CN116811962A - Train running detection method and system based on multi-feature fusion - Google Patents

Train running detection method and system based on multi-feature fusion Download PDF

Info

Publication number
CN116811962A
CN116811962A CN202211576581.4A CN202211576581A CN116811962A CN 116811962 A CN116811962 A CN 116811962A CN 202211576581 A CN202211576581 A CN 202211576581A CN 116811962 A CN116811962 A CN 116811962A
Authority
CN
China
Prior art keywords
train
running
distance value
station
actual distance
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
Application number
CN202211576581.4A
Other languages
Chinese (zh)
Inventor
余丹
兰雨晴
李易君
姚修
彭建强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Standard Intelligent Security Technology Co Ltd
Original Assignee
China Standard Intelligent Security Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Standard Intelligent Security Technology Co Ltd filed Critical China Standard Intelligent Security Technology Co Ltd
Priority to CN202211576581.4A priority Critical patent/CN116811962A/en
Publication of CN116811962A publication Critical patent/CN116811962A/en
Pending legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
    • B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
    • B61L23/08—Control, warning or like safety means along the route or between vehicles or trains for controlling traffic in one direction only
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Train Traffic Observation, Control, And Security (AREA)

Abstract

The invention provides a train running detection method and a train running detection system based on multi-feature fusion, which are characterized in that under the condition that a train is separated from an overhaul station by a larger distance and a smaller distance, multi-feature monitoring is carried out on the train by radar equipment and a camera respectively, the train is roughly monitored in a radar scanning mode when the distance is separated by the larger distance, and the train is accurately monitored in an image shooting mode when the distance is separated by the smaller distance, so that a proper braking control instruction can be conveniently sent to the train in time, the train can be ensured to be aligned to a platform area corresponding to the overhaul station, and the control accuracy and the control reliability of the train parked at the overhaul station are improved.

Description

Train running detection method and system based on multi-feature fusion
Technical Field
The invention relates to the technical field of train running monitoring, in particular to a train running detection method and system based on multi-feature fusion.
Background
After a certain mileage, the train needs to enter a station for maintenance, and then the train needs to be stopped at a corresponding maintenance station for inspection. In order to ensure that the train can stop at the overhaul station, radar equipment is usually arranged outside the overhaul station, and radar scanning detection is carried out on the train so as to determine whether the train runs close to the overhaul station. However, the method is only used for roughly judging the relative motion relationship between the train and the overhaul station, the real-time relative position relationship between the train and the overhaul station cannot be accurately tracked, and the train is dynamically monitored only by virtue of radar equipment, so that the situation of false alarm is easy to occur, and the control accuracy and reliability of stopping the train at the overhaul station are reduced.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides a train running detection method and system based on multi-feature fusion, which utilize radar equipment to perform radar scanning detection on a train to obtain running state information of the train, so as to judge whether the train enters a monitoring area range or not and estimate running duration of the train in the monitoring area range; shooting and analyzing train running images in the running duration time period to obtain running posture information of the train and an actual distance value between the train and a maintenance station, so as to adjust the running state of the train; according to the actual distance value, a braking control instruction is sent to a driving control platform of the train so as to instruct the train to stop at a platform area corresponding to the maintenance station, radar equipment and a camera are respectively utilized to carry out multi-feature monitoring on the train under the condition that the train is separated from the maintenance station by a larger distance and a smaller distance, the train is roughly monitored in a radar scanning mode when the distance is larger, and the train is accurately monitored in an image shooting mode when the distance is smaller, so that the proper braking control instruction can be sent to the train in time, and the train is ensured to be aligned to the platform area corresponding to the maintenance station, thereby improving the control accuracy and reliability of the train to stop at the maintenance station.
The invention provides a train running detection method based on multi-feature fusion, which comprises the following steps:
step S1, radar equipment indicating a preset distance value from an overhaul station performs radar scanning detection on a train so as to obtain running state information of the train; judging whether the train enters a monitoring area range of the overhaul station according to the train running state information; estimating the running duration time of the train in the monitoring area according to the running state information of the train;
step S2, a camera at the maintenance station is instructed to shoot the train in a time period corresponding to the running duration, and a train running image is obtained; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station; according to the driving posture information and the actual distance value, the driving state of the train is adjusted;
and step S3, according to the actual distance value, a braking control instruction is sent to a driving control platform of the train, so that the train is instructed to stop at a platform area corresponding to the maintenance station.
Further, in the step S1, radar equipment indicating a preset distance value from the maintenance station performs radar scanning detection on the train, so as to obtain running state information of the train; judging whether the train enters a monitoring area range of the overhaul station according to the train running state information; and estimating the running duration of the train in the monitoring area according to the running state information of the train specifically comprises the following steps:
the radar equipment which indicates a preset distance value from the overhaul station periodically scans and transmits radar signals outwards, so that radar scanning detection is carried out on trains nearby the radar equipment; according to the radar signals emitted by the radar equipment outwards and the radar signals reflected by the train, obtaining the distance between the train and the radar equipment and the running speed of the train;
judging whether the train enters the monitoring area range of the overhaul station according to the distance and the radius of the monitoring area range of the overhaul station; if yes, estimating the running duration time of the train in the monitoring area according to the running speed; if not, continuing to instruct the radar equipment to periodically scan outwards to transmit radar signals.
Further, in the step S2, a camera located at the inspection station is instructed to shoot the train in a time period corresponding to the running duration, so as to obtain a train running image; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station; according to the driving posture information and the actual distance value, the adjusting the driving state of the train specifically comprises:
a camera at the maintenance station is instructed to dynamically shoot the train in a time period corresponding to the running duration, and a running dynamic image of the train is obtained; carrying out framing treatment on the train running dynamic image to obtain a plurality of train running image frames;
extracting outline information of a train from each train running image frame, and obtaining running posture information of the train according to the outline information corresponding to the train running image frames; the driving gesture information comprises an inclination angle of a vehicle body relative to a plane where a rail is positioned in the driving process of the train;
identifying and obtaining indication information of a preset interval indication board on a rail from each train running image frame so as to obtain an actual distance value between a train and an overhaul station;
judging whether the train is in a running unstable state in the running process according to the running posture information; if the train is in a running unstable state and the actual distance value is greater than a preset distance threshold value, indicating the train to run at a constant speed at a preset speed; if the train is in a stable running state and the actual distance value is larger than a preset distance threshold value, indicating the train to enter an acceleration running mode at a preset acceleration; and if the actual distance value is smaller than or equal to a preset distance threshold value, indicating the train to enter a speed-reducing running mode.
Further, in the step S3, according to the actual distance value, sending a brake control instruction to a driving control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station specifically includes:
if the actual distance value is smaller than or equal to a preset distance threshold value, determining a driving distance value on a rail between the current train and a platform area to be stopped according to the actual distance value; and determining a deceleration acceleration value corresponding to the deceleration running mode according to the running distance value and the real-time running speed of the train, and sending a deceleration braking control instruction to a running control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station.
The invention also provides a train running detection system based on multi-feature fusion, which comprises:
the radar scanning control module is used for indicating radar equipment with a preset distance value from the overhaul station to perform radar scanning detection on the train so as to obtain running state information of the train;
the train running analysis module is used for judging whether the train enters the monitoring area range of the overhaul station according to the train running state information; estimating the running duration time of the train in the monitoring area according to the running state information of the train;
the image shooting control and analysis module is used for indicating a camera positioned at the maintenance station to shoot the train in a time period corresponding to the continuous running time to obtain a train running image; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station;
the train running adjustment module is used for adjusting the running state of the train according to the running posture information and the actual distance value;
and the train stopping control module is used for sending a braking control instruction to a driving control platform of the train according to the actual distance value so as to indicate that the train is stopped at a platform area corresponding to the maintenance station.
Further, the radar scanning control module instructs radar equipment with a preset distance value from the overhaul station to perform radar scanning detection on the train, so as to obtain running state information of the train specifically includes:
the radar equipment which indicates a preset distance value from the overhaul station periodically scans and transmits radar signals outwards, so that radar scanning detection is carried out on trains nearby the radar equipment; according to the radar signals emitted by the radar equipment outwards and the radar signals reflected by the train, obtaining the distance between the train and the radar equipment and the running speed of the train;
the train running analysis module judges whether the train enters a monitoring area range of the overhaul station according to the train running state information; and estimating the running duration of the train in the monitoring area according to the running state information of the train specifically comprises the following steps:
judging whether the train enters the monitoring area range of the overhaul station according to the distance and the radius of the monitoring area range of the overhaul station; if so, estimating the running duration time of the train in the monitoring area according to the running speed.
Further, the image shooting control and analysis module instructs a camera positioned at the maintenance station to shoot the train in a time period corresponding to the continuous running time to obtain a train running image; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station, wherein the method specifically comprises the following steps of:
a camera at the maintenance station is instructed to dynamically shoot the train in a time period corresponding to the running duration, and a running dynamic image of the train is obtained; carrying out framing treatment on the train running dynamic image to obtain a plurality of train running image frames;
extracting outline information of a train from each train running image frame, and obtaining running posture information of the train according to the outline information corresponding to the train running image frames; the driving gesture information comprises an inclination angle of a vehicle body relative to a plane where a rail is positioned in the driving process of the train;
identifying and obtaining indication information of a preset interval indication board on a rail from each train running image frame so as to obtain an actual distance value between a train and an overhaul station;
the train running adjustment module adjusts the running state of the train according to the running posture information and the actual distance value, and specifically comprises the following steps:
judging whether the train is in a running unstable state in the running process according to the running posture information; if the train is in a running unstable state and the actual distance value is greater than a preset distance threshold value, indicating the train to run at a constant speed at a preset speed; if the train is in a stable running state and the actual distance value is larger than a preset distance threshold value, indicating the train to enter an acceleration running mode at a preset acceleration; and if the actual distance value is smaller than or equal to a preset distance threshold value, indicating the train to enter a speed-reducing running mode.
Further, the train stopping control module sends a braking control instruction to a driving control platform of the train according to the actual distance value, so as to indicate that the train is stopped at a platform area corresponding to the maintenance station, and the method specifically comprises the following steps:
if the actual distance value is smaller than or equal to a preset distance threshold value, determining a driving distance value on a rail between the current train and a platform area to be stopped according to the actual distance value; and determining a deceleration acceleration value corresponding to the deceleration running mode according to the running distance value and the real-time running speed of the train, and sending a deceleration braking control instruction to a running control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station.
Compared with the prior art, the train running detection method and system based on multi-feature fusion utilize radar equipment to perform radar scanning detection on the train to obtain running state information of the train, so as to judge whether the train enters a monitoring area range or not and estimate running duration of the train in the monitoring area range; shooting and analyzing train running images in the running duration time period to obtain running posture information of the train and an actual distance value between the train and a maintenance station, so as to adjust the running state of the train; according to the actual distance value, a braking control instruction is sent to a driving control platform of the train so as to instruct the train to stop at a platform area corresponding to the maintenance station, radar equipment and a camera are respectively utilized to carry out multi-feature monitoring on the train under the condition that the train is separated from the maintenance station by a larger distance and a smaller distance, the train is roughly monitored in a radar scanning mode when the distance is larger, and the train is accurately monitored in an image shooting mode when the distance is smaller, so that the proper braking control instruction can be sent to the train in time, and the train is ensured to be aligned to the platform area corresponding to the maintenance station, thereby improving the control accuracy and reliability of the train to stop at the maintenance station.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a train running detection method based on multi-feature fusion.
Fig. 2 is a schematic structural diagram of a train running detection system based on multi-feature fusion.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a train running detection method based on multi-feature fusion according to an embodiment of the present invention is shown. The train running detection method based on multi-feature fusion comprises the following steps:
step S1, radar equipment indicating a preset distance value from an overhaul station performs radar scanning detection on a train so as to obtain running state information of the train; judging whether the train enters a monitoring area range of the overhaul station according to the train running state information; estimating the running duration time of the train in the monitoring area according to the running state information of the train;
step S2, a camera at the maintenance station is instructed to shoot the train in a time period corresponding to the running duration time, and a train running image is obtained; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station; according to the driving posture information and the actual distance value, the driving state of the train is adjusted;
and step S3, according to the actual distance value, a braking control instruction is sent to a driving control platform of the train, so that the train is instructed to stop at a platform area corresponding to the maintenance station.
The beneficial effects of the technical scheme are as follows: the train running detection method based on multi-feature fusion utilizes radar equipment to perform radar scanning detection on the train to obtain running state information of the train, so as to judge whether the train enters a monitoring area range or not and estimate running duration time of the train in the monitoring area range; shooting and analyzing train running images in the running duration time period to obtain running posture information of the train and an actual distance value between the train and a maintenance station, so as to adjust the running state of the train; according to the actual distance value, a braking control instruction is sent to a driving control platform of the train so as to instruct the train to stop at a platform area corresponding to the maintenance station, radar equipment and a camera are respectively utilized to carry out multi-feature monitoring on the train under the condition that the train is separated from the maintenance station by a larger distance and a smaller distance, the train is roughly monitored in a radar scanning mode when the distance is larger, and the train is accurately monitored in an image shooting mode when the distance is smaller, so that the proper braking control instruction can be sent to the train in time, and the train is ensured to be aligned to the platform area corresponding to the maintenance station, thereby improving the control accuracy and reliability of the train to stop at the maintenance station.
Preferably, in the step S1, radar equipment indicating a preset distance value from the maintenance station performs radar scanning detection on the train, so as to obtain running state information of the train; judging whether the train enters a monitoring area range of the overhaul station according to the train running state information; and estimating the running duration of the train in the monitoring area according to the running state information of the train specifically comprises the following steps:
the radar equipment which indicates a preset distance value from the overhaul station periodically scans and transmits radar signals outwards, so that radar scanning detection is carried out on trains nearby the radar equipment; according to the radar signals emitted by the radar equipment outwards and the radar signals reflected by the train, obtaining the distance between the train and the radar equipment and the running speed of the train;
judging whether the train enters the monitoring area range of the overhaul station according to the distance and the radius of the monitoring area range of the overhaul station; if yes, estimating the running duration time of the train in the monitoring area according to the running speed; if not, continuing to instruct the radar equipment to periodically scan outwards to transmit radar signals.
The beneficial effects of the technical scheme are as follows: and erecting radar equipment at a position which is separated from the maintenance station by a preset distance value, so that the radar equipment is used as a first monitoring checkpoint for the train to run close to the maintenance station. The radar equipment periodically scans outwards to emit radar signals, and when the radar signals reach the surface of the train and are reflected back, the radar equipment performs differential processing on the intensity or time of the outwards emitted radar signals and the received radar signals, namely, the distance between the train and the radar equipment and the running speed of the train are obtained, so that the running state of the train is quantitatively calibrated. In addition, the distance and the radius of the monitoring area range of the overhaul station are compared, if the distance is smaller than or equal to the radius of the monitoring area range, the fact that the train enters the monitoring area range of the overhaul station is determined, at the moment, the follow-up timely indication camera is convenient to dynamically shoot the train, and switching from rough monitoring of radar equipment to accurate monitoring of the camera is achieved. And then, according to the radius and the running speed of the monitoring area range, determining the running duration time of the train in the monitoring area range, so that the dynamic shooting duration time of the camera on the train can be controlled conveniently.
Preferably, in the step S2, a camera located at the inspection station is instructed to photograph the train in a time period corresponding to the driving duration, so as to obtain a train driving image; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station; according to the driving posture information and the actual distance value, the adjusting the driving state of the train specifically comprises:
a camera at the maintenance station is instructed to dynamically shoot the train in a time period corresponding to the running duration, and a running dynamic image of the train is obtained; carrying out framing treatment on the train running dynamic image to obtain a plurality of train running image frames;
extracting outline information of a train from each train running image frame, and obtaining running posture information of the train according to the outline information corresponding to the train running image frame; the driving gesture information comprises an inclination angle of a vehicle body relative to a plane where a rail is positioned in the driving process of the train;
identifying and obtaining indication information of a preset interval indication board on a rail from each train running image frame so as to obtain an actual distance value between a train and an overhaul station;
judging whether the train is in a running unstable state in the running process according to the running posture information; if the train is in a running unstable state and the actual distance value is larger than a preset distance threshold value, the train is instructed to run at a constant speed at a preset speed, so that the train can be ensured to run stably and the occurrence of side-tipping accidents can be avoided; if the train is in a stable running state and the actual distance value is larger than a preset distance threshold value, the train is instructed to enter an acceleration running mode at a preset acceleration, so that the train can quickly arrive at a maintenance station under the condition of ensuring a stable form of the train; if the actual distance value is smaller than or equal to the preset distance threshold value, the train is instructed to enter a speed reduction running mode, so that the situation that accurate stopping cannot be performed after the train enters a platform area of the overhaul station can be avoided.
The beneficial effects of the technical scheme are as follows: when the train enters the monitoring area of the maintenance station, a camera which is erected in advance at the maintenance station is indicated to dynamically shoot the train, and the shot train running dynamic image is divided into a plurality of train running image frames. And carrying out identification processing on the outline of the train and the indication information of the track preset indication sign on each train running image frame to obtain the running posture information of the train and the actual distance value between the train and the maintenance station, so as to be convenient for carrying out quantitative calibration on the running state of the train and the relative position relation between the train and the maintenance station.
Preferably, in the step S3, according to the actual distance value, a brake control instruction is sent to a driving control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station specifically includes:
if the actual distance value is smaller than or equal to a preset distance threshold value, determining a driving distance value on a rail between the current train and a platform area to be stopped according to the actual distance value; and determining a deceleration acceleration value corresponding to the deceleration running mode according to the running distance value and the real-time running speed of the train, and sending a deceleration braking control instruction to a running control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station.
The beneficial effects of the technical scheme are as follows: by the method, the running distance value on the rail and the real-time running speed of the train between the current train and the platform area to be parked are taken as references, accurate deceleration braking control is performed on the train, the train is ensured to be aligned to the corresponding platform area to be parked at the maintenance station, and the parking reliability of the train is improved.
Referring to fig. 2, a schematic structural diagram of a train running detection system based on multi-feature fusion according to an embodiment of the present invention is provided. The train running detection system based on multi-feature fusion comprises:
the radar scanning control module is used for indicating radar equipment with a preset distance value from the overhaul station to perform radar scanning detection on the train so as to obtain running state information of the train;
the train running analysis module is used for judging whether the train enters the monitoring area range of the overhaul station according to the train running state information; estimating the running duration time of the train in the monitoring area according to the running state information of the train;
the image shooting control and analysis module is used for indicating a camera positioned at the maintenance station to shoot the train in a time period corresponding to the continuous running time to obtain a train running image; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station;
the train running adjustment module is used for adjusting the running state of the train according to the running posture information and the actual distance value;
and the train stopping control module is used for sending a braking control instruction to a driving control platform of the train according to the actual distance value so as to indicate that the train is stopped at a platform area corresponding to the maintenance station.
The beneficial effects of the technical scheme are as follows: the train running detection system based on multi-feature fusion utilizes radar equipment to perform radar scanning detection on a train to obtain running state information of the train, so as to judge whether the train enters a monitoring area range or not and estimate running duration time of the train in the monitoring area range; shooting and analyzing train running images in the running duration time period to obtain running posture information of the train and an actual distance value between the train and a maintenance station, so as to adjust the running state of the train; according to the actual distance value, a braking control instruction is sent to a driving control platform of the train so as to instruct the train to stop at a platform area corresponding to the maintenance station, radar equipment and a camera are respectively utilized to carry out multi-feature monitoring on the train under the condition that the train is separated from the maintenance station by a larger distance and a smaller distance, the train is roughly monitored in a radar scanning mode when the distance is larger, and the train is accurately monitored in an image shooting mode when the distance is smaller, so that the proper braking control instruction can be sent to the train in time, and the train is ensured to be aligned to the platform area corresponding to the maintenance station, thereby improving the control accuracy and reliability of the train to stop at the maintenance station.
Preferably, the radar scanning control module instructs radar equipment with a preset distance value from the overhaul station to perform radar scanning detection on the train, so as to obtain running state information of the train specifically includes:
the radar equipment which indicates a preset distance value from the overhaul station periodically scans and transmits radar signals outwards, so that radar scanning detection is carried out on trains nearby the radar equipment; according to the radar signals emitted by the radar equipment outwards and the radar signals reflected by the train, obtaining the distance between the train and the radar equipment and the running speed of the train;
the train running analysis module judges whether the train enters a monitoring area range of the overhaul station according to the train running state information; and estimating the running duration of the train in the monitoring area according to the running state information of the train specifically comprises the following steps:
judging whether the train enters the monitoring area range of the overhaul station according to the distance and the radius of the monitoring area range of the overhaul station; if yes, estimating the running duration time of the train in the monitoring area according to the running speed.
The beneficial effects of the technical scheme are as follows: and erecting radar equipment at a position which is separated from the maintenance station by a preset distance value, so that the radar equipment is used as a first monitoring checkpoint for the train to run close to the maintenance station. The radar equipment periodically scans outwards to emit radar signals, and when the radar signals reach the surface of the train and are reflected back, the radar equipment performs differential processing on the intensity or time of the outwards emitted radar signals and the received radar signals, namely, the distance between the train and the radar equipment and the running speed of the train are obtained, so that the running state of the train is quantitatively calibrated. In addition, the distance and the radius of the monitoring area range of the overhaul station are compared, if the distance is smaller than or equal to the radius of the monitoring area range, the fact that the train enters the monitoring area range of the overhaul station is determined, at the moment, the follow-up timely indication camera is convenient to dynamically shoot the train, and switching from rough monitoring of radar equipment to accurate monitoring of the camera is achieved. And then, according to the radius and the running speed of the monitoring area range, determining the running duration time of the train in the monitoring area range, so that the dynamic shooting duration time of the camera on the train can be controlled conveniently.
Preferably, the image shooting control and analysis module instructs a camera positioned at the maintenance station to shoot the train in a time period corresponding to the continuous running time to obtain a train running image; analyzing and processing the train running image to obtain running attitude information of the train and an actual distance value between the train and the overhaul station, wherein the method specifically comprises the following steps of:
a camera at the maintenance station is instructed to dynamically shoot the train in a time period corresponding to the running duration, and a running dynamic image of the train is obtained; carrying out framing treatment on the train running dynamic image to obtain a plurality of train running image frames;
extracting outline information of a train from each train running image frame, and obtaining running posture information of the train according to the outline information corresponding to the train running image frame; the driving gesture information comprises an inclination angle of a vehicle body relative to a plane where a rail is positioned in the driving process of the train;
identifying and obtaining indication information of a preset interval indication board on a rail from each train running image frame so as to obtain an actual distance value between a train and an overhaul station;
the train running adjustment module adjusts the running state of the train according to the running posture information and the actual distance value, and specifically comprises the following steps:
judging whether the train is in a running unstable state in the running process according to the running posture information; if the train is in a running unstable state and the actual distance value is greater than a preset distance threshold value, indicating the train to run at a constant speed at a preset speed; if the train is in a stable running state and the actual distance value is larger than a preset distance threshold value, indicating the train to enter an acceleration running mode at a preset acceleration; and if the actual distance value is smaller than or equal to the preset distance threshold value, indicating the train to enter a speed-reducing running mode.
The beneficial effects of the technical scheme are as follows: when the train enters the monitoring area of the maintenance station, a camera which is erected in advance at the maintenance station is indicated to dynamically shoot the train, and the shot train running dynamic image is divided into a plurality of train running image frames. And carrying out identification processing on the outline of the train and the indication information of the track preset indication sign on each train running image frame to obtain the running posture information of the train and the actual distance value between the train and the maintenance station, so as to be convenient for carrying out quantitative calibration on the running state of the train and the relative position relation between the train and the maintenance station.
Preferably, the train stopping control module sends a braking control instruction to a driving control platform of the train according to the actual distance value, so as to instruct the train to stop at a platform area corresponding to the maintenance station specifically comprises:
if the actual distance value is smaller than or equal to a preset distance threshold value, determining a driving distance value on a rail between the current train and a platform area to be stopped according to the actual distance value; and determining a deceleration acceleration value corresponding to the deceleration running mode according to the running distance value and the real-time running speed of the train, and sending a deceleration braking control instruction to a running control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station.
The beneficial effects of the technical scheme are as follows: by the method, the running distance value on the rail and the real-time running speed of the train between the current train and the platform area to be parked are taken as references, accurate deceleration braking control is performed on the train, the train is ensured to be aligned to the corresponding platform area to be parked at the maintenance station, and the parking reliability of the train is improved.
As can be seen from the foregoing embodiments, the method and system for detecting train running based on multi-feature fusion perform radar scanning detection on a train by using radar equipment to obtain running state information of the train, so as to determine whether the train enters a monitoring area range and estimate running duration of the train in the monitoring area range; shooting and analyzing train running images in the running duration time period to obtain running posture information of the train and an actual distance value between the train and a maintenance station, so as to adjust the running state of the train; according to the actual distance value, a braking control instruction is sent to a driving control platform of the train so as to instruct the train to stop at a platform area corresponding to the maintenance station, radar equipment and a camera are respectively utilized to carry out multi-feature monitoring on the train under the condition that the train is separated from the maintenance station by a larger distance and a smaller distance, the train is roughly monitored in a radar scanning mode when the distance is larger, and the train is accurately monitored in an image shooting mode when the distance is smaller, so that the proper braking control instruction can be sent to the train in time, and the train is ensured to be aligned to the platform area corresponding to the maintenance station, thereby improving the control accuracy and reliability of the train to stop at the maintenance station.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (8)

1. The train running detection method based on multi-feature fusion is characterized by comprising the following steps of:
step S1, radar equipment indicating a preset distance value from an overhaul station performs radar scanning detection on a train so as to obtain running state information of the train; judging whether the train enters a monitoring area range of the overhaul station according to the train running state information; estimating the running duration time of the train in the monitoring area according to the running state information of the train;
step S2, a camera at the maintenance station is instructed to shoot the train in a time period corresponding to the running duration, and a train running image is obtained; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station; according to the driving posture information and the actual distance value, the driving state of the train is adjusted;
and step S3, according to the actual distance value, a braking control instruction is sent to a driving control platform of the train, so that the train is instructed to stop at a platform area corresponding to the maintenance station.
2. The multi-feature fusion-based train running detection method as set forth in claim 1, wherein: in the step S1, radar equipment indicating a preset distance value from an overhaul station performs radar scanning detection on a train, so as to obtain running state information of the train; judging whether the train enters a monitoring area range of the overhaul station according to the train running state information; and estimating the running duration of the train in the monitoring area according to the running state information of the train specifically comprises the following steps:
the radar equipment which indicates a preset distance value from the overhaul station periodically scans and transmits radar signals outwards, so that radar scanning detection is carried out on trains nearby the radar equipment; according to the radar signals emitted by the radar equipment outwards and the radar signals reflected by the train, obtaining the distance between the train and the radar equipment and the running speed of the train;
judging whether the train enters the monitoring area range of the overhaul station according to the distance and the radius of the monitoring area range of the overhaul station; if yes, estimating the running duration time of the train in the monitoring area according to the running speed; if not, continuing to instruct the radar equipment to periodically scan outwards to transmit radar signals.
3. The multi-feature fusion-based train running detection method as set forth in claim 2, wherein: in the step S2, a camera located at the inspection station is instructed to shoot the train in a time period corresponding to the running duration, and a train running image is obtained; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station; according to the driving posture information and the actual distance value, the adjusting the driving state of the train specifically comprises:
a camera at the maintenance station is instructed to dynamically shoot the train in a time period corresponding to the running duration, and a running dynamic image of the train is obtained; carrying out framing treatment on the train running dynamic image to obtain a plurality of train running image frames;
extracting outline information of a train from each train running image frame, and obtaining running posture information of the train according to the outline information corresponding to the train running image frames; the driving gesture information comprises an inclination angle of a vehicle body relative to a plane where a rail is positioned in the driving process of the train; identifying and obtaining indication information of a preset interval indication board on a rail from each train running image frame so as to obtain an actual distance value between a train and an overhaul station;
judging whether the train is in a running unstable state in the running process according to the running posture information; if the train is in a running unstable state and the actual distance value is greater than a preset distance threshold value, indicating the train to run at a constant speed at a preset speed; if the train is in a stable running state and the actual distance value is larger than a preset distance threshold value, indicating the train to enter an acceleration running mode at a preset acceleration; and if the actual distance value is smaller than or equal to a preset distance threshold value, indicating the train to enter a speed-reducing running mode.
4. The multi-feature fusion-based train running detection method as set forth in claim 3, wherein: in the step S3, according to the actual distance value, a braking control instruction is sent to a driving control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station, which specifically includes: if the actual distance value is smaller than or equal to a preset distance threshold value, determining a driving distance value on a rail between the current train and a platform area to be stopped according to the actual distance value; and determining a deceleration acceleration value corresponding to the deceleration running mode according to the running distance value and the real-time running speed of the train, and sending a deceleration braking control instruction to a running control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station.
5. Train running detection system based on multi-feature fusion, which is characterized in that it comprises:
the radar scanning control module is used for indicating radar equipment with a preset distance value from the overhaul station to perform radar scanning detection on the train so as to obtain running state information of the train;
the train running analysis module is used for judging whether the train enters the monitoring area range of the overhaul station according to the train running state information; estimating the running duration time of the train in the monitoring area according to the running state information of the train;
the image shooting control and analysis module is used for indicating a camera positioned at the maintenance station to shoot the train in a time period corresponding to the continuous running time to obtain a train running image; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station;
the train running adjustment module is used for adjusting the running state of the train according to the running posture information and the actual distance value;
and the train stopping control module is used for sending a braking control instruction to a driving control platform of the train according to the actual distance value so as to indicate that the train is stopped at a platform area corresponding to the maintenance station.
6. The multi-feature fusion-based train travel detection system of claim 5, wherein: the radar scanning control module instructs radar equipment with a preset distance value from the overhaul station to perform radar scanning detection on the train, so as to obtain running state information of the train specifically comprises the following steps:
the radar equipment which indicates a preset distance value from the overhaul station periodically scans and transmits radar signals outwards, so that radar scanning detection is carried out on trains nearby the radar equipment; according to the radar signals emitted by the radar equipment outwards and the radar signals reflected by the train, obtaining the distance between the train and the radar equipment and the running speed of the train;
the train running analysis module judges whether the train enters a monitoring area range of the overhaul station according to the train running state information; and estimating the running duration of the train in the monitoring area according to the running state information of the train specifically comprises the following steps:
judging whether the train enters the monitoring area range of the overhaul station according to the distance and the radius of the monitoring area range of the overhaul station; if so, estimating the running duration time of the train in the monitoring area according to the running speed.
7. The multi-feature fusion-based train travel detection system of claim 6, wherein: the image shooting control and analysis module instructs a camera positioned at the maintenance station to shoot the train in a time period corresponding to the continuous running time to obtain a train running image; analyzing and processing the train running image to obtain running posture information of the train and an actual distance value between the train and the overhaul station, wherein the method specifically comprises the following steps of:
a camera at the maintenance station is instructed to dynamically shoot the train in a time period corresponding to the running duration, and a running dynamic image of the train is obtained; carrying out framing treatment on the train running dynamic image to obtain a plurality of train running image frames;
extracting outline information of a train from each train running image frame, and obtaining running posture information of the train according to the outline information corresponding to the train running image frames; the driving gesture information comprises an inclination angle of a vehicle body relative to a plane where a rail is positioned in the driving process of the train; identifying and obtaining indication information of a preset interval indication board on a rail from each train running image frame so as to obtain an actual distance value between a train and an overhaul station;
the train running adjustment module adjusts the running state of the train according to the running posture information and the actual distance value, and specifically comprises the following steps:
judging whether the train is in a running unstable state in the running process according to the running posture information; if the train is in a running unstable state and the actual distance value is greater than a preset distance threshold value, indicating the train to run at a constant speed at a preset speed; if the train is in a stable running state and the actual distance value is larger than a preset distance threshold value, indicating the train to enter an acceleration running mode at a preset acceleration; and if the actual distance value is smaller than or equal to a preset distance threshold value, indicating the train to enter a speed-reducing running mode.
8. The multi-feature fusion-based train travel detection system of claim 7, wherein: the train stopping control module sends a braking control instruction to a driving control platform of the train according to the actual distance value, so as to indicate that the train is stopped at a platform area corresponding to the maintenance station, and the method specifically comprises the following steps: if the actual distance value is smaller than or equal to a preset distance threshold value, determining a driving distance value on a rail between the current train and a platform area to be stopped according to the actual distance value; and determining a deceleration acceleration value corresponding to the deceleration running mode according to the running distance value and the real-time running speed of the train, and sending a deceleration braking control instruction to a running control platform of the train, so as to instruct the train to stop at a platform area corresponding to the maintenance station.
CN202211576581.4A 2022-12-09 2022-12-09 Train running detection method and system based on multi-feature fusion Pending CN116811962A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211576581.4A CN116811962A (en) 2022-12-09 2022-12-09 Train running detection method and system based on multi-feature fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211576581.4A CN116811962A (en) 2022-12-09 2022-12-09 Train running detection method and system based on multi-feature fusion

Publications (1)

Publication Number Publication Date
CN116811962A true CN116811962A (en) 2023-09-29

Family

ID=88113376

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211576581.4A Pending CN116811962A (en) 2022-12-09 2022-12-09 Train running detection method and system based on multi-feature fusion

Country Status (1)

Country Link
CN (1) CN116811962A (en)

Similar Documents

Publication Publication Date Title
CN110264783A (en) Vehicle collision avoidance early warning system and method based on bus or train route collaboration
US20200312052A1 (en) Method for acquiring data captured by a capture module embedded in a mobile device following a predetermined trajectory, corresponding computer program and device
CN108777065A (en) A kind of vehicle bend meeting detection prior-warning device and its method
CN110471085B (en) Track detecting system
CN112132896B (en) Method and system for detecting states of trackside equipment
CN106125731B (en) A kind of automatic driving vehicle kinetic control system and method based on the identification of front vehicle driving intention
US10395104B2 (en) Vehicle imaging system, vehicle imaging method and device, program, and recording medium
WO2020020298A1 (en) Unmanned vehicle control method and apparatus
CN110968086B (en) Vehicle arrival control method and system
CN109910955A (en) Rail tunnel obstacle detection system and method based on transponder information transmission
CN109061669B (en) Limit detection system and method thereof
CN109767651A (en) A kind of typical curved areas seamless communication method under V2X environment
CN109001743A (en) Tramcar anti-collision system
CN110097783A (en) Vehicle early warning method and system
CN111898460A (en) Locomotive auxiliary trailer system, method, device, equipment and storage medium
CN113050654A (en) Obstacle detection method, vehicle-mounted obstacle avoidance system and method for inspection robot
GB2593087A (en) Train identification system and method thereof, train safety inspection system and method thereof
CN116118719B (en) Automatic driving parking speed measuring system based on obstacle judgment vehicle speed
CN111717243A (en) Rail transit monitoring system and method
CN208847836U (en) Tramcar anti-collision system
KR101403936B1 (en) Camera system for vehicles
CN116811962A (en) Train running detection method and system based on multi-feature fusion
JP2007240387A (en) Image recognition device and method
KR102058179B1 (en) Automatic traffic enforcement system using laser signal
CN114464012B (en) Vehicle and pedestrian collision early warning method and system based on Internet of vehicles

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