CN118082938A - Intelligent safety monitoring system for high-speed dynamic multi-dimensional image of railway - Google Patents
Intelligent safety monitoring system for high-speed dynamic multi-dimensional image of railway Download PDFInfo
- Publication number
- CN118082938A CN118082938A CN202410455307.4A CN202410455307A CN118082938A CN 118082938 A CN118082938 A CN 118082938A CN 202410455307 A CN202410455307 A CN 202410455307A CN 118082938 A CN118082938 A CN 118082938A
- Authority
- CN
- China
- Prior art keywords
- dimensional image
- image data
- train
- railroad car
- ith
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 70
- 230000035945 sensitivity Effects 0.000 claims description 31
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 238000005070 sampling Methods 0.000 claims description 16
- 239000003245 coal Substances 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 claims 1
- 230000007246 mechanism Effects 0.000 abstract description 6
- 238000003384 imaging method Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 208000008918 voyeurism Diseases 0.000 description 1
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides a railway high-speed dynamic multi-dimensional image intelligent safety monitoring system, which is characterized in that when a railway passes through a train along the railway, vehicle number information and two three-dimensional image data are captured, two different recognition mechanisms of the two-dimensional image and the three-dimensional image are organically combined, mutually complemented and fused, intelligent analysis and judgment are carried out on the basis, the two mechanisms are effectively complemented by the comprehensive judgment result, and the judgment accuracy and reliability are improved.
Description
Technical Field
The invention relates to an intelligent safety monitoring system for a high-speed dynamic multi-dimensional image of a railway.
Background
In recent years, along with the rapid development of economy in China, the railway transportation amount is larger, the running times of trains are denser, the grouping of each train is longer, the railway transportation burden is heavier, and the requirements and the pressure on the running safety of the railway transportation are heavier.
This safety pressure is largely due to the quality and integrity of the train carriages on the drive line. Such as: the truck comprises a truck bed plate, a truck carriage side plate (side surface), whether the top of the truck is damaged, whether a tank opening at the top of the truck is closed, whether a fixed cross rod in the truck is intact, whether doors and windows of the truck are closed completely, whether the upper cover shed cloth of bulk goods is bound completely, whether foreign matters protrude from the truck carriage, and whether the truck carriage state for loading goods meets the requirements.
The related problems of the railway wagon also show whether residual coal and frozen coal remain after the railway wagon is unloaded, whether foreign matters and residues exist in the railway wagon or at the bottom of the railway wagon, whether the railway wagon is loaded with goods uniformly, whether overload, left-right offset loading, front-back offset loading and the like exist, and whether the railway wagon loaded objects accord with the functional properties of the railway wagon.
The various phenomena are directly related to the driving safety of the train, the light weight affects the integrity of the transported goods, the heavy weight directly causes major safety accidents of railway transportation, and the whole running order and personal safety of the railway transportation are directly damaged.
In order to ensure the safety of railway operation, a large number of manpower safety personnel are usually arranged in each freight station, especially in marshalling stations and large freight stations in China, and the safety personnel carry out inspection on train section by section train rails successively before the trains come in and go out, so that the aim of never putting out the problem train rails for road passing is achieved. However, this necessitates a lot of labor and time and effort. In other cases, people are inevitably left with the leakage, and under the condition of hundreds of thousands of meters, the problem of the road on the railway is still unavoidable.
For this purpose, some stations are also equipped with some security devices, such as: the track scale overload and unbalanced load detection system and the two-dimensional image monitoring equipment. In the device, the metering device-rail balance/overload and unbalanced load detection system is mature, the function of the two-dimensional imaging device for monitoring the safety state of the railway wagon has natural defects, the internal state of the railway wagon cannot be reflected, only the plane state can be observed, the volume size and the three-dimensional form of the loaded substances cannot be calculated, and meanwhile, the requirements of the shooting of the two-dimensional image on light, weather, night and external conditions are very strict. Therefore, a large number of inspection staff still need to inspect the railway wagon state row by row and section by section, the working efficiency is low, and the conditions of missed inspection and misjudgment exist in manual inspection. The three-dimensional image detection is currently available in single-section, static and manual discrimination in the aspect of road transportation, and in the aspect of railway transportation, a large number of multi-section and dynamic tests cannot be performed, but the three-dimensional laser image can be dynamically and three-dimensionally tested due to line scanning imaging. However, three-dimensional imaging also has inherent drawbacks, which are not as capable of peeping into the panorama of the interior of the vehicle as two-dimensional imaging, and cannot effectively capture the color information of the objects in the vehicle due to the adoption of laser line scanning imaging. Therefore, both two-dimensional imaging and three-dimensional imaging have their own distinct advantages and also their own distinct disadvantages.
In summary, in order to ensure the safe operation of the railway system, improve the working efficiency, reduce the manpower resources and reduce the operation cost, the advantages of two-dimensional imaging and three-dimensional imaging are complemented to form a unified train safety detection system, and the problem to be solved in the aspect of railway safety operation is solved.
Disclosure of Invention
The present invention provides a solution to the above-mentioned problems of the prior art.
Specifically, the invention provides a railway high-speed dynamic multi-dimensional image intelligent safety monitoring system, which is provided with a train number identifier and a vehicle speed meter at a selected place along a railway, and is provided with a central processing unit which is in remote communication with the train number identifier and the vehicle speed meter, in addition, the system is provided with a two-dimensional image collector for collecting two-dimensional image data of a train railway passing through the data sampling points and a three-dimensional image collector for collecting three-dimensional image data of the train railway passing through the data sampling points at the data sampling points selected along the railway, the two-dimensional image collector and the three-dimensional image collector send the two-dimensional image data and the three-dimensional image data of the train railway respectively collected to the central processing unit, and at a specific time, the vehicle speed meter senses the arrival of a train and forms a train arrival signal, the train number identifier senses the train number and forms train number information and train number information of the train (train type, length, width, size, axle number and the like), the train arrival signal and the train number signal are transmitted to the central processing unit, the central processing unit transmits an activation signal to the two-dimensional image collector and the three-dimensional image collector, the two-dimensional image collector collects two-dimensional image data of a train wagon passing through the train, the three-dimensional image collector collects three-dimensional image data of the train wagon passing through the train, the two-dimensional image data and the three-dimensional image data are respectively transmitted back to the central processing unit and stored in a computer storage space in the central processing unit, and respective collection time is recorded, so that the central processing unit stores a plurality of train data of the train which have passed through the train, including the two-dimensional image data and the three-dimensional image data of the train and corresponding train number information, then, control software in the central processing unit screens out two-dimensional image data and three-dimensional image data of specific acquisition time and specific train number from stored train data, and stores the specific two-dimensional image data and the specific three-dimensional image data of specific train number at specific time into a data buffer area of the central processing unit according to the position codes of the two-dimensional image collector and the three-dimensional image collector along the railway, wherein in the central processing unit, intelligent recognition software sequentially judges N train phenomena of the train number, i is less than or equal to 1 and less than N, the number i sequentially takes values from 1 to N, the two-dimensional image data and the three-dimensional image data are respectively sensitive to the ith train phenomenon and are respectively calculated as sensitive degree '1', and the insensitivity is calculated as sensitive degree '0'; based on the sensitivity degree, the intelligent recognition software further forms a normal or not judgment of 'two-dimensional normal/two-dimensional abnormal' and 'three-dimensional normal/three-dimensional abnormal' based on the two-dimensional image data and the three-dimensional image data respectively, the intelligent recognition software determines that the ith wagon phenomenon can be ignored or the number i is used as a selection number to be recorded in the central processing unit based on the normal or not judgment, and once the i is completely valued from 1 to N, the wagon is confirmed to run normally if all the values are ignored, and if one or more selection numbers are recorded in the central processing unit after the i is completely valued from 1 to N, the wagon is subjected to alarm, rechecking, processing or overhaul according to the wagon phenomenon corresponding to all the selection numbers.
Preferably, the train number identifier also senses the condition information of the incoming train and compares the condition information to the train number, thereby ensuring proper identification of the incoming train.
Preferably, for the ith railroad car phenomenon of the railroad car, if both the two-dimensional image data and the three-dimensional image data are set to the sensitivity degree "1", and the two-dimensional image data shows "two-dimensional normal" for the ith railroad car phenomenon, and the three-dimensional image data shows "three-dimensional normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored.
Preferably, for the ith railroad car phenomenon of the railroad car, if both the two-dimensional image data and the three-dimensional image data are set to the sensitivity degree "1", and the two-dimensional image data show "two-dimensionally abnormal" for the ith railroad car phenomenon, and the three-dimensional image data show "three-dimensionally abnormal" for the ith railroad car phenomenon, the number i will be recorded as the selected number in the central processing unit.
Preferably, for the ith railroad car phenomenon of the railroad car, if both the two-dimensional image data and the three-dimensional image data are set to the sensitivity degree "1", however, the two-dimensional image data shows "two-dimensional normal" for the ith railroad car phenomenon and the three-dimensional image data shows "three-dimensional abnormal" for the ith railroad car phenomenon, it is further judged whether the three-dimensional image warning index of the ith railroad car phenomenon prestored in the central processing unit is greater than the first threshold value, if it is greater than the first threshold value, the number i is recorded as the selected number in the central processing unit, and if it is not greater than the first threshold value, the ith railroad car phenomenon is ignored or a warning is given as required.
Preferably, if the two-dimensional image data shows "two-dimensionally abnormal" for the ith railroad car phenomenon of the railroad car and the three-dimensional image data shows "three-dimensionally normal" for the ith railroad car phenomenon, it is further judged whether the two-dimensional image warning index of the ith railroad car phenomenon pre-stored in the central processing unit is greater than the second threshold value, if so, the number i is recorded as an optional number in the central processing unit, and if not, the ith railroad car phenomenon is ignored or a prompt is given as needed.
Preferably, for the ith railroad car phenomenon of the railroad car, if the sensitivity level set by the two-dimensional image data is "1" and the sensitivity level set by the three-dimensional image data is "0", the three-dimensional image data is ignored, in which case if the two-dimensional image data shows "two-dimensionally abnormal" for the ith railroad car phenomenon, the number i will be recorded as an option number in the central processing unit, and if the two-dimensional image data shows "two-dimensionally normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored or a hint is given as needed.
Preferably, for the ith railroad car phenomenon of the railroad car, if the degree of sensitivity set by the two-dimensional image data is "0" and the degree of sensitivity set by the three-dimensional image data is "1", the two-dimensional image data is ignored, in which case, if the three-dimensional image data shows "three-dimensionally abnormal" for the ith railroad car phenomenon, the railroad car phenomenon number i will be recorded as an option number in the central processing unit, and if the three-dimensional image data shows "three-dimensionally normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored or a prompt is given as needed.
Preferably, at the data sampling points, a two-dimensional image collector is arranged on the left side, the right side and the upper side of the train, and 2 three-dimensional image collectors are arranged on the upper side of the train.
Preferably, a gantry is provided at the data sampling point for application in mounting a stationary two-dimensional image collector and a three-dimensional image collector.
Preferably, the system not only can detect whether the train wagon is safe or not, but also can detect residual substances exceeding a certain size range in the train wagon and influence on train running safety and economic value, such as frozen coal residue after train unloading and the like.
In summary, the invention provides a railway high-speed dynamic multi-dimensional image intelligent safety monitoring system, when a railway passes through a train along the railway, the information of a train number and two three-dimensional image data are captured, two different recognition mechanisms of the two-dimensional image and the three-dimensional image are organically combined, mutually complemented and fused, intelligent analysis and judgment are carried out on the basis, the comprehensive judgment result effectively compensates for the two mechanisms, and the judgment accuracy and reliability are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following discussion will discuss the embodiments or the drawings required in the description of the prior art, and it is obvious that the technical solutions described in connection with the drawings are only some embodiments of the present invention, and that other embodiments and drawings thereof can be obtained according to the embodiments shown in the drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a flow chart of the operation of a railway telling dynamic safety detection system according to the invention.
Detailed Description
The following description of the embodiments of the present invention will be made in detail with reference to the accompanying drawings, wherein it is apparent that the embodiments described are only some, but not all embodiments of the present invention. All other embodiments, which can be made by a person of ordinary skill in the art without the need for inventive faculty, are within the scope of the invention, based on the embodiments described in the present invention.
Hereinafter, a specific frame of the railway high-speed dynamic multi-dimensional image intelligent safety monitoring system according to the present invention will be described in detail. In which fig. 1 shows a flow chart of the operation of a railway high-speed dynamic safety detection system according to the present invention.
In order to ensure the normal operation of a two-dimensional and three-dimensional train security inspection system, the synchronization of image acquisition and the integrity of acquired images in the dynamic state of a plurality of batches of train carriages are ensured at first, so that the intelligent safety monitoring system for the high-speed dynamic multi-dimensional images of the railway is provided with a train number identifier and a train speed meter along the railway at first. The train number identifier is used for identifying the train number of the train carriage, so that a plurality of two-dimensional and three-dimensional image acquisition instruments with the same test sampling point can provide the image data of the same train wagon to the central processing unit and analyze the image data by the central processing unit. The speedometer is used for identifying the travelling speed of the train and transmitting a travelling speed signal to the central processing unit, so that the central processing unit can be ensured to completely acquire the image data of the train wagon according to the travelling speed of the train. The central processing unit may be implemented by artificial intelligence software.
Two-dimensional image collectors for collecting two-dimensional image data of the train wagon passing through the data sampling points and three-dimensional image collectors for collecting three-dimensional image data of the train wagon passing through the data sampling points are arranged at the data sampling points along the railway. The two-dimensional image collector and the three-dimensional image collector respectively collect two-dimensional image data and three-dimensional image data, and the two-dimensional image data and the three-dimensional image data are sent to the central processing unit for data storage and data processing.
Preferably, in order to ensure comprehensive and complete collection of the railway wagon image data, two-dimensional image collectors are respectively arranged at the left side, the right side and the upper side of the train at the data sampling points, and 2 three-dimensional image collectors are arranged at the upper side of the train so as to form three-dimensional image data. More preferably, in order to fix the two-dimensional image collector and the three-dimensional image collector, a portal frame may be provided at the data sampling point so as to mount these image collectors.
In the intelligent safety monitoring system for the railway high-speed dynamic multidimensional image, the core part is naturally a central processing unit which is provided with intelligent analysis software, and the system control software is compiled according to the system operation time sequence relation and the relation among all the components of the system so as to ensure the normal operation of the whole system. The intelligent analysis software is the soul of the whole system reaching the functional target. The intelligent analysis software carries out judgment, analysis and feedback on various different images, different vehicle types, different defects and various abnormal phenomena through artificial intelligent supervision learning aiming at big data, and further can achieve accurate and automatic judgment of targets only by repeatedly verifying and modifying parameters according to feedback data.
The specific monitoring process of the intelligent railway high-speed dynamic multi-dimensional image safety monitoring system provided by the invention is specifically described below.
Before the train wagon is monitored, whether the train arrives and which amount of the train arrives are judged first. Thus, at a specific time, the train arrival is sensed by the above-mentioned train speed meter along the railway line and a train arrival signal is formed, the train number is sensed by the train number identifier and train number information and the train number and train self structure information (train type, length, width, height, delivery size, axle number and the like) of the train number are formed, and the train number below the train number is sensed by the counter and a number signal is formed. Thus, the specific attribution of the train to be examined can be clearly known by locking the specific train number of the incoming train or the specific train number in the train number.
Further, the car number identifier may also preferably sense car condition information of an upcoming train, such as train width, weight, etc., and in the background database, these car condition information may often be associated with a car number, that is, for the recorded car number, car condition information of the width, weight, etc. of the train corresponding to the car number may also be recorded at the same time. The train condition information can help to verify whether the train corresponding to the train number is identified correctly.
The train arrival signal and the train number signal are transmitted to the central processing unit, and the central processing unit transmits the activation signal to the two-dimensional image collector and the three-dimensional image collector, so that the two-dimensional image collector collects two-dimensional image data of a train wagon passing through the train, and the three-dimensional image collector collects three-dimensional image data of the train wagon passing through the train. The two-dimensional image data and the three-dimensional image data are respectively sent back to the central processing unit and stored in the storage space of the computer in the central processing unit, and the respective acquisition time and the data address number are recorded. Whereby the central processing unit will store a plurality of train data having passed through the train, including two-dimensional image data and three-dimensional image data of having passed through the train and corresponding train number information.
And then, the control software in the central processing unit screens out the two-dimensional image data and the three-dimensional image data of specific acquisition time and specific train number from the stored train data, and stores the specific two-dimensional image data and the specific three-dimensional image data of the specific train number at the specific time into a data buffer area of the central processing unit according to the position codes of the two-dimensional image collector and the three-dimensional image collector along the railway.
In the central processing unit, intelligent recognition software makes normal and abnormal judgment on the railway wagon state reflected by specific two-dimensional image data, and accordingly a judgment result of 'two-dimensional normal' or 'two-dimensional abnormal' is formed.
It should be noted that the two-dimensional image collector and the three-dimensional image collector can identify various kinds of railway carriage or train carriage, even up to tens of kinds, such as the use state, the degree of old and new, the degree of damage, whether the quantity and the kind of railway carriage or train carriage loading articles are in compliance, whether foreign matters or personnel are in the railway carriage or train carriage, whether the car door is opened without any reason, etc.
These railroad car phenomena are presented in two-dimensional image data and three-dimensional image data to different extents. The so-called "different degree" is actually the sensitivity of each railroad car phenomenon in a two-dimensional image and a three-dimensional image.
For example, a train of cars carrying coal often has little sense of the amount of coal remaining in the car, where the two-dimensional image data is very low in sensitivity to the amount of car load (e.g., coal), which may be counted as "0", while the three-dimensional image data is more sensitive to the amount of coal remaining in the car, which may be counted as "1".
In other words, for each in-car phenomenon, the two-dimensional image cannot perceive the in-car phenomenon, and is defined as "insensitive" and "0" in the two-dimensional image; if the two-dimensional image is capable of perceiving the phenomenon in the railroad car, it is defined as "sensitive" to the two-dimensional image, and is counted as "1". Similarly, the three-dimensional image cannot sense the phenomenon in the car, and is defined as "insensitive" and "0" of the three-dimensional image; if the three-dimensional image is capable of perceiving the phenomenon in the railroad car, it is defined as "sensitive" to the three-dimensional image, and is counted as "1".
Therefore, before the two-dimensional image data and the three-dimensional image data are combined to judge whether the railway wagon is normal or abnormal, the sensitivity degree of the two-dimensional image and the three-dimensional image to the specific railway wagon phenomenon is firstly confirmed.
The specific judgment process of the central processing unit will be described in detail hereinafter. In the judging sequence, firstly judging that the sensitivity is insensitive, and then judging that the normal state is abnormal.
First, N kinds of railroad car phenomena of railroad car are set in the central processing unit. It is apparent that, as described above, in the central processing unit, each railroad car phenomenon may be set to a sensitivity level "1" or a sensitivity level "0" for both the two-dimensional image data and the three-dimensional image data.
The central processing unit judges the N railway wagon phenomena in sequence. The judgment process is as follows.
For the ith railroad car phenomenon (wherein i is equal to or more than 1 and is equal to N, i takes values from 1 to N in sequence), if the two-dimensional image data and the three-dimensional image data are both set to the sensitivity degree of "1", and the two-dimensional image data show "two-dimensional normal" for the ith railroad car phenomenon, and the three-dimensional image data show "three-dimensional normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored, in other words, the ith railroad car phenomenon is normal under the judgment of two dimensions without consideration.
For the ith railroad car phenomenon, if the two-dimensional image data and the three-dimensional image data are both set to the sensitivity degree "1", and the two-dimensional image data shows "two-dimensional abnormality" for the ith railroad car phenomenon, and the three-dimensional image data shows "three-dimensional abnormality" for the ith railroad car phenomenon, the railroad car phenomenon number i will be recorded as a selection number in the central processing unit, in other words, the ith railroad car phenomenon is abnormal under the judgment of both dimensions, which needs to be considered with emphasis.
For the ith railroad car phenomenon, if the two-dimensional image data and the three-dimensional image data are both set to the sensitivity degree of "1", however, the two-dimensional image data shows "two-dimensional normal" for the ith railroad car phenomenon and the three-dimensional image data shows "three-dimensional abnormal" for the ith railroad car phenomenon, it is further judged whether the three-dimensional image warning index of the ith railroad car phenomenon pre-stored in the central processing unit is greater than a first threshold value, if it is actually greater than the first threshold value, the railroad car phenomenon number i is recorded as the selected number in the central processing unit, if it is not greater than the first threshold value, the ith railroad car phenomenon is ignored or a prompt is given as needed.
And vice versa, if the two-dimensional image data shows "two-dimensional abnormal" for the ith railroad car phenomenon and the three-dimensional image data shows "three-dimensional normal" for the ith railroad car phenomenon, further judging whether the two-dimensional image warning index of the ith railroad car phenomenon pre-stored in the central processing unit is larger than a second threshold value, if so, the railroad car phenomenon number i is recorded in the central processing unit as an optional number, if not, the ith railroad car phenomenon is ignored or a prompt is given as required.
While for the ith railroad car phenomenon, if the sensitivity levels set for the two-dimensional image data and the three-dimensional image data are different, for example, the sensitivity level set for the two-dimensional image data is "1" and the sensitivity level set for the three-dimensional image data is "0", the three-dimensional image data is ignored, in which case, if the two-dimensional image data shows "two-dimensional abnormality" for the ith railroad car phenomenon, the railroad car phenomenon number i will be recorded in the central processing unit as an option number. Of course, if the two-dimensional image data shows "two-dimensional normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored or a prompt is given as needed.
And vice versa. For example, if the sensitivity level set for the two-dimensional image data is "0" and the sensitivity level set for the three-dimensional image data is "1", the two-dimensional image data is ignored, in which case if the three-dimensional image data shows "three-dimensional abnormality" for the ith railroad car phenomenon, the railroad car phenomenon number i will be recorded as the selection number in the central processing unit. Of course, if the three-dimensional image data shows "three-dimensional normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored.
In the central processing unit, once i is completely valued from 1 to N, if all the valued values are ignored, the normal operation of the wagon is confirmed. If one or more selected numbers are recorded in the central processing unit after the values of i from 1 to N are finished, alarming, rechecking, processing or overhauling the train according to the train phenomenon corresponding to all the selected numbers.
The present invention has been described in detail. In summary, the invention provides a railway high-speed dynamic multi-dimensional image intelligent safety monitoring system, when a railway passes through a train along the railway, the information of a train number and two three-dimensional image data are captured, two different recognition mechanisms of the two-dimensional image and the three-dimensional image are organically combined, mutually complemented and fused, intelligent analysis and judgment are carried out on the basis, the comprehensive judgment result effectively compensates for the two mechanisms, and the judgment accuracy and reliability are improved.
The foregoing description of the exemplary embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, and variations which fall within the spirit and scope of the invention are intended to be included in the scope of the invention.
Claims (10)
1. A railway high-speed dynamic multi-dimensional image intelligent safety monitoring system is characterized in that,
The system is provided with a train number identifier and a speedometer along the railway, and is provided with a central processing unit which is in remote communication with the train number identifier and the speedometer, in addition, the system is provided with a two-dimensional image collector for collecting two-dimensional image data of the train railway passing through the data sampling points and a three-dimensional image collector for collecting three-dimensional image data of the train railway passing through the data sampling points at the selected data sampling points along the railway, the two-dimensional image collector and the three-dimensional image collector send the two-dimensional image data and the three-dimensional image data of the train railway respectively collected to the central processing unit,
At a specific time, the vehicle speed meter senses the arrival of a train and forms a train arrival signal, the train number identifier senses the train number and forms a train number signal, the counter is used for sensing the train number of a specific section of train under the train number and forms a number signal,
The train arrival signal, the train number signal and the number signal are transmitted to a central processing unit, the central processing unit transmits the activation signal to a two-dimensional image collector and a three-dimensional image collector, the two-dimensional image collector collects two-dimensional image data of a train wagon passing through the train, the three-dimensional image collector collects three-dimensional image data of the train wagon passing through the train, the two-dimensional image data and the three-dimensional image data are respectively transmitted back to the central processing unit and stored in a computer storage space in the central processing unit respectively, and the respective collection time is recorded, thereby a plurality of train data of the train which has passed through the train, including the two-dimensional image data and the three-dimensional image data of the train and corresponding train number information are stored in the central processing unit,
Then, the control software in the central processing unit screens out the two-dimensional image data and the three-dimensional image data of the specific acquisition time and the specific train number from the stored train data, and stores the specific two-dimensional image data and the specific three-dimensional image data of the specific train number at the specific time into the data buffer area of the central processing unit according to the position codes of the two-dimensional image collector and the three-dimensional image collector along the railway,
In a central processing unit, intelligent recognition software sequentially judges N railway wagon phenomena of the train number, wherein i is more than or equal to 1 and less than or equal to N, the number i sequentially takes values from 1 to N, the two-dimensional image data and the three-dimensional image data are respectively sensitive to the ith railway wagon phenomenon and are respectively calculated as a sensitive degree '1', and the insensitivity is calculated as a sensitive degree '0'; based on the sensitivity, the intelligent recognition software further forms a normal or not judgment of 'two-dimensional normal/two-dimensional abnormal' and 'three-dimensional normal/three-dimensional abnormal' based on the two-dimensional graphic data and the three-dimensional image data respectively, the intelligent recognition software determines that the ith train wagon phenomenon can be ignored or the number i is used as an option to be recorded in the central processing unit based on the normal or not judgment,
Once i is completely valued from 1 to N, if all the values are ignored, the running of the train is confirmed to be normal, and if one or more selected numbers are recorded in the central processing unit after i is completely valued from 1 to N, the train is subjected to alarm maintenance rechecking processing according to the train phenomenon corresponding to all the selected numbers.
2. The system of claim 1 wherein the train number identifier also brings up the condition information of the incoming train and compares the condition information to the train number in combination, thereby ensuring proper identification of the incoming train.
3. The system according to claim 1, wherein for an i-th railroad car phenomenon of the railroad car, if both the two-dimensional image data and the three-dimensional image data are set to the sensitivity level "1", and the two-dimensional image data show "two-dimensional normal" for the i-th railroad car phenomenon, and the three-dimensional image data show "three-dimensional normal" for the i-th railroad car phenomenon, the i-th railroad car phenomenon is ignored.
4. The system according to claim 1, wherein for the ith railroad car phenomenon of the railroad car, if both the two-dimensional image data and the three-dimensional image data are set to the sensitivity degree "1", and the two-dimensional image data show "two-dimensionally abnormal" for the ith railroad car phenomenon, and the three-dimensional image data show "three-dimensionally abnormal" for the ith railroad car phenomenon, the number i is recorded as an option number in the central processing unit.
5. The system according to claim 1, wherein for an i-th railroad car phenomenon of the railroad car, if both the two-dimensional image data and the three-dimensional image data are set to the sensitivity degree "1", however, the two-dimensional image data show "two-dimensional normal" for the i-th railroad car phenomenon and the three-dimensional image data show "three-dimensional abnormal" for the i-th railroad car phenomenon, it is further judged whether or not a three-dimensional image warning index of the i-th railroad car phenomenon pre-stored in the central processing unit is greater than a first threshold value, if it is greater than the first threshold value, the number i is recorded as a selected reading in the central processing unit, and if it is not greater than the first threshold value, the i-th railroad car phenomenon is ignored.
6. The system according to claim 1, wherein for the ith railroad car phenomenon of the railroad car, if the two-dimensional image data and the three-dimensional image data are both set to the sensitivity degree "1", however, the two-dimensional image data shows "two-dimensionally abnormal" for the ith railroad car phenomenon and the three-dimensional image data shows "three-dimensionally normal" for the ith railroad car phenomenon, it is further judged whether the two-dimensional image warning index of the ith railroad car phenomenon pre-stored in the central processing unit is greater than a second threshold value, and if it is greater than the second threshold value, the number i is recorded in the central processing unit as a selected reading, and if it is not greater than the second threshold value, the ith railroad car phenomenon is ignored.
7. The system according to claim 1, wherein for the ith railroad car phenomenon, if the degree of sensitivity set by the two-dimensional image data is "1" and the degree of sensitivity set by the three-dimensional image data is "0", the three-dimensional image data is ignored, in which case, if the two-dimensional image data shows "two-dimensionally abnormal" for the ith railroad car phenomenon, the number i is recorded as an option number in the central processing unit, and if the two-dimensional image data shows "two-dimensionally normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored.
8. The system according to claim 1, wherein for the ith railroad car phenomenon, if the degree of sensitivity set by the two-dimensional image data is "0" and the degree of sensitivity set by the three-dimensional image data is "1", the two-dimensional image data is ignored, in which case, if the three-dimensional image data shows "three-dimensionally abnormal" for the ith railroad car phenomenon, the railroad car phenomenon number i is recorded as an option in the central processing unit, and if the three-dimensional image data shows "three-dimensionally normal" for the ith railroad car phenomenon, the ith railroad car phenomenon is ignored.
9. The system of claim 1, wherein one two-dimensional image collector is disposed at each of the left, right and upper sides of the train at the data sampling point, 2 three-dimensional image collectors are disposed at the upper side of the train, and a portal frame is disposed at the data sampling point for mounting the fixed two-dimensional image collector and the three-dimensional image collector.
10. The system of claim 1, wherein in the event that one of the phenomena of coal remaining is present in the railroad car and the volume of coal remaining exceeds the rated amount, the determination result of "two-dimensional normal" and "three-dimensional abnormal" will be obtained simultaneously.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410455307.4A CN118082938A (en) | 2024-04-16 | 2024-04-16 | Intelligent safety monitoring system for high-speed dynamic multi-dimensional image of railway |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410455307.4A CN118082938A (en) | 2024-04-16 | 2024-04-16 | Intelligent safety monitoring system for high-speed dynamic multi-dimensional image of railway |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118082938A true CN118082938A (en) | 2024-05-28 |
Family
ID=91151893
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410455307.4A Pending CN118082938A (en) | 2024-04-16 | 2024-04-16 | Intelligent safety monitoring system for high-speed dynamic multi-dimensional image of railway |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118082938A (en) |
-
2024
- 2024-04-16 CN CN202410455307.4A patent/CN118082938A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102941864B (en) | Train loading state high-definition monitoring and overloading detection method | |
CN107103654A (en) | A kind of Cargo Inspection safety detection controlling and management and method | |
CN201429413Y (en) | Pantograph performance on-line automatic detection system for high-speed trains | |
CN109165541A (en) | Coding method for vehicle component in intelligent recognition rail traffic vehicles image | |
CN100511287C (en) | Intelligent management method for long-distance passenger transport fare | |
CN110646801A (en) | Detection device and detection method for railway wagon carriage | |
CN111942434A (en) | Intelligent fault image detection device for key parts of railway wagon | |
CN102749908B (en) | A kind of thermal power plant fuel Intelligent unattended managing and control system on duty and method | |
CN115479949B (en) | Bridge safety monitoring and early warning method and system based on big data | |
CN112033510A (en) | Data authenticity monitoring platform based on garbage storage and transportation process | |
RU2754286C1 (en) | Method for sensory analysis, control system containing computer software product for sensory analysis, passenger counting system and vehicle for transporting passengers, in particular, in rail and road traffic | |
CN118082938A (en) | Intelligent safety monitoring system for high-speed dynamic multi-dimensional image of railway | |
CN113734241A (en) | Method and system for monitoring ice and snow state of magnetic suspension line | |
CN210591921U (en) | Dynamic image detection system for whole-body operation faults of motor train unit | |
KR102623294B1 (en) | System for measuring dynamic movement of railroad | |
CN207717572U (en) | A kind of train transporting coal quality inspection device | |
CN112432963A (en) | Movable vehicle inspection system based on X ray | |
CN105277622B (en) | A kind of Railway wheelset method for detection fault detection and device | |
CN214472818U (en) | Mounting rack for intelligent railway goods inspection detection device and detection device | |
DE102007011231A1 (en) | Testing device for a transport system for general cargo containers | |
CN114279542A (en) | Toll station access & exit transfinite transportation detecting system | |
Maly et al. | New development of an overall train inspection system for increased operational safety | |
CN201863868U (en) | Novel track data acquisition train | |
CN205862592U (en) | A kind of novel intelligent load bearing system | |
CN204614210U (en) | A kind of overload transport based on electronic license plate just rechecks system |
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 |