, the inside wall lining of sign tunnel that obtains falls the identification information of piece more accurate, realized the technological effect of reporting to the police to high-speed railway tunnel lining falling piece accuracy.
Step S160: obtaining output information of the training model, wherein the output information comprises a first output result and a second output result, the first output result is the result that the wall lining in the high-speed railway tunnel has the block falling, and the second output result is the result that the wall lining in the high-speed railway tunnel has no block falling;
specifically, after deformation information and waveform information are input into a training model as horizontal and vertical coordinates, a coordinate system is constructed; and the machine learning model adopts a logistic regression model, a logistic regression line is obtained according to the constructed coordinate system, one side of the first logistic regression line represents a first result, the other side of the logistic regression line represents a second result, and the first result and the second result are different. When the input horizontal and vertical coordinate information falls on one side of a regression line, obtaining a first output result, wherein the first output result is the result that the inner wall lining of the high-speed railway tunnel has the falling blocks; when the input horizontal and vertical coordinate information falls on the other side of the regression line, obtaining a second output result, wherein the second output result is the result that the blocks do not fall off in the lining of the inner wall of the high-speed railway tunnel; whether the lining of the inner wall of the tunnel is safe or not is judged according to the mode of judging whether the first output result or the second output result is obtained, the technical problem that the lining falling block of the high-speed railway tunnel cannot be known is solved, and the technical effect of accurately knowing the lining falling block of the high-speed railway tunnel is achieved.
Step S170: determining whether a first alarm instruction is obtained or not according to the first output result and the second output result, wherein the first alarm instruction is used for reminding that lining falling blocks exist on the inner wall of the high-speed railway tunnel;
specifically, the first alarm instruction is used for reminding that lining falling blocks exist on the inner wall of the high-speed railway tunnel, and when the output result is a first output result, the first alarm instruction is obtained and used for alarming that lining falling blocks exist; and when the output result is the second output result, the first alarm instruction is not obtained. Whether the wall lining inside the tunnel is safe or not is judged by judging whether an alarm instruction is obtained or not, and then identification information for identifying the grade of the falling blocks of the wall lining inside the tunnel is used as supervision data, and the grade of the falling blocks of the wall lining is output, so that alarm is given according to the grade, the problem that the lining of the high-speed railway tunnel falls blocks and accidents are caused due to the fact that the lining of the high-speed railway tunnel falls blocks is solved, and the technical effect of accurately giving an alarm for the falling blocks of the high-speed railway tunnel lining is achieved.
In order to further explain the high-speed railway tunnel lining block dropping video monitoring method, the steps are further refined by combining the operation steps and the first drawing. Determining whether a first alarm instruction is obtained according to the first output result and the second output result, including: if the output result is a first output result, obtaining a first alarm instruction; and if the output result is a second output result, obtaining a second alarm instruction, wherein the second alarm instruction is used for reminding the daily maintenance of the inner wall of the high-speed railway tunnel.
In particular, when the output result is the second output result, the machine learning model may be further refined: an output result a close to the logistic regression line and an output result B far from the logistic regression line. Of course, the approach and the approach are further defined according to specific implementation and are continuously corrected by machine learning models and a large amount of data. And when the second output result is an output result A close to the logistic regression line, obtaining a second alarm instruction to remind the user of performing daily maintenance on the inner wall of the high-speed railway tunnel. And when the second output result is an output result B far away from the logistic regression line, the inner wall of the high-speed railway tunnel is in a good state at the moment, and the maintenance is not needed temporarily.
Further, after obtaining the first alarm instruction if the output result is the first output result, the method includes: obtaining a first time threshold; judging whether a vehicle passes through the high-speed railway tunnel within a first time threshold value after a first alarm instruction; if the high-speed railway tunnel is passed within a first time threshold value after the first alarm instruction, obtaining a third alarm instruction, wherein the third alarm instruction is used for reminding that the tunnel in front of the train has lining falling blocks; and if no train passes through the high-speed railway tunnel within a first time threshold value after the first alarm instruction, obtaining a fourth alarm instruction, wherein the fourth alarm instruction is used for reminding a worker of maintenance in the future.
Specifically, when the output result is a first output result and a first alarm instruction is obtained, a first time threshold is obtained, wherein the first time threshold is calculated from the first alarm instruction, whether a train passes through the first time threshold or not is determined within a certain time period, and the certain time period is longer than the maintenance time period. If a vehicle passes through the first time threshold, obtaining a third alarm instruction, and reminding that the front tunnel of the train has lining and blocks fall off; and if no train passes through the first time threshold, obtaining a fourth alarm instruction for reminding a worker of maintenance in the front.
Further, the training model comprises: obtaining deformation quantity information of the inner wall of the high-speed railway tunnel, and taking the deformation quantity information as a horizontal coordinate; obtaining the internal waveform information of the high-speed railway tunnel, and taking the waveform information as a vertical coordinate; obtaining a logistic regression line according to the abscissa and the ordinate by adopting a logistic regression model, wherein the logistic regression line comprises a first position and a first angle, and the first position and the first angle are located in a coordinate system constructed by the abscissa and the ordinate; wherein one side of the logistic regression line represents a first output result and the other side of the logistic regression line represents a second output result, wherein the first output result and the second output result are different.
Specifically, the training model is a machine learning model, and the machine learning model constructs a coordinate system by taking the deformation amount information as an abscissa and the waveform information as an ordinate; and the machine learning model adopts a logistic regression model, a logistic regression line is obtained according to the constructed coordinate system, one side of the first logistic regression line represents a first result, the other side of the logistic regression line represents a second result, and the first result and the second result are different. Specifically, the first result may be a result of a drop of the inner wall lining of the high speed railway tunnel, and the second result may be a result of no drop of the inner wall lining of the high speed railway tunnel. Whether the lining of the inner wall of the tunnel is safe or not is judged according to the mode of judging whether the first result or the second result is obtained, the technical problem that the lining falling block of the high-speed railway tunnel cannot be known is solved, and the technical effect of accurately knowing the lining falling block of the high-speed railway tunnel is achieved.
Furthermore, in the machine learning model, deformation information and waveform information are respectively used as horizontal and vertical coordinates to form a coordinate system, and a logistic regression line is constructed according to the coordinate system, wherein the logistic regression line comprises a first position and a first angle, and the first position and the first angle are used for adjusting the logistic regression line. Further, the machine learning model is obtained by training a plurality of sets of training data, each set of training data in the plurality of sets including: the deformation information, the waveform information and the identification information used for identifying the broken blocks of the wall lining in the tunnel are obtained, and the logistic regression line adjusts a large amount of data input and output, so that the judgment of the machine learning model is more accurate, and the technical effect of accurately knowing the broken blocks of the high-speed railway tunnel lining is achieved.
Furthermore, in the machine learning model, the first position and the first angle of the logistic regression line can be automatically adjusted according to the tunnel building duration information, the weather information and the judgment result: adjust first angle through weather information, adjust first position through long information when the tunnel is built, through the continuous correction of first angle and first position, make the position of logistic regression line become more accurate according to actual conditions, make the judgement of machine learning model learn constantly, progress, promote, and then make after the learning model is inputed through deformation variable information and waveform information, the inside wall lining of sign tunnel that obtains falls the identification information of piece more accurate, realized the technological effect of reporting to the police to high-speed railway tunnel lining falling piece accuracy.
Further, wherein the method comprises: obtaining the position information of the high-speed railway tunnel; obtaining first weather forecast information according to the position information, wherein the first weather forecast information is weather forecast information at the position information; obtaining a first influence parameter according to the first weather forecast information; and adjusting the first angle according to the first influence parameter.
In particular, the machine learning model may be adjusted by relevant influencing factors. Obtaining weather forecast information according to the position information: when the temperature is high, according to the principle of expansion with heat and contraction with cold, the deformation quantity of the abscissa is increased, and meanwhile, the waveform of the ordinate is reduced, which is specifically represented as that the first angle is reduced; when the temperature is lower, the amount of deformation of the abscissa decreases while the waveform of the ordinate increases, as reflected by an increase in the first angle. The weather factor is a first influence parameter, the first angle is adjusted through the first influence factor, the position of the logistic regression line is further adjusted, the machine learning model is further corrected, and therefore the technical effect of accurately alarming the lining dropping of the high-speed railway tunnel is achieved.
Further, obtaining a first influence parameter according to the first weather forecast information includes: obtaining a predetermined weather threshold; judging whether the first weather forecast information is within the preset weather threshold value; obtaining a first influencing parameter if the first weather forecast information is not within the predetermined weather threshold.
Specifically, the first influence parameter is obtained according to weather judgment, and a weather range, that is, the weather threshold value: when the temperature is within the range of 5-18 ℃, the influence of the weather condition on the learning model can be ignored, so that no influence parameter is generated, when the temperature is not within the range of 5-18 ℃, the weather condition has certain influence on the learning model, so that a first influence parameter is obtained, the machine learning model is adjusted, the accuracy of judging the machine learning model is further improved, and the technical effect of accurately alarming the lining dropping of the high-speed railway tunnel is achieved.
Further, wherein the method comprises: acquiring construction time length information of the high-speed railway tunnel; acquiring a second influence parameter according to the construction duration information; and adjusting the first position according to the second influence parameter.
Specifically, the machine learning model may adjust the first position of the logistic regression line according to a second impact parameter, the second impact parameter being controlled by the build duration information. When the construction time is 0-2 years, the second influence parameter is not obtained; when the construction time is 2-3 years, obtaining a second influence parameter a, and moving the first position to the left by a first distance; when the building time is 3-4 years, a second influence parameter b is obtained, and the first position moves to the left by a second distance. The second influence parameter is generated through the construction duration information, and the first position of the logistic regression line is adjusted through the second influence parameter, so that the logistic regression line is more accurate, the accuracy of machine learning model judgment is further improved, and the technical effect of accurately alarming the lining dropping of the high-speed railway tunnel is achieved.
Further, wherein the method comprises: obtaining classification information of the high-speed railway tunnel lining; obtaining a third influence parameter according to the classification information; and adjusting the first position according to the third influence parameter.
Specifically, the first position of the logistic regression line may be further adjusted according to a third influencing parameter, which is controlled by the lining type. When the lining is an integral concrete lining, obtaining a third influencing parameter S, and moving the first position by a first distance; when the lining is an assembled lining, obtaining a third influence parameter T, and moving the first position by a second distance; when the lining is the anchor spraying lining, obtaining a third influence parameter U, and moving the first position by a third distance; when the lining is a composite lining, obtaining a third influence parameter V, and moving the first position by a fourth distance; when the lining is a double arch lining, a third influencing parameter W is obtained, and the first position moves a fifth distance. Through the difference of the types of the linings, a third influence parameter is generated to further adjust the first position of the logistic regression line, so that the logistic regression line is more accurate, the accuracy of machine learning model judgment is further improved, and the technical effect of accurately alarming the lining falling of the high-speed railway tunnel is achieved.
1. The deformation quantity of the wall of the tunnel in different time periods and the waveform in the tunnel are used as input information, the identification information for identifying the wall lining falling block in the tunnel is used as supervision data, and the wall lining falling block risk grade is output, so that the method for alarming according to the grade level solves the problem that the lining falling block of the high-speed railway tunnel cannot be known and alarms, so that the lining falling block of the high-speed railway tunnel causes accidents, and the technical effect of accurately alarming the lining falling block of the high-speed railway tunnel is achieved.
2. The method comprises the steps that a logistic regression model is adopted, logistic regression lines are obtained by respectively taking deformation of a wall and a waveform in a tunnel as horizontal and vertical coordinates, and a first angle of the logistic regression lines is adjusted by taking weather as a first influence parameter; generating a second influence parameter during the construction time, and adjusting the first position of the logistic regression line; the lining category is used as a third influence parameter, and the first position of the logistic regression line is further adjusted, so that the output result of the logistic regression model on the input deformation and waveform is more accurate, the problem that accidents are caused by lining dropping of the high-speed railway tunnel due to the fact that the lining dropping of the high-speed railway tunnel cannot be known and an alarm is given is solved, and the technical effect of accurately alarming the lining dropping of the high-speed railway tunnel is achieved.
Example two
Based on the same inventive concept as the video monitoring method for the lining dropping block of the high-speed railway tunnel in the previous embodiment, the invention also provides a device for video monitoring of the lining dropping block of the high-speed railway tunnel, as shown in fig. three, the device comprises:
the first obtaining unit 11 is configured to obtain first image information, where the first image information is image information of a wall inside a high-speed railway tunnel at a first time;
a second obtaining unit 12, configured to obtain second image information, where the second image information is image information of an internal wall of the high-speed railway tunnel at a second time, where the second time is after the first time;
a third obtaining unit 13, wherein the third obtaining unit 13 is configured to obtain deformation amount information of the inner wall of the high-speed railway tunnel according to the first image information and the second image information;
a fourth obtaining unit 14, wherein the fourth obtaining unit 14 is used for obtaining the internal waveform information of the high-speed railway tunnel;
a first input unit 15, where the first input unit 15 is configured to input the deformation amount information and the waveform information into a training model, where the training model is obtained by training multiple sets of training data, and each set of training data in the multiple sets includes: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel;
a fifth obtaining unit 16, where the fifth obtaining unit 16 is configured to obtain output information of the training model, where the output information includes a first output result and a second output result, the first output result is a result that a wall lining inside the high-speed railway tunnel has a block drop, and the second output result is a result that a wall lining inside the high-speed railway tunnel has no block drop;
a first determining unit 17, where the first determining unit 17 is configured to determine whether a first alarm instruction is obtained according to the first output result and the second output result, and the first alarm instruction is used to remind that a lining drop block exists on an inner wall of the high-speed railway tunnel.
Further, the apparatus further comprises:
the determining whether to obtain a first alarm instruction according to the first output result and the second output result includes:
a sixth obtaining unit, configured to obtain a first alarm instruction if the output result is the first output result;
further, the apparatus further comprises:
a seventh obtaining unit, configured to obtain a second alarm instruction if the output result is a second output result, where the second alarm instruction is used to prompt daily maintenance of the inner wall of the high-speed railway tunnel;
further, the apparatus further comprises:
an eighth obtaining unit, configured to obtain deformation amount information of an inner wall of the high-speed railway tunnel, and use the deformation amount information as an abscissa;
further, the apparatus further comprises:
a ninth obtaining unit, configured to obtain waveform information inside the high-speed railway tunnel, and use the waveform information as a vertical coordinate;
further, the apparatus further comprises:
a tenth obtaining unit, configured to obtain a logistic regression line according to the abscissa and the ordinate by using a logistic regression model, where the logistic regression line includes a first position and a first angle, and the first position and the first angle are located in a coordinate system constructed by the abscissa and the ordinate; wherein one side of the logistic regression line represents a first output result and the other side of the logistic regression line represents a second output result, wherein the first output result and the second output result are different.
Further, the apparatus further comprises:
an eleventh obtaining unit configured to obtain a first time threshold;
further, the apparatus further comprises:
the first judgment unit is used for judging whether a vehicle passes through the high-speed railway tunnel within a first time threshold value after a first alarm instruction;
further, the apparatus further comprises:
a twelfth obtaining unit, configured to obtain a third alarm instruction if the high-speed railway tunnel passes within a first time threshold after the first alarm instruction, where the third alarm instruction is used to remind the tunnel in front of the train that a lining is dropped;
further, the apparatus further comprises:
a thirteenth obtaining unit, configured to obtain a fourth warning instruction if the high-speed railway tunnel does not pass through the train within a first time threshold after the first warning instruction, where the fourth warning instruction is used to remind a worker of maintenance in the future.
Further, the apparatus further comprises:
a fourteenth obtaining unit configured to obtain position information of the high-speed railway tunnel;
further, the apparatus further comprises:
a fifteenth obtaining unit configured to obtain first weather forecast information according to the location information, where the first weather forecast information is weather forecast information at the location information;
further, the apparatus further comprises:
a sixteenth obtaining unit to obtain a predetermined weather threshold;
further, the apparatus further comprises:
a second determination unit configured to determine whether the first weather forecast information is within the predetermined weather threshold;
further, the apparatus further comprises:
a seventeenth obtaining unit, configured to obtain a first influence parameter according to the first weather forecast information if the first weather forecast information is not within the predetermined weather threshold;
further, the apparatus further comprises:
a first adjusting unit, configured to adjust the first angle according to the first influence parameter;
further, the apparatus further comprises:
an eighteenth obtaining unit, configured to obtain construction duration information of the high-speed railway tunnel;
further, the apparatus further comprises:
a nineteenth obtaining unit, configured to obtain a second impact parameter according to the construction duration information;
further, the apparatus further comprises:
a second adjusting unit, configured to adjust the first position according to the second influence parameter;
various changes and specific examples of the video monitoring method for the lining dropping block of the high-speed railway tunnel in the first embodiment of fig. 1 are also applicable to the video monitoring management device for the lining dropping block of the high-speed railway tunnel in the present embodiment, and through the foregoing detailed description of the video monitoring method for the lining dropping block of the high-speed railway tunnel, those skilled in the art can clearly know the implementation method of the video monitoring device for the lining dropping block of the high-speed railway tunnel in the present embodiment, so for the brevity of the description, detailed description is not repeated here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. four.
Fig. four illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the high-speed railway tunnel lining block-dropping video monitoring method in the foregoing embodiment, the present invention further provides a device of the high-speed railway tunnel lining block-dropping video monitoring method, wherein a computer program is stored thereon, and when the program is executed by a processor, the steps of any one of the methods of the high-speed railway tunnel lining block-dropping video monitoring method are implemented.
Where in fig. 4 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
Exemplary readable storage Medium
Based on the same inventive concept as the video monitoring method for the lining dropping of the high-speed railway tunnel in the previous embodiment, the invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the following steps:
acquiring first image information, wherein the first image information is image information of the inner wall of the high-speed railway tunnel at the first time; obtaining second image information, wherein the second image information is image information of the inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time; according to the first image information and the second image information, deformation amount information of the inner wall of the high-speed railway tunnel is obtained; obtaining the internal waveform information of the high-speed railway tunnel; inputting the deformation amount information and the waveform information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel; obtaining output information of the training model, wherein the output information comprises a first output result and a second output result, the first output result is the result that the wall lining in the high-speed railway tunnel has the block falling, and the second output result is the result that the wall lining in the high-speed railway tunnel has no block falling; and determining whether a first alarm instruction is obtained or not according to the first output result and the second output result, wherein the first alarm instruction is used for reminding that lining falling blocks exist on the inner wall of the high-speed railway tunnel.
According to the video monitoring method and device for the lining dropping of the high-speed railway tunnel, first image information is obtained, and the first image information is image information of the inner wall of the high-speed railway tunnel at the first time; obtaining second image information, wherein the second image information is image information of the inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time; according to the first image information and the second image information, deformation amount information of the inner wall of the high-speed railway tunnel is obtained; obtaining the internal waveform information of the high-speed railway tunnel; inputting the deformation amount information and the waveform information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel; obtaining output information of the training model, wherein the output information comprises a first output result and a second output result, the first output result is the result that the wall lining in the high-speed railway tunnel has the block falling, and the second output result is the result that the wall lining in the high-speed railway tunnel has no block falling; and determining whether a first alarm instruction is obtained or not according to the first output result and the second output result, wherein the first alarm instruction is used for reminding that lining falling blocks exist on the inner wall of the high-speed railway tunnel. The problem of the prior art can't know and report to the police, lead to the high-speed railway tunnel lining to fall the piece and cause the accident is solved, the technical effect of accurate warning of high-speed railway tunnel lining falling piece has been reached.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A high-speed railway tunnel lining block dropping video monitoring method comprises the following steps:
acquiring first image information, wherein the first image information is image information of the inner wall of the high-speed railway tunnel at the first time;
obtaining second image information, wherein the second image information is image information of the inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time;
according to the first image information and the second image information, deformation amount information of the inner wall of the high-speed railway tunnel is obtained;
radar monitoring is carried out inside the high-speed railway tunnel, and waveform information inside the high-speed railway tunnel is obtained;
inputting the deformation amount information and the waveform information into a training model, wherein the training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel;
obtaining output information of the training model, wherein the output information comprises a first output result and a second output result, the first output result is the result that the wall lining in the high-speed railway tunnel is broken, and the second output result is the result that the wall lining in the high-speed railway tunnel is not broken;
if the output information is the first output result, obtaining a first alarm instruction, wherein the first alarm instruction is used for reminding the lining and block falling phenomenon of the inner wall of the high-speed railway tunnel;
and if the output information is the second output result, obtaining a second alarm instruction, wherein the second alarm instruction is used for reminding the daily maintenance of the inner wall of the high-speed railway tunnel.
2. The method of claim 1, wherein the training model comprises:
obtaining deformation quantity information of the inner wall of the high-speed railway tunnel, and taking the deformation quantity information as a horizontal coordinate;
obtaining the internal waveform information of the high-speed railway tunnel, and taking the waveform information as a vertical coordinate;
obtaining a logistic regression line according to the abscissa and the ordinate by adopting a logistic regression model, wherein the logistic regression line comprises a first position and a first angle, and the first position and the first angle are located in a coordinate system constructed by the abscissa and the ordinate; wherein one side of the logistic regression line represents a first output result and the other side of the logistic regression line represents a second output result, wherein the first output result and the second output result are different.
3. The method of claim 1, wherein said obtaining a first alarm instruction if said output information is said first output result comprises:
obtaining a first time threshold;
judging whether a vehicle passes through the high-speed railway tunnel within a first time threshold value after a first alarm instruction;
if the high-speed railway tunnel is passed within a first time threshold value after the first alarm instruction, obtaining a third alarm instruction, wherein the third alarm instruction is used for reminding that the tunnel in front of the train has a lining block falling phenomenon;
and if no train passes through the high-speed railway tunnel within a first time threshold value after the first alarm instruction, obtaining a fourth alarm instruction, wherein the fourth alarm instruction is used for reminding a worker of maintenance in the future.
4. The method of claim 2, wherein the method comprises:
obtaining the position information of the high-speed railway tunnel;
obtaining first weather forecast information according to the position information, wherein the first weather forecast information is weather forecast information at the position information;
obtaining a predetermined weather threshold;
judging whether the first weather forecast information is within the preset weather threshold value;
if the first weather forecast information is not within the predetermined weather threshold, obtaining a first impact parameter;
and adjusting the first angle according to the first influence parameter.
5. The method of claim 2, wherein the method comprises:
acquiring construction time length information of the high-speed railway tunnel;
acquiring a second influence parameter according to the construction duration information;
and adjusting the first position according to the second influence parameter.
6. A high speed railway tunnel lining drop-block video monitoring device, wherein the device comprises:
the first obtaining unit is used for obtaining first image information, and the first image information is image information of the wall inside the high-speed railway tunnel at the first time;
a second obtaining unit, configured to obtain second image information, where the second image information is image information of an inner wall of the high-speed railway tunnel at a second time, and the second time is after the first time;
a third obtaining unit, configured to obtain deformation amount information of the inner wall of the high-speed railway tunnel according to the first image information and the second image information;
a fourth obtaining unit, configured to obtain the internal waveform information of the high-speed railway tunnel;
a first input unit, configured to input the deformation amount information and the waveform information into a training model, where the training model is obtained by training multiple sets of training data, and each set of training data in the multiple sets of training data includes: the deformation amount information, the waveform information and identification information for identifying wall lining falling blocks in the tunnel;
a fifth obtaining unit, configured to obtain output information of the training model, where the output information includes a first output result and a second output result, where the first output result is a result that a wall lining inside the high-speed railway tunnel has a block drop, and the second output result is a result that a wall lining inside the high-speed railway tunnel has no block drop;
a sixth obtaining unit, configured to obtain a first alarm instruction if the output information is a first output result, where the first alarm instruction is used to remind a lining dropping phenomenon of an inner wall of the high-speed railway tunnel;
and the seventh obtaining unit is used for obtaining a second alarm instruction if the output information is a second output result, and the second alarm instruction is used for reminding the daily maintenance of the inner wall of the high-speed railway tunnel.
7. A high speed railway tunnel lining chipping video monitoring apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the program.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010866312.6A CN111878174B (en) | 2020-08-25 | 2020-08-25 | High-speed railway tunnel lining block dropping video monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010866312.6A CN111878174B (en) | 2020-08-25 | 2020-08-25 | High-speed railway tunnel lining block dropping video monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111878174A CN111878174A (en) | 2020-11-03 |
| CN111878174B true CN111878174B (en) | 2022-03-01 |
Family
ID=73199515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010866312.6A Active CN111878174B (en) | 2020-08-25 | 2020-08-25 | High-speed railway tunnel lining block dropping video monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111878174B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435250B (en) * | 2020-12-01 | 2023-04-07 | 江苏博沃汽车电子系统有限公司 | Intelligent maintenance method and device for integrated circuit |
| CN113055649A (en) * | 2021-03-17 | 2021-06-29 | 杭州公路工程监理咨询有限公司 | Tunnel intelligent video monitoring method and device, intelligent terminal and storage medium |
| CN114353686B (en) * | 2021-09-10 | 2023-10-20 | 重庆交通大学 | Intelligent obtaining method and related device for curvature distribution of tunnel lining |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205382956U (en) * | 2016-01-19 | 2016-07-13 | 湖南华宏铁路高新科技开发有限公司 | Railway tunnel wall detection device based on image |
| CN108535721A (en) * | 2018-03-28 | 2018-09-14 | 山东大学 | A kind of secondary lining detecting system and method based on artificial intelligence |
| CN110220909A (en) * | 2019-04-28 | 2019-09-10 | 浙江大学 | A kind of Shield-bored tunnels Defect inspection method based on deep learning |
| CN110454231A (en) * | 2019-09-05 | 2019-11-15 | 中交一公局集团有限公司 | A kind of tunnel safety early warning robot device |
| CN110905602A (en) * | 2019-12-13 | 2020-03-24 | 石家庄铁道大学 | Tunnel is torn open and is traded section atress monitoring devices and system |
| CN111325829A (en) * | 2020-02-13 | 2020-06-23 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Real-time three-dimensional modeling method and system for tunnel |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100567706C (en) * | 2005-07-15 | 2009-12-09 | 联邦科学和工业研究组织 | The method and apparatus that is used for altering gateway structure in monitoring mine section |
-
2020
- 2020-08-25 CN CN202010866312.6A patent/CN111878174B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205382956U (en) * | 2016-01-19 | 2016-07-13 | 湖南华宏铁路高新科技开发有限公司 | Railway tunnel wall detection device based on image |
| CN108535721A (en) * | 2018-03-28 | 2018-09-14 | 山东大学 | A kind of secondary lining detecting system and method based on artificial intelligence |
| CN110220909A (en) * | 2019-04-28 | 2019-09-10 | 浙江大学 | A kind of Shield-bored tunnels Defect inspection method based on deep learning |
| CN110454231A (en) * | 2019-09-05 | 2019-11-15 | 中交一公局集团有限公司 | A kind of tunnel safety early warning robot device |
| CN110905602A (en) * | 2019-12-13 | 2020-03-24 | 石家庄铁道大学 | Tunnel is torn open and is traded section atress monitoring devices and system |
| CN111325829A (en) * | 2020-02-13 | 2020-06-23 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Real-time three-dimensional modeling method and system for tunnel |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111878174A (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111878174B (en) | High-speed railway tunnel lining block dropping video monitoring method and device | |
| CN105632175B (en) | Vehicle behavior analysis method and system | |
| US20210004607A1 (en) | Identification and classification of traffic conflicts | |
| CN101299275B (en) | Method and device for detecting target as well as monitoring system | |
| US20130289865A1 (en) | Predicting impact of a traffic incident on a road network | |
| CN106327880B (en) | A kind of speed recognition methods and its system based on monitor video | |
| CN116343436A (en) | Landslide detection method, landslide detection device, landslide detection equipment and landslide detection medium | |
| CN110487242A (en) | A kind of monitoring system of tunnel ground surface sedimentation | |
| CN112906428B (en) | Image detection region acquisition method and space use condition judgment method | |
| KR100782205B1 (en) | Apparatus and system for displaying speed of car using image detection | |
| CN113408361A (en) | Deep learning-based mining conveyor belt bulk material detection method and system | |
| CN113988353A (en) | Method and device for predicting track of traffic participant and sensor system | |
| US9047495B2 (en) | Identifying impact of a traffic incident on a road network | |
| KR102519715B1 (en) | Road information providing system and method | |
| TWI730509B (en) | Method of acquiring detection zone in image and method of determining zone usage | |
| CN115440071A (en) | Automatic driving illegal parking detection method | |
| CN114488337A (en) | High-altitude parabolic detection method and device | |
| CN110717466B (en) | Method for returning to position of safety helmet based on face detection frame | |
| CN112668535A (en) | YOLOv3 model-based coal mine monkey vehicle violation detection and early warning method | |
| CN115081662A (en) | Data processing method and device, electronic equipment and readable storage medium | |
| CN116977920B (en) | Critical protection method for multi-zone type multi-reasoning early warning mechanism | |
| Prevedouros et al. | Video incident detection tests in freeway tunnels | |
| JP2000149181A (en) | Traffic stream measurement system | |
| JP2005176077A (en) | Camera monitoring system and its monitoring control method | |
| KR102354734B1 (en) | Method and system for predicting, analyzing and judging accidental hazard of car and object having relative high variations |
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 |