CN110135258A - Escalator control method, apparatus, storage medium and computer equipment - Google Patents
Escalator control method, apparatus, storage medium and computer equipment Download PDFInfo
- Publication number
- CN110135258A CN110135258A CN201910295937.9A CN201910295937A CN110135258A CN 110135258 A CN110135258 A CN 110135258A CN 201910295937 A CN201910295937 A CN 201910295937A CN 110135258 A CN110135258 A CN 110135258A
- Authority
- CN
- China
- Prior art keywords
- human body
- frame image
- current frame
- escalator
- region
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 210000004197 pelvis Anatomy 0.000 claims description 63
- 210000003127 knee Anatomy 0.000 claims description 53
- 210000003423 ankle Anatomy 0.000 claims description 34
- 210000002683 foot Anatomy 0.000 claims description 33
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 12
- 238000003708 edge detection Methods 0.000 claims description 8
- 210000001364 upper extremity Anatomy 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 210000001624 hip Anatomy 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B29/00—Safety devices of escalators or moving walkways
- B66B29/005—Applications of security monitors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B29/00—Safety devices of escalators or moving walkways
- B66B29/02—Safety devices of escalators or moving walkways responsive to, or preventing, jamming by foreign objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Abstract
The application provides a kind of escalator control method, apparatus, storage medium and computer equipment, is applied to technical field of biometric identification.The method includes: the current frame image for obtaining escalator monitoring area；The information of preset human body key position is extracted from the current frame image；According to the information of the human body key position, judge in the current frame image with the presence or absence of unusual condition；If there are unusual conditions in the current frame image, stop the operation of escalator.Personnel safety has been effectively ensured in the embodiment of the present application.
Description
Technical field
This application involves technical field of biometric identification, specifically, this application involves a kind of escalator control methods, dress
It sets, storage medium and computer equipment.
Background technique
Escalator (Escalator), also known as escalator are a kind of staircases with circular flow ladder, for
Fixation power driven equipment that is upper or tilting down transport passenger, by the handrail of terraced road (apron conveyor of modification) and both sides
(belt conveyor of deformation) composition.The advantages that escalator is convenient and efficient because of its is widely used in market, subway, airport
Equal public places.During escalator operation, it often will appear abnormal conditions, such as falling over of human body is fallen in a swoon or accidentally
Skirt, trousers or jewelry are accidentally stuck in staircase gap etc., if this kind of abnormal conditions fail to find and handle in time, easily make
At casualties.
Summary of the invention
The application is directed to the shortcomings that existing way, proposes a kind of escalator control method, apparatus, storage medium and calculating
Machine equipment, personnel safety is effectively ensured.
Embodiments herein provides a kind of escalator control method according to first aspect, comprising:
Obtain the current frame image of escalator monitoring area；
The information of preset human body key position is extracted from the current frame image；
According to the information of the human body key position, judge in the current frame image with the presence or absence of unusual condition；
If there are unusual conditions in the current frame image, stop the operation of escalator.
In one embodiment, the human body key position includes ankle, knee, pelvis and backbone；It is described to work as from described
The information of preset human body key position is extracted in prior image frame, comprising:
Human body image is extracted from the current frame image；
Edge detection is carried out to the human body image, obtains the human body contour outline being made of each marginal point；
It, will be in pelvis region using the region of the middle preset width of the human body contour outline as pelvis region
Coordinate points of the heart point as pelvis；
The minimum point that head zone is identified from the human body contour outline, using the coordinate of the minimum point as the upper top of backbone
Point coordinate；
Foot areas is identified from the human body contour outline, and the coordinate in the middle position on the upper end boundary of foot areas is made
For the coordinate points of ankle；
Using pelvis region and the region of the middle preset width of foot areas as knee area, by knee area
Coordinate points of the central point as knee.
In one embodiment, the information according to the human body key position, judge be in the current frame image
It is no that there are unusual conditions, comprising:
According to the coordinate points of the coordinate points of ankle, the coordinate points of knee and pelvis, the angle of the human body lower part of the body is calculated；
According to the upper apex coordinate of the coordinate points of knee, the coordinate points of pelvis and backbone, the angle of upper half of human body is calculated
Degree；
If the angle of the lower part of the body and the angle of the upper part of the body are respectively less than preset value, determine to be not present in the current frame image
Otherwise unusual condition determines that there are unusual conditions in the current frame image.
In one embodiment, the human body key position includes ankle, knee, pelvis and backbone；It is described to work as from described
The information of preset human body key position is extracted in prior image frame, comprising:
Human body image is extracted from the current frame image；
Head zone is identified from the human body image, calculates the height of head zone；
Since the bottom of head zone, along foot's downwardly direction, determine in the human body image with head zone
Distance from bottom be (setting value * head zone height/2- head zone height) position, by the bottom of the position and head zone
Region behind region removal upper limb region between portion as backbone and pelvis；
From the bottom of backbone and pelvis region, along foot's downwardly direction, determine in the human body image with ridge
Column and the distance from bottom in pelvis region are the position of (setting value * head zone height/4), will descend predetermined width in this position
Region is as knee area；
The foot areas for identifying the human body image, using the region of predetermined width above the step region as ankle zone
Domain；
The region of backbone and pelvis, knee area and ankle zone are expressed as three vertical directions by Hough transform
Straight line.
In one embodiment, the information according to the human body key position, judge be in the current frame image
It is no that there are unusual conditions, comprising:
Calculate the first angle of the vertical straight line in the region of backbone and pelvis and the vertical straight line of knee area；
Calculate the second angle of the vertical straight line of knee area and the vertical straight line of ankle zone；
If first angle and second angle are respectively less than preset value, determine that there is no different in the current frame image
Otherwise normal situation determines that there are unusual conditions in the current frame image.
In one embodiment, if there are unusual conditions in the current frame image, stop the operation of escalator,
Include:
If there are unusual conditions for only one human body in the current frame image, after the current frame image is obtained
N frame image judges whether there is also unusual conditions for same human body in the nth frame image, if there is also abnormal shapes for same human body
Condition stops the operation of escalator；
If there are unusual conditions for multiple human bodies in the current frame image, stop the operation of escalator.
In one embodiment, if there is also unusual conditions for the same human body, stop the operation of escalator, comprising:
It obtains same human body and enters M frame image before escalator, judge that same human body is in the M frame image
No there are unusual conditions, if it is not, stopping the operation of escalator.
Embodiments herein additionally provides a kind of controller of escalator according to the second aspect, comprising:
Current frame image obtains module, for obtaining the current frame image of escalator monitoring area；
Human body key position information extraction modules, for extracting preset human body key position from the current frame image
Information；
Judgment module judges to whether there is in the current frame image for the information according to the human body key position
Unusual condition；
Escalator control module, for, there are when unusual condition, stopping escalator in the current frame image
Operation.
Embodiments herein additionally provides a kind of computer readable storage medium, stores thereon according in terms of third
There is computer program, which realizes escalator control method described in above-mentioned any one when being executed by processor.
Embodiments herein additionally provides a kind of computer equipment, the computer equipment packet according to the 4th aspect
It includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes escalator control method described in above-mentioned any one.
Above-mentioned escalator control method, apparatus, storage medium and computer equipment, is monitored escalator,
The posture of human body on escalator is analyzed by the current frame image in monitor video, once there is exception in discovery posture, then certainly
It is dynamic to shut down elevator and avoid accident, so that personnel safety be effectively ensured.
The additional aspect of the application and advantage will be set forth in part in the description, these will become from the following description
It obtains obviously, or recognized by the practice of the application.
Detailed description of the invention
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the schematic diagram of the escalator control method of the application one embodiment；
Fig. 2 is the schematic diagram of the controller of escalator of the application one embodiment；
Fig. 3 is the schematic diagram of the computer equipment of the application one embodiment.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the application, and cannot be construed to the limitation to the application.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in the description of the present application
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in the application fields.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
As shown in Figure 1, the schematic diagram of the escalator control method for an embodiment, this method comprises:
S110, the current frame image for obtaining escalator monitoring area.
Escalator monitoring area refer to can above effective monitoring escalator passenger status region.It can be certainly
The monitoring devices such as suitable position installation camera above dynamic staircase, shoot the monitoring on escalator by the monitoring device and regard
Frequently, it is then sent to the identification that background computer carries out human body attitude.
For the posture of human body on more accurate monitoring escalator, multiple monitoring can be just installed on the escalator
Equipment, for example, respectively installing a monitoring device in escalator both ends and middle position.Monitoring device can be with 24 hours continuously
Monitor video on disconnected shooting escalator.If escalator is that just brings into operation in someone, nobody when stop
Escalator, can also when escalator brings into operation just open monitoring device, obtain monitor video carry out unusual condition
Analysis, escalator it is out of service after close monitoring device, no longer shooting monitor video.
Monitoring device is just opened when in view of escalator operation and obtains monitor video, might have prolonging for certain time
Late, be also possible to be abnormal situation within the delay time, therefore, optionally, can also by human body proximity sensor out,
Human body proximity sensor is installed near escalator, is detecting that someone enters elevator and works as according to human body proximity sensor
When preceding escalator is in halted state, monitoring device is opened in advance, shoots monitor video.
The monitor video for obtaining escalator monitoring area, extracts current frame image, present frame figure from the monitor video
As the wherein frame image currently to be analyzed.
S120, the information that preset human body key position is extracted from the current frame image.
The human body key position for needing to extract is preset, in order to realize accurately identifying for human body attitude, optionally, human body
Key position includes ankle, knee, pelvis and backbone.It should be understood that the application is not to the human body key position of setting
It is defined.
Current frame image is analyzed, the information of the key position of each human body in current frame image is extracted.
S130, according to the information of the human body key position, judge in the current frame image with the presence or absence of unusual condition.
Unusual condition refers to whether human body attitude is normal, for example, if according to the letter of the key position of some human body
Breath, judges that the human body is in flexible non-stand-up state, it is determined that unusual condition occur.If there are multiple human bodies in current frame image,
The posture of multiple human bodies can be then determined respectively, can also just be stopped when detecting that some human body attitude occurs abnormal to it
The detection of its human body attitude.
If there are unusual conditions in S140, the current frame image, stop the operation of escalator.
If detecting unusual condition, it can be automatically turned off escalator by the modes such as cut off the power, with
It avoids accidents.When closing escalator, in order to avoid causing unnecessary fear, can also export escalator will
The voice messaging of Suspend Job.
After unusual condition exclusion, restore the normal operation of escalator.If there are also passengers on the escalator, in order to
Avoid suddenly automatic running cause unnecessary fear, the voice reminder that reminding passengers escalator brings into operation can also be exported
Information.
If detecting does not have unusual condition, the normal operation of escalator is kept.
Above-mentioned escalator control method analyzes the appearance of human body on escalator by the current frame image in monitor video
State is then automatically turned off elevator and avoids accident, so that personnel safety be effectively ensured once exception occurs in discovery posture.
In order to improve the efficiency of human body key position extraction, the embodiment of the present application also provides two kinds of extraction human body key portions
The method of the information of position, below describes to both methods in detail.
In one embodiment, the information that preset human body key position is extracted from the current frame image, packet
It includes:
S120a, human body image is extracted from the current frame image.
Contexts segmentation or other processing are carried out to the monitoring image of shooting, extract human body image.The people of extraction
Body image includes the overall profile of people.
S120b, edge detection is carried out to the human body image, obtains the human body contour outline being made of each marginal point.
Edge detection is the basic problem in image procossing and computer vision, and the purpose of edge detection is reference numbers figure
The apparent point of brightness change as in.The step can extract human body wheel using existing edge detection algorithm in the prior art
It is wide.
S120c, using the region of the middle preset width of the human body contour outline as pelvis region, by pelvis location
Coordinate points of the central point in domain as pelvis.
In view of general pelvis is located at the intermediate region of human body, therefore it can first determine the middle position of human body contour outline,
Then certain value is extended up and down respectively from the middle position, obtain the region where pelvis, extend up and down
Value can be determined according to actual needs.After obtaining pelvis region, central point is found, with the coordinate points generation of the central point
The coordinate points of table pelvis.
S120d, the minimum point that head zone is identified from the human body contour outline, using the coordinate of the minimum point as backbone
Upper apex coordinate.
The head zone of human body contour outline can be identified using existing recognizer in the prior art, it is contemplated that backbone connects
Head zone, therefore find the minimum point of head zone, the upper vertex of backbone represented with the coordinate of the minimum point of head zone
Coordinate.
S120e, foot areas is identified from the human body contour outline, by the middle position on the upper end boundary of foot areas
Coordinate points of the coordinate as ankle.
The foot areas of human body contour outline can be identified using existing recognizer in the prior art, it is contemplated that ankle position
In the upper surface of foot areas, therefore, the upper end boundary of foot areas is first found, then makees the coordinate of the central point on upper end boundary
For the coordinate points of ankle.
S120f, using pelvis region and the region of the middle preset width of foot areas as knee area, by knee
Coordinate points of the central point in region as knee.
In view of knee area is normally at the middle position of pelvis region and foot areas, therefore can first determine
Middle position between pelvis region and foot areas out, then from the middle position, extension is certain up and down respectively
Value, obtains knee area, the value extended up and down can be determined according to actual needs.After obtaining knee area, look for
To central point, the coordinate points of knee are represented with the coordinate points of the central point.
In another embodiment, the information that preset human body key position is extracted from the current frame image,
Include:
S120A, human body image is extracted from the current frame image.
Contexts segmentation or other processing are carried out to the monitoring image of shooting, extract human body image.The people of extraction
Body image includes the overall profile of people.
S120B, head zone is identified from the human body image, calculate the height of head zone.
Head zone is identified using existing algorithm in the prior art, optionally, find head zone highest point and
Minimum point, according to the difference of highs and lows, so that it may obtain the height of head zone.
S120C, since the bottom of head zone, along foot's downwardly direction, determine in the human body image with head
The distance from bottom in portion region is the position of (setting value * head zone height/2- head zone height), by the position and header area
Region behind region removal upper limb region between the bottom in domain as backbone and pelvis.
In view of the ratio of common people is 7 bodies, therefore 7 can be set by setting value.In view of the upper part of the body of human body
Almost be with the lower part of the body it is contour, therefore, the height of human body is first obtained according to setting value * head zone height, then by height/
2 obtain the height of upper half of human body, and the height of the upper part of the body is subtracted to the height of head zone, just obtain backbone and pelvis region
Highly.It, can be from the height according to backbone and pelvis region in order to improve the accuracy of detection in view of above the waist further including arm
It spends and removes upper limb region in obtained region, using remaining region as the region of backbone and pelvis.
S120D, the human body image is determined from the bottom of backbone and pelvis region along foot's downwardly direction
In with backbone and the distance from bottom in pelvis region be (setting value * head zone height/4) position, will be lower default in this position
The region of width is as knee area.
In view of knee area is almost in the middle position of the lower part of the body, therefore according to setting value * head zone height/4
The middle position for finding knee extends downwards one fixed width from the middle position, then available knee area upwards respectively, to
On the width that extends downwards can be determined according to actual needs.
The foot areas of S120E, the identification human body image, using the region of predetermined width above the step region as
Ankle zone.
Foot areas is identified using existing algorithm in the prior art, it is contemplated that ankle in the upper surface of foot areas, because
, directly using the region of predetermined width above foot areas as ankle zone, predetermined width can carry out really according to actual needs for this
It is fixed.
S120F, by the region of backbone and pelvis, knee area and ankle zone by Hough transform be expressed as three it is perpendicular
Histogram to straight line.
Hough transform is a kind of parameter estimation techniques using voting principle, and principle is to utilize image space and Hough
Test problems in image space are transformed into parameter space by the point-line duality of parameter space.It, will by Hough transform
The region of backbone and pelvis is expressed as the straight line of a vertical direction, and knee area is expressed as to the straight line of a vertical direction,
Ankle zone is expressed as to the straight line of a vertical direction.
For the method for both the above human body key position information extraction, the application also each provides corresponding abnormal shape
Condition judgment method, is introduced in detail below.
It is in one embodiment, described to be closed according to the human body for the first human body key position information extracting method
The information at key position judges in the current frame image with the presence or absence of unusual condition, comprising: according to the coordinate points of ankle, knee
Coordinate points and pelvis coordinate points, calculate the human body lower part of the body angle；According to the coordinate points of knee, the coordinate points of pelvis with
And the upper apex coordinate of backbone, calculate the angle of upper half of human body；If the angle of the lower part of the body and the angle of the upper part of the body are respectively less than
Preset value determines otherwise to determine there is abnormal shape in the current frame image in the current frame image there is no unusual condition
Condition.In the present embodiment, the principle of angle can be calculated based on three coordinate points, calculate separately out the human body lower part of the body angle and
The angle of the upper part of the body determines that human body is in upright state if the angle of the lower part of the body and the angle of the upper part of the body are respectively less than preset value,
There is no unusual condition, otherwise determines that multiplying human body is in flexible non-stand-up state, there is unusual condition.
It is in one embodiment, described to be closed according to the human body for second of human body key position information extracting method
The information at key position judges in the current frame image with the presence or absence of unusual condition, comprising: calculate the region of backbone and pelvis
First angle of vertical straight line and the vertical straight line of knee area；Calculate knee area vertical straight line and ankle zone it is vertical
Second angle of straight line；If first angle and second angle are respectively less than preset value, determine in the current frame image
There is no unusual conditions, otherwise determine that there are unusual conditions in the current frame image.It is perpendicular by calculating three in the present embodiment
Angle between straight straight line determines whether human body is in upright state, if two angles are respectively less than preset value, determines at human body
In upright state, there is no unusual condition, otherwise determines that human body is in flexible non-stand-up state, there is unusual condition.
In order to further increase the accuracy of unusual condition judgement, the application can also be different according to occurring in current frame image
The number of the human body of normal situation, is further determined, therefore, in one embodiment, if the current frame image
In there are unusual conditions, stop the operation of escalator, comprising: if in the current frame image only one human body exist it is abnormal
Situation obtains the nth frame image after the current frame image, judge in the nth frame image same human body whether there is also
Unusual condition stops the operation of escalator if there is also unusual conditions for same human body；If multiple people in the current frame image
There are unusual conditions for body, stop the operation of escalator；N is more than or equal to 1.
In the present embodiment, when there is unusual condition in only one human body (i.e. passenger) in current frame image, it is contemplated that passenger
It is possible that only staggering, do not fall down really, in order to avoid invalid escalator stops, causing the waste of resource,
Detect that there are when unusual condition, then detect nth frame figure after the current frame image in current frame image in the above manner
Whether there are also unusual conditions to occur by the passenger in picture (such as a certain frame of the frame after 10 seconds), if the passenger still has abnormal shape
Condition, judgement are abnormal situation, stop the operation of escalator.When unusual condition occur in multiple passengers in current frame image, then
A possibility that actually occurring unusual condition is very big, therefore can directly determine to be abnormal situation in the case of this kind, stops automatic
The operation of staircase, since this kind of situation harmfulness is larger, it is also necessary to warning information is exported to staff, to exclude exception in time
Situation.
The passenger has unusual condition in nth frame (such as a certain frame after the frame 10) image after detection present frame
When, it is contemplated that passenger may inherently be in flexible non-stand-up state due to impediment etc., in order to avoid invalid is helped automatically
Ladder stops, and causes the waste of resource, therefore, in one embodiment, if there is also unusual conditions for the same human body, stops certainly
The operation of dynamic staircase, comprising: M frame (such as the 5th frame) image before same human body enters escalator is obtained, described in judgement
Same human body whether there is unusual condition in M frame image, if it is not, stopping the operation of escalator；M is more than or equal to 1.This implementation
In example, when certain passenger has abnormality in detecting the nth frame image after present frame and the present frame, the passenger is obtained
Into certain frame image before escalator, whether just the posture of the passenger in entering the frame image before escalator is determined
Often, if normally, judgement is abnormal situation, stop escalator operation, otherwise determine passenger impediment itself, protect
Hold the normal operation of escalator.
Furthermore, it is contemplated that generally can be along with noise, therefore, in order to avoid invalid escalator when being abnormal situation
Stop, causing the waste of resource, ambient noise can also be acquired in real time, certain passenger has abnormal shape in detecting current frame image
When state, whether the ambient noise detected instantly increases suddenly, if so, determining to be abnormal situation.
Based on the same inventive concept, the application also provides a kind of controller of escalator, with reference to the accompanying drawing to this Shen
Please the specific embodiment of device describe in detail.
As shown in Fig. 2, the schematic diagram of the controller of escalator for an embodiment, described device include:
Current frame image obtains module 210, for obtaining the current frame image of escalator monitoring area；
Human body key position information extraction modules 220, it is crucial for extracting preset human body from the current frame image
The information at position；
Judgment module 230 judges whether deposit in the current frame image for the information according to the human body key position
In unusual condition；
Escalator control module 240, for, there are when unusual condition, stopping escalator in the current frame image
Operation.
In one embodiment, the human body key position includes ankle, knee, pelvis and backbone；Human body key position
Information extraction modules 220 include:
Human body image extraction unit, for extracting human body image from the current frame image；
Edge detection unit obtains the people being made of each marginal point for carrying out edge detection to the human body image
Body profile；
Pelvis coordinate points determination unit, for using the region of the middle preset width of the human body contour outline as where pelvis
Region, using the central point of pelvis region as the coordinate points of pelvis；
Backbone coordinate determination unit is minimum by this for identifying the minimum point of head zone from the human body contour outline
Upper apex coordinate of the coordinate of point as backbone；
Ankle coordinate determination unit, for identifying foot areas from the human body contour outline, by the upper end of foot areas
Coordinate points of the coordinate in the middle position on boundary as ankle；
Knee coordinate determination unit, for using pelvis region and the region of the middle preset width of foot areas as
Knee area, using the central point of knee area as the coordinate points of knee.
In one embodiment, judgment module 230 includes:
Lower part of the body angle calculation unit, for the coordinate points according to the coordinate points of ankle, the coordinate points of knee and pelvis,
Calculate the angle of the human body lower part of the body；
Upper part of the body angle calculation unit, for the upper vertex according to the coordinate points of knee, the coordinate points of pelvis and backbone
Coordinate calculates the angle of upper half of human body；
Judging unit, it is described current for determining when the angle of the lower part of the body and the angle of the upper part of the body are respectively less than preset value
Unusual condition is not present in frame image, otherwise determines that there are unusual conditions in the current frame image.
In one embodiment, the human body key position includes ankle, knee, pelvis and backbone；Human body key position
Information extraction modules 220 include:
Human body image extraction unit, for extracting human body image from the current frame image；
Head zone height calculation unit calculates head zone for identifying head zone from the human body image
Height；
Backbone and pelvis area determination unit, for since the bottom of head zone, along foot's downwardly direction, really
It is calmly (setting value * head zone height/2- head zone height) with the distance from bottom of head zone in the human body image
Position, by the region behind the region removal upper limb region between the position and the bottom of head zone as backbone and pelvis；
Knee area determination unit, for from the bottom of backbone and pelvis region, along foot's downwardly direction, really
It is calmly the position of (setting value * head zone height/4) with backbone and the distance from bottom in pelvis region in the human body image, it will
Descend the region of predetermined width as knee area in this position；
Ankle zone determination unit, the foot areas of the human body image for identification will be pre- above the step region
If the region of width is as ankle zone；
Hough transform unit, for the region of backbone and pelvis, knee area and ankle zone to be passed through Hough transform
It is expressed as the straight line of three vertical directions.
In one embodiment, judgment module 230 includes:
First angle calcu-lation unit, for calculate the region of backbone and pelvis vertical straight line and knee area it is vertical straight
First angle of line；
Second angle calcu-lation unit, for calculating the second of the vertical straight line of knee area and the vertical straight line of ankle zone
Angle；
Judging unit, it is described current for determining when first angle and second angle are respectively less than preset value
Unusual condition is not present in frame image, otherwise determines that there are unusual conditions in the current frame image.
In one embodiment, escalator control module 240 is used for only one human body in the current frame image
There are nth frame images when unusual condition, obtained after the current frame image, judge same human body in the nth frame image
Whether there is also unusual conditions stops the operation of escalator if there is also unusual conditions for same human body；In the present frame figure
Multiple human bodies stop the operation of escalator there are when unusual condition as in.
In one embodiment, escalator control module 240 obtains same human body and enters M frame before escalator
Image judges that same human body whether there is unusual condition in the M frame image, if it is not, stopping the operation of escalator.
Other technical characteristics of above-mentioned controller of escalator are identical as above-mentioned escalator control method, refuse herein
It repeats.
The embodiment of the present application also provides a kind of computer readable storage medium, is stored thereon with computer program, the program
Escalator control method described in above-mentioned any one is realized when being executed by processor.Wherein, the storage medium include but
Be not limited to any kind of disk (including floppy disk, hard disk, CD, CD-ROM and magneto-optic disk), ROM (Read-Only Memory,
Read-only memory), RAM (Random AcceSS Memory, immediately memory), EPROM (EraSable Programmable
Read-Only Memory, Erarable Programmable Read only Memory), EEPROM (Electrically EraSable
Programmable Read-Only Memory, Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or light card
Piece.It is, storage medium includes by equipment (for example, computer) with any Jie for the form storage or transmission information that can be read
Matter.It can be read-only memory, disk or CD etc..
The embodiment of the present application also provides a kind of computer equipment, and the computer equipment includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes escalator control method described in above-mentioned any one.
Fig. 3 is the structural schematic diagram of the application computer equipment, including processor 320, storage device 330, input unit
The devices such as 340 and display unit 350.It will be understood by those skilled in the art that the structure devices shown in Fig. 3 are not constituted to institute
There is the restriction of computer equipment, may include than illustrating more or fewer components, or the certain components of combination.Storage device
330 can be used for storing application program 310 and each functional module, and processor 320 runs the application journey for being stored in storage device 330
Sequence 310, thereby executing the various function application and data processing of equipment.Storage device 330 can be built-in storage or external memory
Reservoir, or including both built-in storage and external memory.Built-in storage may include read-only memory, programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory or random storage
Device.External memory may include hard disk, floppy disk, ZIP disk, USB flash disk, tape etc..Storage device disclosed in the present application includes but not
It is limited to the storage device of these types.Storage device 330 disclosed in the present application is only used as example rather than as restriction.
Input unit 340 is used to receive the input of signal, and receives the current frame image of escalator monitoring area.It is defeated
Entering unit 340 may include touch panel and other input equipments.Touch panel collects the touch of user on it or nearby
Operation (for example user uses any suitable objects or attachment such as finger, stylus on touch panel or near touch panel
Operation), and drive corresponding attachment device according to a pre-set procedure；Other input equipments can include but is not limited to object
Manage one of keyboard, function key (such as broadcasting control button, switch key etc.), trace ball, mouse, operating stick etc. or more
Kind.Display unit 350 can be used for showing user input information or be supplied to user information and computer equipment it is various
Menu.The forms such as liquid crystal display, Organic Light Emitting Diode can be used in display unit 350.Processor 320 is computer equipment
Control centre is stored in storage dress by running or executing using the various pieces of various interfaces and the entire computer of connection
The software program and/or module in 330 are set, and calls the data being stored in storage device, performs various functions and handles
Data.
In one embodiment, computer equipment includes one or more processors 320, and one or more storage dresses
330 are set, one or more application program 310, wherein one or more of application programs 310 are stored in storage device 330
In and be configured as being executed by one or more of processors 320, one or more of application programs 310 are configured to hold
Escalator control method described in row above embodiments.
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
It should be understood that can be integrated in a processing module in each functional unit in each embodiment of the application,
It can be physically existed alone, can also be integrated in two or more units in a module with each unit.It is above-mentioned integrated
Module both can take the form of hardware realization, can also be realized in the form of software function module.
The above is only some embodiments of the application, it is noted that for the ordinary skill people of the art
For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered
It is considered as the protection scope of the application.
Claims (10)
1. a kind of escalator control method characterized by comprising
Obtain the current frame image of escalator monitoring area；
The information of preset human body key position is extracted from the current frame image；
According to the information of the human body key position, judge in the current frame image with the presence or absence of unusual condition；
If there are unusual conditions in the current frame image, stop the operation of escalator.
2. escalator control method according to claim 1, which is characterized in that the human body key position includes foot
Ankle, knee, pelvis and backbone；The information that preset human body key position is extracted from the current frame image, comprising:
Human body image is extracted from the current frame image；
Edge detection is carried out to the human body image, obtains the human body contour outline being made of each marginal point；
Using the region of the middle preset width of the human body contour outline as pelvis region, by the central point of pelvis region
Coordinate points as pelvis；
The minimum point that head zone is identified from the human body contour outline is sat the coordinate of the minimum point as the upper vertex of backbone
Mark；
Foot areas is identified from the human body contour outline, using the coordinate in the middle position on the upper end boundary of foot areas as foot
The coordinate points of ankle；
Using pelvis region and the region of the middle preset width of foot areas as knee area, by the center of knee area
Coordinate points of the point as knee.
3. escalator control method according to claim 2, which is characterized in that described according to the human body key position
Information, judge in the current frame image with the presence or absence of unusual condition, comprising:
According to the coordinate points of the coordinate points of ankle, the coordinate points of knee and pelvis, the angle of the human body lower part of the body is calculated；
According to the upper apex coordinate of the coordinate points of knee, the coordinate points of pelvis and backbone, the angle of upper half of human body is calculated；
If the angle of the lower part of the body and the angle of the upper part of the body are respectively less than preset value, determine that there is no abnormal in the current frame image
Otherwise situation determines that there are unusual conditions in the current frame image.
4. escalator control method according to claim 1, which is characterized in that the human body key position includes foot
Ankle, knee, pelvis and backbone；The information that preset human body key position is extracted from the current frame image, comprising:
Human body image is extracted from the current frame image；
Head zone is identified from the human body image, calculates the height of head zone；
Since the bottom of head zone, along foot's downwardly direction, the bottom in the human body image with head zone is determined
Portion's distance is the position of (setting value * head zone height/2- head zone height), by the position and the bottom of head zone it
Between region removal upper limb region after region as backbone and pelvis；
From the bottom of backbone and pelvis region, along foot's downwardly direction, determine in the human body image with backbone and
The distance from bottom in pelvis region is the position of (setting value * head zone height/4), will descend the region of predetermined width in this position
As knee area；
The foot areas for identifying the human body image, using the region of predetermined width above the step region as ankle zone；
The region of backbone and pelvis, knee area and ankle zone are expressed as the straight of three vertical directions by Hough transform
Line.
5. escalator control method according to claim 4, which is characterized in that described according to the human body key position
Information, judge in the current frame image with the presence or absence of unusual condition, comprising:
Calculate the first angle of the vertical straight line in the region of backbone and pelvis and the vertical straight line of knee area；
Calculate the second angle of the vertical straight line of knee area and the vertical straight line of ankle zone；
If first angle and second angle are respectively less than preset value, determine that there is no abnormal shapes in the current frame image
Otherwise condition determines that there are unusual conditions in the current frame image.
6. according to claim 1 to escalator control method described in 5 any one, which is characterized in that if described work as
There are unusual conditions in prior image frame, stop the operation of escalator, comprising:
If there are unusual conditions for only one human body in the current frame image, the nth frame after the current frame image is obtained
Image, judge in the nth frame image same human body whether there is also unusual condition, if same human body there is also unusual condition,
Stop the operation of escalator；
If there are unusual conditions for multiple human bodies in the current frame image, stop the operation of escalator.
7. escalator control method according to claim 6, which is characterized in that if there is also exceptions for the same human body
Situation stops the operation of escalator, comprising:
It obtains same human body and enters M frame image before escalator, judge whether same human body is deposited in the M frame image
In unusual condition, if it is not, stopping the operation of escalator.
8. a kind of controller of escalator characterized by comprising
Current frame image obtains module, for obtaining the current frame image of escalator monitoring area；
Human body key position information extraction modules, for extracting the letter of preset human body key position from the current frame image
Breath；
Judgment module judges in the current frame image for the information according to the human body key position with the presence or absence of abnormal
Situation；
Escalator control module, for, there are when unusual condition, stopping the operation of escalator in the current frame image.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
Escalator control method as claimed in any of claims 1 to 7 in one of claims is realized when row.
10. a kind of computer equipment, which is characterized in that the computer equipment includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now escalator control method as claimed in any of claims 1 to 7 in one of claims.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910295937.9A CN110135258A (en) | 2019-04-12 | 2019-04-12 | Escalator control method, apparatus, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910295937.9A CN110135258A (en) | 2019-04-12 | 2019-04-12 | Escalator control method, apparatus, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110135258A true CN110135258A (en) | 2019-08-16 |
Family
ID=67569811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910295937.9A Pending CN110135258A (en) | 2019-04-12 | 2019-04-12 | Escalator control method, apparatus, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135258A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490171A (en) * | 2019-08-26 | 2019-11-22 | 睿云联(厦门)网络通讯技术有限公司 | A kind of danger gesture recognition method, device, computer equipment and storage medium |
| CN111914661A (en) * | 2020-07-06 | 2020-11-10 | 广东技术师范大学 | Abnormal behavior recognition method, target abnormal recognition method, device, and medium |
| CN112645201A (en) * | 2020-12-10 | 2021-04-13 | 通力电梯有限公司 | Method and device for setting the state of a scene detection module of an escalator |
| CN112978551A (en) * | 2021-02-27 | 2021-06-18 | 浙江城际特种设备检测有限公司 | Escalator safety inspection method and system, storage medium and intelligent terminal |
| CN113033300A (en) * | 2021-02-07 | 2021-06-25 | 广东省科学院智能制造研究所 | Escalator safety automatic monitoring method and system based on computer vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011011876A (en) * | 2009-07-02 | 2011-01-20 | Mitsubishi Electric Engineering Co Ltd | Overturning detecting device and man conveyor provided with the same |
| KR101329526B1 (en) * | 2013-01-31 | 2013-11-14 | 한상진 | Escalator of real-time safe driving system and its control method |
| JP2014016742A (en) * | 2012-07-06 | 2014-01-30 | Nippon Signal Co Ltd:The | Fall detection system |
| CN107506706A (en) * | 2017-08-14 | 2017-12-22 | 南京邮电大学 | A kind of tumble detection method for human body based on three-dimensional camera |
| CN108805093A (en) * | 2018-06-19 | 2018-11-13 | 华南理工大学 | Escalator passenger based on deep learning falls down detection algorithm |
| CN208200104U (en) * | 2018-04-28 | 2018-12-07 | 刘伟 | A kind of escalator automatic start-stop control system based on image recognition |
-
2019
- 2019-04-12 CN CN201910295937.9A patent/CN110135258A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011011876A (en) * | 2009-07-02 | 2011-01-20 | Mitsubishi Electric Engineering Co Ltd | Overturning detecting device and man conveyor provided with the same |
| JP2014016742A (en) * | 2012-07-06 | 2014-01-30 | Nippon Signal Co Ltd:The | Fall detection system |
| KR101329526B1 (en) * | 2013-01-31 | 2013-11-14 | 한상진 | Escalator of real-time safe driving system and its control method |
| CN107506706A (en) * | 2017-08-14 | 2017-12-22 | 南京邮电大学 | A kind of tumble detection method for human body based on three-dimensional camera |
| CN208200104U (en) * | 2018-04-28 | 2018-12-07 | 刘伟 | A kind of escalator automatic start-stop control system based on image recognition |
| CN108805093A (en) * | 2018-06-19 | 2018-11-13 | 华南理工大学 | Escalator passenger based on deep learning falls down detection algorithm |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490171A (en) * | 2019-08-26 | 2019-11-22 | 睿云联(厦门)网络通讯技术有限公司 | A kind of danger gesture recognition method, device, computer equipment and storage medium |
| CN111914661A (en) * | 2020-07-06 | 2020-11-10 | 广东技术师范大学 | Abnormal behavior recognition method, target abnormal recognition method, device, and medium |
| CN112645201A (en) * | 2020-12-10 | 2021-04-13 | 通力电梯有限公司 | Method and device for setting the state of a scene detection module of an escalator |
| CN113033300A (en) * | 2021-02-07 | 2021-06-25 | 广东省科学院智能制造研究所 | Escalator safety automatic monitoring method and system based on computer vision |
| CN112978551A (en) * | 2021-02-27 | 2021-06-18 | 浙江城际特种设备检测有限公司 | Escalator safety inspection method and system, storage medium and intelligent terminal |
| CN112978551B (en) * | 2021-02-27 | 2023-01-31 | 浙江城际特种设备检测有限公司 | Escalator safety inspection method and system, storage medium and intelligent terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110135258A (en) | Escalator control method, apparatus, storage medium and computer equipment | |
| Wang et al. | Yawning detection for determining driver drowsiness | |
| WO2017125094A1 (en) | Body fall smart control system and method therefor | |
| US10165971B2 (en) | Driver state determination apparatus | |
| CN107662872B (en) | Monitoring system and monitoring method for passenger conveyor | |
| CN109963539B (en) | Nursing support system, control method thereof, and computer-readable recording medium | |
| JP4587067B2 (en) | Method and apparatus for monitoring the fall of an object | |
| US20200334477A1 (en) | State estimation apparatus, state estimation method, and state estimation program | |
| EP3224177B1 (en) | Elevator security and control system based on passenger movement | |
| Vaidehi et al. | Video based automatic fall detection in indoor environment | |
| CN103903281A (en) | Old people tumbling detecting method based on multi-feature analyzing and scene studying | |
| CN111275910B (en) | Method and system for detecting border crossing behavior of escalator based on Gaussian mixture model | |
| JP6779410B2 (en) | Video analyzer, video analysis method, and program | |
| JP4883415B2 (en) | Monitoring device and program | |
| US20220036056A1 (en) | Image processing apparatus and method for recognizing state of subject | |
| JPH05261692A (en) | Working environment monitoring device for robot | |
| JP2002029421A (en) | Method and device for determining presence of train, and monitoring system | |
| CN114708552A (en) | Three-dimensional area intrusion detection method and system based on human skeleton | |
| EP3335151A1 (en) | Occupancy detection | |
| JP6503262B2 (en) | Motion recognition device | |
| JP7146450B2 (en) | object detector | |
| CN115611126A (en) | Method, device, equipment and storage medium for guiding escalator passenger behaviors | |
| JP6000762B2 (en) | Image monitoring device | |
| CN116229502A (en) | Image-based tumbling behavior identification method and equipment | |
| JPH1186005A (en) | Operation detecting device |
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 |