CN110264651A - Railway platform pedestrian gets over line monitoring method, device, terminal and storage medium - Google Patents
Railway platform pedestrian gets over line monitoring method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN110264651A CN110264651A CN201910377519.4A CN201910377519A CN110264651A CN 110264651 A CN110264651 A CN 110264651A CN 201910377519 A CN201910377519 A CN 201910377519A CN 110264651 A CN110264651 A CN 110264651A
- Authority
- CN
- China
- Prior art keywords
- train
- image
- pedestrian
- target
- target image
- 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
Classifications
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
- G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
Abstract
A kind of railway platform pedestrian gets over line monitoring method, comprising: obtains the first object image in the default first object region on waiting station platform;Judge that whether there is or not pedestrians in the first object image;When determining has pedestrian in the first object image, the second target image in default second target area on train rail is obtained;Judge that whether there is or not trains in second target image;When determining has train in second target image and the train is not currently in dead ship condition, the result that output has pedestrian that cross-lane occurs.The present invention also provides a kind of railway platform pedestrians to get over line monitoring device, terminal and storage medium.The present invention is with the computer vision and the sense of hearing of artificial intelligence deep learning; the artificial 7*24 hours strict intelligence warning free of discontinuities on duty of substitution; protect the routine safety of passenger safety and train operation, the initiative blind zone problem for solving safety management " last rice " by video monitoring and image processing techniques.
Description
Technical field
The present invention relates to technical field of video monitoring, and in particular to a kind of railway platform pedestrian get over line monitoring method, device,
Terminal and storage medium.
Background technique
In modern carrier, especially since high-speed rail operation, the railway system is high, quick, easypro with its safety coefficient
The advantages that suitable, increasingly becomes the first choice of people's trip.At the train station or on subway station platform, 1 meter of edge of table leaving from station or so of ground
Side indicates the safety line of a yellow, and pedestrian must stand and wait other than safety line.Due between platform and track without similar
The device of protective door often occurs the behavior that pedestrian gets over line, causes people during crowded or child plays
The phenomenon that body injures happens occasionally, or even causes Train delay or traffic accident.
Existing platform is waited system, gets over line alarm system almost without installation.Pedestrian gets over line monitoring and uses pure people at present
Work mode walks up and down by artificial scene and pedestrian is warned not get over line, and artificial detection need to take a substantial amount of time and manpower;
In addition, simple rely on manually can not also ensure that people will not cross safe-guard line in platform walking process completely.
Therefore, it is necessary to propose it is a kind of can find that pedestrian gets over the technical solution of the behavior of line in time, avoid it is some need not
The generation of the personal injury or safety accident wanted.
Summary of the invention
In view of the foregoing, it is necessary to propose that a kind of railway platform pedestrian gets over line monitoring method, device, terminal and storage and is situated between
Matter, can be with the computer vision and the sense of hearing of artificial intelligence deep learning, and artificial 7*24 hours on duty of substitution free of discontinuities strict
Intelligence warning, protects the routine safety of passenger safety and train operation, and initiative relies on video monitoring and image procossing skill
Art solves the blind zone problem of safety management " last rice ".
The first aspect of the present invention provides a kind of railway platform pedestrian and gets over line monitoring method, which comprises
Obtain the first object image in the default first object region on waiting station platform;
Judge that whether there is or not pedestrians in the first object image;
When determining has pedestrian in the first object image, obtain in default second target area on train rail
Second target image;
Judge that whether there is or not trains in second target image;
When determining has train in second target image, judge the train currently whether in dead ship condition;
When determining that the train is not currently in the dead ship condition, the result that output has pedestrian that cross-lane occurs.
Preferably, whether there is or not trains in judgement second target image includes:
Obtain the background image before the train arrives;
Second target image and the background image are subjected to difference processing and obtain difference image;
Judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
When the characteristic value for judging the difference image is more than or equal to the default characteristic threshold value, described second is determined
There is train in target image;
When the characteristic value for judging the difference image is less than the default characteristic threshold value, second target image is determined
Middle no train.
Preferably, described to judge whether the train currently in dead ship condition includes:
The contour area of the train in multiple described second target images is detected using YOLO algorithm of target detection;
Judge whether position of the contour area of the train in every second target image is fixed;
When position of the contour area of the train in every second target image is fixed, the train is determined
It is currently at the dead ship condition;
When position of the contour area of the train in every second target image is not fixed, the column are determined
Vehicle is not currently in the dead ship condition.
Preferably, when determining that the train is not currently in the dead ship condition, the method also includes:
Judge whether displacement of the contour area of the train in multiple described second target images is reducing;
When judge displacement of the contour area of the train in multiple described second target images reduce when, determine institute
It states train and is currently at the state of entering the station;
When judge displacement of the contour area of the train in multiple described second target images increase when, determine institute
It states train and is currently at outbound state.
Preferably, described when in second target image without train when determining there is pedestrian in the first object image
Method further include:
The result that output has pedestrian that cross-lane occurs.
Preferably, after the result that the output has pedestrian that cross-lane occurs, the method also includes:
It sends a warning message to the control room at station;
Meanwhile the acoustic-optic alarm that triggering is arranged on the waiting station platform is alarmed.
Preferably, when determining there is pedestrian in the first object image, there are train, the column in second target image
When vehicle is currently at dead ship condition, the method also includes:
Export the result that cross-lane occurs without pedestrian.
The second aspect of the present invention provides a kind of railway platform pedestrian and gets over line monitoring device, and described device includes:
First obtains module, for obtaining the first object image in the default first object region on waiting station platform;
First judgment module, for judging that whether there is or not pedestrians in the first object image;
Second obtains module, for obtaining when the first judgment module, which determines, has pedestrian in the first object image
Take the second target image in default second target area on train rail;
Second judgment module, for judging that whether there is or not trains in second target image;
Third judgment module, for sentencing when second judgment module, which determines, has train in second target image
The train break currently whether in dead ship condition;
Output module, it is defeated for determining that the train is not currently in the dead ship condition when the third judgment module
There is pedestrian that the result of cross-lane occurs out.
The third aspect of the present invention provides a kind of terminal, and the terminal includes processor, and the processor is deposited for executing
Realize that the railway platform pedestrian gets over line monitoring method when the computer program stored in reservoir.
The fourth aspect of the present invention provides a kind of computer readable storage medium, deposits on the computer readable storage medium
Computer program is contained, the computer program realizes that the railway platform pedestrian gets over line monitoring method when being executed by processor.
In conclusion railway platform pedestrian of the present invention gets over line monitoring method, device, terminal and storage medium, first
The first object image in the first object region in yellow safety line is obtained, and has pedestrian in judging first object image
When, the second target image in the second target area on train rail is obtained, when having train in judging the second target image,
The operating status of train is further judged, if train is in dead ship condition, it is believed that more line belongs to normal behaviour, if train is in fortune
Row state, it is believed that more line belongs to irregularities, and when in judge the second target image without train, it is believed that get over line and also belong to not
Normal behaviour.With the computer vision and the sense of hearing of artificial intelligence deep learning, artificial 7*24 hours on duty of substitution free of discontinuities tight
Intelligence warning, protect the routine safety of passenger safety and train operation.It is initiative by video monitoring and image procossing
Technology solves the blind zone problem of safety management " last rice ".
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the flow chart that the railway platform pedestrian that the embodiment of the present invention one provides gets over line monitoring method.
Fig. 2 is the structure chart that railway platform pedestrian provided by Embodiment 2 of the present invention gets over line monitoring device.
Fig. 3 is the structural schematic diagram for the terminal that the embodiment of the present invention three provides.
The present invention that the following detailed description will be further explained with reference to the above drawings.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying example, the present invention will be described in detail.It should be noted that in the absence of conflict, the embodiment of the present invention and embodiment
In feature can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment is only
It is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Embodiment one
Fig. 1 is the flow chart that the railway platform pedestrian that the embodiment of the present invention one provides gets over line monitoring method.
In the present embodiment, the railway platform pedestrian, which gets over line monitoring method, can be applied in terminal, for need into
Ranks station console pedestrian gets over the terminal of line monitoring, can directly integrate railway platform provided by method of the invention at the terminal
Pedestrian gets over the function of line monitoring, or transports in the form of Software Development Kit (Software Development Kit, SKD)
Row is in the terminal.
As shown in Figure 1, the railway platform pedestrian gets over this special scenes that line monitoring method is applied to railway platform, institute
State railway platform pedestrian and get over line monitoring method and specifically include following steps, according to different requirements, in the flow chart step it is suitable
Sequence can change, certain to can be omitted.
S11: the first object image in the default first object region on waiting station platform is obtained.
On waiting station platform in the present embodiment, 1 meter of edge of table leaving from station or so of place indicates a yellow safety line, to
Mark forbids pedestrian to cross yellow safety line.
In the present embodiment, default first mesh on the first high-definition digital image capture device acquisition waiting station platform can star
The image in region is marked, the image in the default first object region of acquisition is referred to as first object image.On waiting station platform
First object region be pre-set first monitoring region, the first monitoring region on waiting station platform is yellow safety line
To the position between platform edge.
It, can be every predetermined period, for example, obtaining default first mesh on waiting station platform every 5 minutes in the present embodiment
Mark the image in region.
In the present embodiment, the first high-definition digital image capture device may include more high definition cameras, the high definition
Camera is mounted at least one support frame of the setting of train travelling route described in two lateral edges of train waiting station platform, is obtained in real time
It presets the image or video in first object region and is sent to Streaming Media storage device.Certainly in other embodiments, described
High definition camera can also have other installation sites, as long as clear image in default first object region can clearly be obtained i.e.
It can.
First high-definition digital image capture device can be by technologies such as dedicated video optical transmitter and receiver, cable networks to each vehicle
The high-definition image that the indoor video analytics server transmission in control room of standing acquires, enables Train Management department to lead at any time
It crosses indoor video analytics server and grasps the case where pedestrian gets over line.
S12: judge that whether there is or not pedestrians in the first object image.
In the present embodiment, one in default first object region is being acquired by the first high-definition digital image capture device
After image, needs to judge that whether there is or not pedestrians in the first object image, make whether there is or not the results that pedestrian gets over line convenient for subsequent.
Preferably, whether there is or not pedestrians in the judgement first object image includes:
Calling default detection algorithm to detect in the first object image, whether there is or not pedestrians, and the default detection includes: YOLO
Algorithm of target detection or Face datection algorithm.
YOLO (You Only Look Once:Better, Faster, Stronger) algorithm of target detection is quick more mesh
Detection algorithm is marked, can detect multiple targets simultaneously, and have selected the contour area of each target with the form frame of rectangle frame.
Face datection algorithm can detect multiple faces simultaneously, and the profile region of each face is had selected with the form frame of rectangle frame
Domain.YOLO algorithm of target detection and Face datection algorithm are the prior art, and the present invention is not described in detail herein.
When judging has pedestrian in the first object image, then S13 is executed;Otherwise, when judging the first object figure
When as in without pedestrian, then S11 can be continued to execute.
S13: the second target image in default second target area on train rail is obtained.
In the present embodiment, default second mesh on train rail can be obtained by the second high-definition digital image capture device
The image in region is marked, the image in default second target area of acquisition is referred to as the second target image.On train rail
The second target area be pre-set second monitoring region, the second monitoring region on train rail corresponds to waiting station platform
Position.It when having pedestrian within yellow safety line, needs to judge whether pedestrian gets on the bus in queuing, that is, needs to judge the second target
Whether there is or not the states that train and train are presently in region.
In the present embodiment, it can start the second high-definition digital Image Acquisition according to the train shift report of train scheduling room and set
The second target image in standby default second target area obtained on train rail.In preset time period before train arrival
Start the second high-definition digital image capture device and obtains the second target image.The second mesh can also be obtained every preset period of time
Logo image.
High speed continuous shooting digital photo technologies can be used, by the second high-definition digital image capture device quickly to described pre-
If carrying out continuous shooting in the second target area to obtain multiple high-definition digital images.Especially during train driving, need
High speed continuous shooting digital photo technologies are used, obtain the top of multiple trains and the image on head, or pass through the second high definition number
Word image capture device acquires video flowing, multiple images is obtained by extracting the frame in video flowing, will pass through multiple continuitys
Image synthesis identify the operating status of train.
In the present embodiment, the second high-definition digital image capture device may include more high definition cameras, the high definition
Camera is mounted at least one support frame of the setting of train travelling route described in two lateral edges of train waiting station platform, is obtained in real time
It presets the image or video in the second target area and is sent to Streaming Media storage device.Certainly in other embodiments, described
High definition camera can also have other installation sites, as long as the first high-definition digital image capture device and second high definition
The respective independent operating of digital image acquisition apparatus, between each other without influence, and captured region is different.
Second high-definition digital image capture device can be by technologies such as dedicated video optical transmitter and receiver, cable networks to each vehicle
The high-definition image that the indoor video analytics server transmission in control room of standing acquires, enables Train Management department to lead at any time
Cross the operating condition that indoor video analytics server grasps train.
Preferably, after the second target image in default second target area on the acquisition train rail, institute
State method further include:
Every second target image is pre-processed.
In the present embodiment, the pretreatment may include: to carry out illumination or contrast to every second target image
Normalized;Noise reduction process is carried out to the second target image of every after normalized using bilateral filtering algorithm.
Due to monitoring be round-the-clock (different periods, different light intensity, Different climate feature) train operation state,
After pre-processing to train image, the normalization of the contrast of image under different periods, different illumination conditions can be solved, from
And the feature of identification division required in image is optimized and is highlighted, remaining feature for not needing identification division is weakened
Processing, to improve, whether there is or not the detection efficiency of train and subsequent use YOLO algorithm of target detection in the second target image of detection
Detect the contour area of the train in the second target image.
The bilateral filtering algorithm can effectively remove noise, for example, being produced by the second high-definition digital image capture device
Raw salt-pepper noise, meanwhile, also there is good edge details holding capacity.Treatment process about bilateral filtering algorithm is existing
There is technology, in this not go into detail by the present invention.
S14: judge that whether there is or not trains in second target image.
In the present embodiment, after obtaining the target image in default second target area on train rail, need to adopt
Judge whether there is train in second target image with frame difference method, convenient for subsequent according to whether there is or not trains to determine in the second target image
Determine whether the pedestrian within yellow safety line belongs to cross-lane.
Preferably, whether there is or not trains in judgement second target image includes:
141) background image before the train arrives is obtained;
In the present embodiment, the second high-definition digital image capture device is first passed through before train arrival and acquires a figure
Picture, as background image;Or from the image before a frame train arrives is intercepted in video, as background image.
It should be understood that only include background information in the background image, for example, rail information, sky information etc., and
Foreground information not comprising any train and compartment.
142) second target image and the background image are subjected to difference processing and obtain difference image;
In the present embodiment, since background image is the image before train arrives, the image after train arrives is in Background
This prospect of train is increased as on the basis of, and the camera site of the second high-definition digital image capture device is fixed, i.e. background
The size of image and second target image is identical, thus can directly by the second target image each pixel with
Corresponding pixel in the background image carries out difference processing.That is, the region for belonging to background in the second target image is gone
Fall, only remains the image of this foreground area of train.
143) judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
In the present embodiment, the characteristic value of difference image can be calculated, for example, variance, mean value or comentropy, histogram
Deng.Then the size relation between judging characteristic value and default characteristic threshold value.
It should be understood that the variance of difference image should be calculated if pre-set characteristic threshold value is variance yields;Together
Reason should calculate the histogram of difference image if pre-set characteristic threshold value is histogram.
144) when the characteristic value for judging the difference image is more than or equal to the default characteristic threshold value, described in determination
There is train in second target image;When the characteristic value for judging the difference image is less than the default characteristic threshold value, institute is determined
It states in the second target image without train.
It is easily understood that will have train if presetting in the second target image in the second target area has train
It certainly include this prospect of train in second target image and the difference image after background image progress difference processing, obtained, then
The characteristic value for calculating difference image is greater than pre-set characteristic threshold value.If the second target image in default second target area
Middle no train, then after the second target image of no train and background image being carried out difference processing, in obtained difference image not
Comprising this prospect of train, most pixel value is 0, then the characteristic value for calculating difference image is necessarily smaller than pre-set spy
Levy threshold value.Therefore, it is possible to quickly judge whether there is train in the second target image using frame difference method.
When determining there is train in second target image, S15 is executed;Otherwise, when determining in second target image
When without train, S17 is executed.
S15: judge the train currently whether in dead ship condition.
Even if determining in the first goal-selling region there is pedestrian, that is, there is pedestrian to cross yellow safety line, but still need
The state that is presently in conjunction with the train on train rail judges whether pedestrian has cross-lane.
In the present embodiment, the operating status of train includes: the state of entering the station, dead ship condition and outbound state.The shape that enters the station
State is train slowly close to the state of waiting station platform, and pedestrian cannot cross yellow safety line at this time.The dead ship condition
For the state of suspension of service, pedestrian can cross yellow safety line at this time.The outbound state is that train is quick
State far from waiting station platform, pedestrian cannot also cross yellow safety line at this time.
Preferably, described to judge whether the train currently in dead ship condition includes:
151) profile region of the train in multiple described second target images is detected using YOLO algorithm of target detection
Domain;
152) judge whether position of the contour area of the train in every second target image is fixed;
153) when the position when the contour area of the train in every second target image is fixed, described in determination
Train is currently at the dead ship condition;When position of the contour area in every second target image of the train not
When fixed, determine that the train is not currently in the dead ship condition.
Position described in the present embodiment refers to relative position, that is, the contour area on every second target image is opposite
For this image.If train is to be in dead ship condition, the contour area of train is in every second target image
In relative position it is fixed, be consistent;If train is to be in motion state, the contour area of train is every
The relative position opened in the second target image will change.Therefore, it is possible to by judging the contour area of train at multiple
Whether the current operating conditions whether position in the second target image is fixed to judge train are dead ship condition, simply, quickly.
Further, when determining that the train is not currently in the dead ship condition, the method also includes:
1531) judge whether displacement of the contour area of the train in multiple described second target images is reducing;
1532) when judge displacement of the contour area of the train in multiple described second target images reduce when,
Determine that the train is currently at the state of entering the station;When judging the contour area of the train in multiple described second target images
Displacement increase when, determine that the train is currently at outbound state.
The variation occurred by the displacement of multiple the second target images, may further determine that train is proximate to waiting station platform
Or far from waiting station platform.
In other embodiments, when can also be by the headstock that recognizes train, it be determined as the state of entering the station;Recognize train
The tailstock when, be determined as outbound state.
It further, can be with when the current state for determining train is outbound state, and when in yellow safety line there are also pedestrian
By manually determining whether the pedestrian for crossing yellow safety line has not enough time to get on the bus, manage more humanized.
When judging that the train is currently at dead ship condition, S16 is executed;When judging that the train is not currently in parking
When state, S17 is executed.
S16: the result that cross-lane occurs without pedestrian is exported.
In the present embodiment, there is pedestrian in determining first object image, have train in the second target image, and train is current
When in dead ship condition, that is, determine within the yellow safety line on waiting station platform there is pedestrian, though there is train place on train rail
In the scene that state out of service, corresponding train waiting pedestrian are got on the bus, such situation thinks that pedestrian crosses yellow safety line category
In normal behaviour, the result that cross-lane occurs without pedestrian is exported.
S17: the result that output has pedestrian that cross-lane occurs.
In the present embodiment, there is pedestrian in determining first object image, when in the second target image without train, that is, determine
There is pedestrian within yellow safety line on waiting station platform, but there is no train on train rail, such situation thinks that pedestrian crosses Huang
Color safety line belongs to irregularities, then the result that output has pedestrian that cross-lane occurs.Alternatively, determining first object image
In have pedestrian, have train in the second target image, but when train is not currently in dead ship condition, that is, determine on waiting station platform
There is pedestrian within yellow safety line, also there is train on train rail, train is currently entering the station or outbound, and such situation thinks
Pedestrian crosses yellow safety line and belongs to irregularities, then the result that output has pedestrian that cross-lane occurs.
Further, after the result that the output has pedestrian that cross-lane occurs, the method also includes:
It sends a warning message to the control room at station;
Meanwhile the acoustic-optic alarm that triggering is arranged on the waiting station platform is alarmed.
In the present embodiment, when discovery has pedestrian that cross-lane occurs, send a warning message to the control room at station same
When, it triggers the acoustic-optic alarm being arranged on the waiting station platform and alarms.It sends a warning message to control room, is convenient for vehicle
The staff that stands prevents the pedestrian for having cross-lane in time, in addition, the alarm of triggering warning device is to further function as warning pedestrian
Cross the effect of yellow safety line.
In conclusion railway platform pedestrian of the present invention gets over line monitoring method, the in yellow safety line is first obtained
First object image in one target area, and when having pedestrian in judging first object image obtains the on train rail
The second target image in two target areas when having train in judging the second target image, further judges the operation of train
State, if train is in dead ship condition, it is believed that more line belongs to normal behaviour, if train is in operating status, it is believed that more line belongs to
Irregularities, and when in judging the second target image without train, it is believed that more line also belongs to irregularities.With artificial intelligence
The computer vision and the sense of hearing of deep learning, the artificial 7*24 hours strict intelligence warning free of discontinuities on duty of substitution, protect passenger
Safety and the routine safety of train operation.The initiative technology by video monitoring and image procossing solves safety management
The blind zone problem of " last rice ".Effective ancillary technique means are provided for the safety detection of train and pedestrian, have been broken completely
The mechanism of cross-lane is passively judged whether there is by pure artificial vision, mitigates the workload of field personnel significantly, is improved
The safety of train operation realizes effective control to transportation safety production, and provides effectively for train scheduling room
The foundation of HD image.
Embodiment two
Fig. 2 is the structure chart that railway platform pedestrian provided by Embodiment 2 of the present invention gets over line monitoring device.
In some embodiments, it may include multiple by program code segments that the railway platform pedestrian, which gets over line monitoring device 20,
Composed functional module.The program code that the railway platform pedestrian gets over each program segment in line monitoring device 20 can be deposited
It is stored in the memory of terminal, and as performed by least one described processor, with execution (being detailed in Fig. 1 description) to there are trains
Platform pedestrian gets over line and detects.
In the present embodiment, the railway platform pedestrian gets over line monitoring device 20, operates in this specific field of railway platform
Scape, the function according to performed by it, s can be divided into multiple functional modules.The functional module may include: the first acquisition
Module 201, first judgment module 202, second obtain module 203, preprocessing module 204, the second judgment module 205, third and sentence
Disconnected module 206, output module 207 and sending module 208.The so-called module of the present invention refers to that one kind can be handled by least one
Device is performed and can complete the series of computation machine program segment of fixed function, and storage is in memory.In the present embodiment
In, the function about each module will be described in detail in subsequent embodiment.
First obtains module 201, for obtaining the first object image in the default first object region on waiting station platform.
On waiting station platform in the present embodiment, 1 meter of edge of table leaving from station or so of place indicates a yellow safety line, to
Mark forbids pedestrian to cross yellow safety line.
In the present embodiment, default first mesh on the first high-definition digital image capture device acquisition waiting station platform can star
The image in region is marked, the image in the default first object region of acquisition is referred to as first object image.On waiting station platform
First object region be pre-set first monitoring region, the first monitoring region on waiting station platform is yellow safety line
To the position between platform edge.
It, can be every predetermined period, for example, obtaining default first mesh on waiting station platform every 5 minutes in the present embodiment
Mark the image in region.
In the present embodiment, the first high-definition digital image capture device may include more high definition cameras, the high definition
Camera is mounted at least one support frame of the setting of train travelling route described in two lateral edges of train waiting station platform, is obtained in real time
It presets the image or video in first object region and is sent to Streaming Media storage device.Certainly in other embodiments, described
High definition camera can also have other installation sites, as long as clear image in default first object region can clearly be obtained i.e.
It can.
First high-definition digital image capture device can be by technologies such as dedicated video optical transmitter and receiver, cable networks to each vehicle
The high-definition image that the indoor video analytics server transmission in control room of standing acquires, enables Train Management department to lead at any time
It crosses indoor video analytics server and grasps the case where pedestrian gets over line.
First judgment module 202, for judging that whether there is or not pedestrians in the first object image.
In the present embodiment, one in default first object region is being acquired by the first high-definition digital image capture device
After image, needs to judge that whether there is or not pedestrians in the first object image, make whether there is or not the results that pedestrian gets over line convenient for subsequent.
Preferably, the first judgment module 202 judges in the first object image that whether there is or not pedestrians and includes:
Calling default detection algorithm to detect in the first object image, whether there is or not pedestrians, and the default detection includes: YOLO
Algorithm of target detection or Face datection algorithm.
YOLO (You Only Look Once:Better, Faster, Stronger) algorithm of target detection is quick more mesh
Detection algorithm is marked, can detect multiple targets simultaneously, and have selected the contour area of each target with the form frame of rectangle frame.
Face datection algorithm can detect multiple faces simultaneously, and the profile region of each face is had selected with the form frame of rectangle frame
Domain.YOLO algorithm of target detection and Face datection algorithm are the prior art, and the present invention is not described in detail herein.
Described first obtains module 201, is also used to determine in the first object image when the first judgment module 202
When without pedestrian, continue to obtain the first object image in the default first object region on waiting station platform.
Second obtains module 203, for when the first judgment module 202, which determines, has pedestrian in the first object,
Obtain the second target image in default second target area on train rail.
In the present embodiment, default second mesh on train rail can be obtained by the second high-definition digital image capture device
The image in region is marked, the image in default second target area of acquisition is referred to as the second target image.On train rail
The second target area be pre-set second monitoring region, the second monitoring region on train rail corresponds to waiting station platform
Position.It when having pedestrian within yellow safety line, needs to judge whether pedestrian gets on the bus in queuing, that is, needs to judge the second target
Whether there is or not the states that train and train are presently in region.
In the present embodiment, it can start the second high-definition digital Image Acquisition according to the train shift report of train scheduling room and set
The second target image in standby default second target area obtained on train rail.In preset time period before train arrival
Start the second high-definition digital image capture device and obtains the second target image.The second mesh can also be obtained every preset period of time
Logo image.
High speed continuous shooting digital photo technologies can be used, by the second high-definition digital image capture device quickly to described pre-
If carrying out continuous shooting in the second target area to obtain multiple high-definition digital images.Especially during train driving, need
High speed continuous shooting digital photo technologies are used, obtain the top of multiple trains and the image on head, or pass through the second high definition number
Word image capture device acquires video flowing, multiple images is obtained by extracting the frame in video flowing, will pass through multiple continuitys
Image synthesis identify the operating status of train.
In the present embodiment, the second high-definition digital image capture device may include more high definition cameras, the high definition
Camera is mounted at least one support frame of the setting of train travelling route described in two lateral edges of train waiting station platform, is obtained in real time
It presets the image or video in the second target area and is sent to Streaming Media storage device.Certainly in other embodiments, described
High definition camera can also have other installation sites, as long as the first high-definition digital image capture device and second high definition
The respective independent operating of digital image acquisition apparatus, between each other without influence, and captured region is different.
Second high-definition digital image capture device can be by technologies such as dedicated video optical transmitter and receiver, cable networks to each vehicle
The high-definition image that the indoor video analytics server transmission in control room of standing acquires, enables Train Management department to lead at any time
Cross the operating condition that indoor video analytics server grasps train.
Preferably, second preset in the second target area on the acquisition train rail of module 203 is obtained described second
After target image, the railway platform pedestrian gets over line monitoring device further include:
Preprocessing module 204, for being pre-processed to every second target image.
In the present embodiment, the pretreatment may include: to carry out illumination or contrast to every second target image
Normalized;Noise reduction process is carried out to the second target image of every after normalized using bilateral filtering algorithm.
Due to monitoring be round-the-clock (different periods, different light intensity, Different climate feature) train operation state,
After pre-processing to train image, the normalization of the contrast of image under different periods, different illumination conditions can be solved, from
And the feature of identification division required in image is optimized and is highlighted, remaining feature for not needing identification division is weakened
Processing, to improve, whether there is or not the detection efficiency of train and subsequent use YOLO algorithm of target detection in the second target image of detection
Detect the contour area of the train in the second target image.
The bilateral filtering algorithm can effectively remove noise, for example, being produced by the second high-definition digital image capture device
Raw salt-pepper noise, meanwhile, also there is good edge details holding capacity.Treatment process about bilateral filtering algorithm is existing
There is technology, in this not go into detail by the present invention.
Second judgment module 205, for judging that whether there is or not trains in second target image.
In the present embodiment, after obtaining the target image in default second target area on train rail, need to adopt
Judge whether there is train in second target image with frame difference method, convenient for subsequent according to whether there is or not trains to determine in the second target image
Determine whether the pedestrian within yellow safety line belongs to cross-lane.
Preferably, second judgment module 205 judges in second target image that whether there is or not trains and includes:
141) background image before the train arrives is obtained;
In the present embodiment, the second high-definition digital image capture device is first passed through before train arrival and acquires a figure
Picture, as background image;Or from the image before a frame train arrives is intercepted in video, as background image.
It should be understood that only include background information in the background image, for example, rail information, sky information etc., and
Foreground information not comprising any train and compartment.
142) second target image and the background image are subjected to difference processing and obtain difference image;
In the present embodiment, since background image is the image before train arrives, the image after train arrives is in Background
This prospect of train is increased as on the basis of, and the camera site of the second high-definition digital image capture device is fixed, i.e. background
The size of image and second target image is identical, thus can directly by the second target image each pixel with
Corresponding pixel in the background image carries out difference processing.That is, the region for belonging to background in the second target image is gone
Fall, only remains the image of this foreground area of train.
143) judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
In the present embodiment, the characteristic value of difference image can be calculated, for example, variance, mean value or comentropy, histogram
Deng.Then the size relation between judging characteristic value and default characteristic threshold value.
It should be understood that the variance of difference image should be calculated if pre-set characteristic threshold value is variance yields;Together
Reason should calculate the histogram of difference image if pre-set characteristic threshold value is histogram.
144) when the characteristic value for judging the difference image is more than or equal to the default characteristic threshold value, described in determination
There is train in second target image;When the characteristic value for judging the difference image is less than the default characteristic threshold value, institute is determined
It states in the second target image without train.
It is easily understood that will have train if presetting in the second target image in the second target area has train
It certainly include this prospect of train in second target image and the difference image after background image progress difference processing, obtained, then
The characteristic value for calculating difference image is greater than pre-set characteristic threshold value.If the second target image in default second target area
Middle no train, then after the second target image of no train and background image being carried out difference processing, in obtained difference image not
Comprising this prospect of train, most pixel value is 0, then the characteristic value for calculating difference image is necessarily smaller than pre-set spy
Levy threshold value.Therefore, it is possible to quickly judge whether there is train in the second target image using frame difference method.
Third judgment module 206, for determining in second target image there is train when second judgment module 205
When, judge the train currently whether in dead ship condition.
Even if determining in the first goal-selling region there is pedestrian, that is, there is pedestrian to cross yellow safety line, but still need
The state that is presently in conjunction with the train on train rail judges whether pedestrian has cross-lane.
In the present embodiment, the operating status of train includes: the state of entering the station, dead ship condition and outbound state.The shape that enters the station
State is train slowly close to the state of waiting station platform, and pedestrian cannot cross yellow safety line at this time.The dead ship condition
For the state of suspension of service, pedestrian can cross yellow safety line at this time.The outbound state is that train is quick
State far from waiting station platform, pedestrian cannot also cross yellow safety line at this time.
Preferably, the third judgment module 206 judges whether the train currently in dead ship condition includes:
151) profile region of the train in multiple described second target images is detected using YOLO algorithm of target detection
Domain;
152) judge whether position of the contour area of the train in every second target image is fixed;
153) when the position when the contour area of the train in every second target image is fixed, described in determination
Train is currently at the dead ship condition;When position of the contour area in every second target image of the train not
When fixed, determine that the train is not currently in the dead ship condition.
Position described in the present embodiment refers to relative position, that is, the contour area on every second target image is opposite
For this image.If train is to be in dead ship condition, the contour area of train is in every second target image
In relative position it is fixed, be consistent;If train is to be in motion state, the contour area of train is every
The relative position opened in the second target image will change.Therefore, it is possible to by judging the contour area of train at multiple
Whether the current operating conditions whether position in the second target image is fixed to judge train are dead ship condition, simply, quickly.
Further, third judgment module 206 is also used to:
1531) judge whether displacement of the contour area of the train in multiple described second target images is reducing;
1532) when judge displacement of the contour area of the train in multiple described second target images reduce when,
Determine that the train is currently at the state of entering the station;When judging the contour area of the train in multiple described second target images
Displacement increase when, determine that the train is currently at outbound state.
The variation occurred by the displacement of multiple the second target images, may further determine that train is proximate to waiting station platform
Or far from waiting station platform.In other embodiments, when can also be by the headstock that recognizes train, it be determined as the state of entering the station;
When recognizing the tailstock of train, it is determined as outbound state.
It further, can be with when the current state for determining train is outbound state, and when in yellow safety line there are also pedestrian
By manually determining whether the pedestrian for crossing yellow safety line has not enough time to get on the bus, manage more humanized.
The output module 207, for determining in first object image there is pedestrian in the first judgment module 202, institute
When stating in determining second target image of the second judgment module 205 without train, output has the result of pedestrian's generation cross-lane.
In the present embodiment, determine within the yellow safety line on waiting station platform there is pedestrian, but there is no train on train rail,
Such situation thinks that pedestrian crosses yellow safety line and belongs to irregularities, then the result that output has pedestrian that cross-lane occurs.
The output module 207 is also used to have pedestrian in the determining first object image of the first judgment module 202,
Second judgment module 205, which determines, train in the second target image, but third judgment module 206 determines that train is not located currently
When dead ship condition, output has the result of pedestrian's generation cross-lane.
In the present embodiment, determining has pedestrian within the yellow safety line on waiting station platform, also there is train on train rail, column
Vehicle is currently entering the station or outbound, and such situation thinks that pedestrian crosses yellow safety line and belongs to irregularities, then output has
The result of pedestrian's generation cross-lane.
Output module 207 is also used to determine in first object image there is pedestrian in the first judgment module 202, described
Second judgment module 205, which determines, train in the second target image, but third judgment module 206 determines that train is currently at parking
When state, the result that cross-lane occurs without pedestrian is exported.
In the present embodiment, there is pedestrian in determining first object image, have train in the second target image, and train is current
When in dead ship condition, that is, determine within the yellow safety line on waiting station platform there is pedestrian, though there is train place on train rail
In the scene that state out of service, corresponding train waiting pedestrian are got on the bus, such situation thinks that pedestrian crosses yellow safety line category
In normal behaviour, the result that cross-lane occurs without pedestrian is exported.
Further, after the result that the output module 207 output has pedestrian that cross-lane occurs, the train station
Platform pedestrian gets over line monitoring device 20 further include:
Sending module 208, for sending a warning message to the control room at station;
The sending module 208 is also used to trigger the acoustic-optic alarm being arranged on the waiting station platform and alarms.
In the present embodiment, when discovery has pedestrian that cross-lane occurs, send a warning message to the control room at station same
When, it triggers the acoustic-optic alarm being arranged on the waiting station platform and alarms.It sends a warning message to control room, is convenient for vehicle
The staff that stands prevents the pedestrian for having cross-lane in time, in addition, the alarm of triggering warning device is to further function as warning pedestrian
Cross the effect of yellow safety line.
In conclusion railway platform pedestrian of the present invention gets over line monitoring device, the in yellow safety line is first obtained
First object image in one target area, and when having pedestrian in judging first object image obtains the on train rail
The second target image in two target areas when having train in judging the second target image, further judges the operation of train
State, if train is in dead ship condition, it is believed that more line belongs to normal behaviour, if train is in operating status, it is believed that more line belongs to
Irregularities, and when in judging the second target image without train, it is believed that more line also belongs to irregularities.With artificial intelligence
The computer vision and the sense of hearing of deep learning, the artificial 7*24 hours strict intelligence warning free of discontinuities on duty of substitution, protect passenger
Safety and the routine safety of train operation.The initiative technology by video monitoring and image procossing solves safety management
The blind zone problem of " last rice ".Effective ancillary technique means are provided for the safety detection of train and pedestrian, have been broken completely
The mechanism of cross-lane is passively judged whether there is by pure artificial vision, mitigates the workload of field personnel significantly, is improved
The safety of train operation realizes effective control to transportation safety production, and provides effectively for train scheduling room
The foundation of HD image.
Embodiment three
As shown in fig.3, the structural schematic diagram of the terminal provided for the embodiment of the present invention three.In present pre-ferred embodiments
In, the terminal 3 includes memory 31, at least one processor 32, at least one communication bus 33 and transceiver 34.
It will be understood by a person skilled in the art that the structure of the terminal shown in Fig. 3 does not constitute the restriction of the embodiment of the present invention,
Either bus topology, be also possible to star structure, the terminal 3 can also include than illustrate it is more or fewer other
Hardware perhaps software or different component layouts.
In some embodiments, the terminal 3 includes that one kind can be automatic to carry out according to the instruction for being previously set or storing
Numerical value calculates and/or the terminal of information processing, and hardware includes but is not limited to microprocessor, specific integrated circuit, programmable gate
Array, digital processing unit and embedded device etc..The terminal 3 may also include customer equipment, and the customer equipment includes but not
Human-computer interaction can be carried out by modes such as keyboard, mouse, remote controler, touch tablet or voice-operated devices with client by being limited to any one
Electronic product, for example, personal computer, tablet computer, smart phone, digital camera etc..
It should be noted that the terminal 3 is only for example, other electronic products that are existing or being likely to occur from now on such as may be used
It is adapted to the present invention, should also be included within protection scope of the present invention, and is incorporated herein by reference.
In some embodiments, the memory 31 is used to store program code and various data, such as is mounted on described
Railway platform pedestrian in terminal 3 gets over line monitoring device 20, and realizes high speed in the operational process of terminal 3, is automatically completed
The access of program or data.The memory 31 includes read-only memory (Read-Only Memory, ROM), random access memory
(Random Access Memory, RAM), programmable read only memory (Programmable Read-Only Memory,
PROM), Erasable Programmable Read Only Memory EPROM (Erasable Programmable Read-Only Memory, EPROM), one
Secondary programmable read only memory (One-time Programmable Read-Only Memory, OTPROM), electronics erasing type
Can make carbon copies read-only memory (Electrically-Erasable Programmable Read-Only Memory, EEPROM),
CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic
Tape storage or any other the computer-readable medium that can be used in carrying or storing data.
In some embodiments, at least one described processor 32 can be made of integrated circuit, such as can be by single
The integrated circuit of encapsulation is formed, and is also possible to be made of the integrated circuit that multiple identical functions or different function encapsulate, be wrapped
Include one or more central processing unit (Central Processing unit, CPU), microprocessor, digital processing chip,
The combination etc. of graphics processor and various control chips.At least one described processor 32 is the control core of the terminal 3
(Control Unit) is stored in using all parts of various interfaces and the entire terminal 3 of connection by running or executing
Program or module in the memory 31, and the data being stored in the memory 31 are called, to execute terminal 3
Various functions and processing data, such as execute the function that railway platform pedestrian gets over line monitoring.
In some embodiments, at least one communication bus 33 is arranged to realize the memory 31 and described
Connection communication between at least one processor 32 etc..
Although being not shown, the terminal 3 can also include the power supply (such as battery) powered to all parts, it is preferred that
Power supply can be logically contiguous by electric power controller and at least one described processor 32, to pass through electric power controller reality
The functions such as now management charging, electric discharge and power managed.Power supply can also include one or more direct current or alternating current
The random components such as source, recharging device, power failure detection circuit, power adapter or inverter, power supply status indicator.
The terminal 3 can also include multiple sensors, bluetooth module, Wi-Fi module etc., and details are not described herein.
It should be appreciated that the embodiment is only purposes of discussion, do not limited by this structure in patent claim.
The above-mentioned integrated unit realized in the form of software function module, can store and computer-readable deposit at one
In storage media.Above-mentioned software function module is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, terminal or the network equipment etc.) or processor (processor) execute each reality of the present invention
Apply the part of the method.
In a further embodiment, in conjunction with Fig. 2, the operation of the terminal 3 is can be performed at least one described processor 32
Device and the types of applications program of installation (railway platform pedestrian as mentioned gets over line monitoring device 20), program code etc., example
Such as, above-mentioned modules.
Program code is stored in the memory 31, and at least one described processor 32 can call the memory 31
The program code of middle storage is to execute relevant function.For example, modules described in Fig. 2 are stored in the memory 31
In program code, and as performed by least one described processor 32, to realize the function of the modules to reach
Railway platform pedestrian gets over the purpose of line monitoring.
In one embodiment of the invention, the memory 31 stores multiple instruction, the multiple instruction by it is described extremely
A few processor 32 is performed to realize that railway platform pedestrian gets over the function of line monitoring.
Specifically, at least one described processor 32 can refer to the corresponding implementation of Fig. 1 to the concrete methods of realizing of above-metioned instruction
The description of correlation step in example, this will not be repeated here.
In several embodiments provided by the present invention, it should be understood that disclosed device, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the module
It divides, only a kind of logical function partition, there may be another division manner in actual implementation.
The module as illustrated by the separation member may or may not be physically separated, aobvious as module
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of the modules therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
It, can also be in addition, each functional module in each embodiment of the present invention can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds software function module.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " is not excluded for other units or, odd number is not excluded for plural number.The multiple units stated in device claim
Or device can also be implemented through software or hardware by a unit or device.The first, the second equal words are used to indicate name
Claim, and does not indicate any particular order.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. a kind of railway platform pedestrian gets over line monitoring method, which is characterized in that the described method includes:
Obtain the first object image in the default first object region on waiting station platform;
Judge that whether there is or not pedestrians in the first object image;
When determining has pedestrian in the first object image, second in default second target area on train rail is obtained
Target image;
Judge that whether there is or not trains in second target image;
When determining has train in second target image, judge the train currently whether in dead ship condition;
When determining that the train is not currently in the dead ship condition, the result that output has pedestrian that cross-lane occurs.
2. the method as described in claim 1, which is characterized in that whether there is or not train packets in judgement second target image
It includes:
Obtain the background image before the train arrives;
Second target image and the background image are subjected to difference processing and obtain difference image;
Judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
When the characteristic value for judging the difference image is more than or equal to the default characteristic threshold value, second target is determined
There is train in image;
When the characteristic value for judging the difference image is less than the default characteristic threshold value, nothing in second target image is determined
Train.
3. the method as described in claim 1, which is characterized in that described to judge the train currently whether in dead ship condition packet
It includes:
The contour area of the train in multiple described second target images is detected using YOLO algorithm of target detection;
Judge whether position of the contour area of the train in every second target image is fixed;
When position of the contour area of the train in every second target image is fixed, determine that the train is current
In the dead ship condition;
When position of the contour area of the train in every second target image is not fixed, determine that the train is worked as
Before be not at the dead ship condition.
4. method as claimed in claim 3, which is characterized in that when determining that the train is not currently in the dead ship condition
When, the method also includes:
Judge whether displacement of the contour area of the train in multiple described second target images is reducing;
When judge displacement of the contour area of the train in multiple described second target images reduce when, determine the column
Vehicle is currently at the state of entering the station;
When judge displacement of the contour area of the train in multiple described second target images increase when, determine the column
Vehicle is currently at outbound state.
5. the method as described in Claims 1-4 any one, which is characterized in that have when determining in the first object image
Pedestrian, when in second target image without train, the method also includes:
The result that output has pedestrian that cross-lane occurs.
6. method as claimed in claim 5, which is characterized in that it is described output have pedestrian occur cross-lane result it
Afterwards, the method also includes:
It sends a warning message to the control room at station;
Meanwhile the acoustic-optic alarm that triggering is arranged on the waiting station platform is alarmed.
7. the method as described in Claims 1-4 any one, which is characterized in that have when determining in the first object image
Pedestrian has train in second target image, when the train is currently at dead ship condition, the method also includes:
Export the result that cross-lane occurs without pedestrian.
8. a kind of railway platform pedestrian gets over line monitoring device, which is characterized in that described device includes:
First obtains module, for obtaining the first object image in the default first object region on waiting station platform;
First judgment module, for judging that whether there is or not pedestrians in the first object image;
Second obtains module, for obtaining column when the first judgment module, which determines, has pedestrian in the first object image
The second target image in default second target area on track road;
Second judgment module, for judging that whether there is or not trains in second target image;
Third judgment module, for judging institute when second judgment module, which determines, has train in second target image
Whether train is stated currently in dead ship condition;
Output module, for determining that the train is not currently in the dead ship condition when the third judgment module, output has
The result of pedestrian's generation cross-lane.
9. a kind of terminal, which is characterized in that the terminal includes processor, and the processor is used to execute to store in memory
Realize that the railway platform pedestrian as described in any one of claim 1 to 7 gets over line monitoring method when computer program.
10. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
It is, the railway platform pedestrian as described in any one of claim 1 to 7 is realized when the computer program is executed by processor
More line monitoring method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910377519.4A CN110264651A (en) | 2019-05-07 | 2019-05-07 | Railway platform pedestrian gets over line monitoring method, device, terminal and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910377519.4A CN110264651A (en) | 2019-05-07 | 2019-05-07 | Railway platform pedestrian gets over line monitoring method, device, terminal and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110264651A true CN110264651A (en) | 2019-09-20 |
Family
ID=67914362
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910377519.4A Pending CN110264651A (en) | 2019-05-07 | 2019-05-07 | Railway platform pedestrian gets over line monitoring method, device, terminal and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110264651A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112528825A (en) * | 2020-12-04 | 2021-03-19 | 交控科技股份有限公司 | Station passenger recruitment service method based on image recognition |
CN112863121A (en) * | 2021-03-01 | 2021-05-28 | 哈尔滨市科佳通用机电股份有限公司 | Railway platform end line-crossing monitoring method |
CN113034866A (en) * | 2021-03-01 | 2021-06-25 | 哈尔滨市科佳通用机电股份有限公司 | Railway platform line crossing detection device and line crossing monitoring method |
CN114283544A (en) * | 2021-12-10 | 2022-04-05 | 中国电子科技集团公司第三十八研究所 | Railway platform intrusion monitoring system and method based on artificial intelligence |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060047379A1 (en) * | 2004-08-27 | 2006-03-02 | Schullian John M | Railcar transport telematics system |
CN101105097A (en) * | 2007-08-23 | 2008-01-16 | 上海交通大学 | Platform shield door intelligent control method |
CN105172844A (en) * | 2015-09-18 | 2015-12-23 | 王新 | Train platform precise display and cross-line voice alarm integrated management system for railway station |
CN109410250A (en) * | 2018-11-13 | 2019-03-01 | 深圳通业科技股份有限公司 | A kind of the vehicle pull-in recognition methods and terminal of view-based access control model image |
CN109686048A (en) * | 2019-01-02 | 2019-04-26 | 平安科技(深圳)有限公司 | Station platform gets over method for early warning, device, computer equipment and the storage medium of line |
-
2019
- 2019-05-07 CN CN201910377519.4A patent/CN110264651A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060047379A1 (en) * | 2004-08-27 | 2006-03-02 | Schullian John M | Railcar transport telematics system |
CN101105097A (en) * | 2007-08-23 | 2008-01-16 | 上海交通大学 | Platform shield door intelligent control method |
CN105172844A (en) * | 2015-09-18 | 2015-12-23 | 王新 | Train platform precise display and cross-line voice alarm integrated management system for railway station |
CN109410250A (en) * | 2018-11-13 | 2019-03-01 | 深圳通业科技股份有限公司 | A kind of the vehicle pull-in recognition methods and terminal of view-based access control model image |
CN109686048A (en) * | 2019-01-02 | 2019-04-26 | 平安科技(深圳)有限公司 | Station platform gets over method for early warning, device, computer equipment and the storage medium of line |
Non-Patent Citations (2)
Title |
---|
杨帆: "《数字图像处理与分析》", 31 January 2019, 北京航空航天大学出版社 * |
杨露菁等: "《智能图像处理及应用》", 31 March 2019, 中国铁道出版社有限公司 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112528825A (en) * | 2020-12-04 | 2021-03-19 | 交控科技股份有限公司 | Station passenger recruitment service method based on image recognition |
CN112863121A (en) * | 2021-03-01 | 2021-05-28 | 哈尔滨市科佳通用机电股份有限公司 | Railway platform end line-crossing monitoring method |
CN113034866A (en) * | 2021-03-01 | 2021-06-25 | 哈尔滨市科佳通用机电股份有限公司 | Railway platform line crossing detection device and line crossing monitoring method |
CN114283544A (en) * | 2021-12-10 | 2022-04-05 | 中国电子科技集团公司第三十八研究所 | Railway platform intrusion monitoring system and method based on artificial intelligence |
CN114283544B (en) * | 2021-12-10 | 2023-08-01 | 中国电子科技集团公司第三十八研究所 | Railway platform intrusion monitoring system and method based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110264651A (en) | Railway platform pedestrian gets over line monitoring method, device, terminal and storage medium | |
KR101146583B1 (en) | Smart computer camera for identifying vehicles in parking area | |
CN103116996B (en) | Tunnel illumination and security system | |
US10217359B2 (en) | System of correlated video and lighting for parking management and control | |
CN110759189A (en) | Elevator management method, device and system | |
KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
CN110490108A (en) | A kind of labeling method, device, storage medium and the electronic device of state violating the regulations | |
CN103987577A (en) | Method for monitoring and signaling a traffic situation in the surroundings of a vehicle | |
GB2455837A (en) | Co-operative camera surveillance method | |
CN110175533A (en) | Overpass traffic condition method of real-time, device, terminal and storage medium | |
CN110263623A (en) | Train climbs monitoring method, device, terminal and storage medium | |
CN103287943B (en) | A kind of Intelligent elevator management system | |
KR102122850B1 (en) | Solution for analysis road and recognition vehicle license plate employing deep-learning | |
CN105550666A (en) | Alarming system and method for preventing juveniles from driving cars | |
CN110782681B (en) | Traffic indicator lamp self-adaptive control method, device, terminal and storage medium | |
CN104361753A (en) | Method and device for obtaining evidences of rule and regulation breaking of vehicles not running in alternating mode | |
CN106228812A (en) | Illegal vehicle image-pickup method and system | |
KR102043922B1 (en) | A cctv divided management system and method it | |
WO2018123054A1 (en) | Accident prevention system, method, and program | |
CN111614884A (en) | Artificial intelligent camera and monitoring method | |
CN106327890A (en) | System and method for traffic emergency intervention | |
CN107067734A (en) | A kind of urban signal controlling intersection vehicles are detained peccancy detection method | |
CN110263622A (en) | Train fire monitoring method, apparatus, terminal and storage medium | |
CN112562407B (en) | ODD state prejudging method and device and autonomous passenger-riding parking system | |
CN106981200A (en) | Urban track traffic intelligent monitor 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |