CN104961009A - Multi-elevator parallel operation coordination control method and system based on machine vision - Google Patents
Multi-elevator parallel operation coordination control method and system based on machine vision Download PDFInfo
- Publication number
- CN104961009A CN104961009A CN201510279503.1A CN201510279503A CN104961009A CN 104961009 A CN104961009 A CN 104961009A CN 201510279503 A CN201510279503 A CN 201510279503A CN 104961009 A CN104961009 A CN 104961009A
- Authority
- CN
- China
- Prior art keywords
- elevator
- floor
- ladder
- control method
- parallel operation
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/02—Control systems without regulation, i.e. without retroactive action
- B66B1/06—Control systems without regulation, i.e. without retroactive action electric
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Elevator Control (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The invention discloses a multi-elevator parallel operation coordination control method and system based on machine vision. The multi-elevator parallel operation coordination control method includes the following steps of converting images acquired by cameras inside and outside elevators to grey-scale images and performing binarization processing; performing HOG feature extraction to obtain human body characteristic samples, constructing a type-2 fuzzy neural classifier, performing Binary judgment by means of the trained type-2 fuzzy neural classifier, counting and adding the human body characteristic samples judged by the classifier to obtain the number of people inside and outside the elevators; and scheduling the elevators by means of a coordination control algorithm through the statistics of the number of people inside and outside the elevators, and the comprehensive considering of the number of people waiting for the elevators of each floor, the residual capacity in each elevator, and distance from elevator waiting positions. The multi-elevator parallel operation coordination control method and system effectively reduce the unnecessary elevating of the elevators, reduce the wearing of the elevators, prolong the service life of the elevators, reduce the waiting time for elevator passengers, and make people's life convenient on the basis of energy saving.
Description
Technical field
The present invention relates to a kind of many elevator in parallel operation based on machine vision control method for coordinating and system.
Background technology
Along with the development in city, the requirement of people to living standard improves constantly, and the intellectuality of building is important all the more.No matter be in residential quarter or at office block, elevator has become one of requisite vehicle.
And along with the increase of people's current density, can take elevator efficiently in time for the ease of people, building has multi-section elevator in parallel operation.When people are when waiting elevator, often can, simultaneously by several elevators in parallel, allow it receive instruction together to save time, which portion comes take advantage of which elevator soon.But this way is while facilitating some people, also increase the wait time of other passenger-in-elevators, and increase the wearing and tearing of elevator, the elevator life-span is reduced, and fault increases.
Therefore, be necessary the research and development carrying out many elevators coordinated operation control method in parallel and device, reduce elevator operation energy consumption, personnel's wait time to reach, increase the effect in elevator life-span.
On the other hand, along with the reduction of the cost of camera, be widely applied in building and elevator.The security monitoring being carried out elevator operation by the video image of the camera shooting inside and outside elevator is widely applied, but has not yet to see the research how adopting these video images to realize many elevator in parallel operation cooperation control aspect.
The basis realizing many elevator in parallel operation cooperation control carries out demographics discovery, present stage according to the image of the inside and outside shooting of ladder, and the process carrying out demographics based on video image has Hough loop truss algorithm, Harr method etc.But due to the video image inside and outside ladder, often visibility is low and be very easily subject to the impact of the disturbing factors such as light.In such cases, often precision is not high to adopt the conventional personnel's method of counting based on video image.
Summary of the invention
The present invention is in order to solve the problem, propose a kind of many elevator in parallel operation based on machine vision control method for coordinating and system, the video image of the present invention to the pick up camera shooting inside and outside elevator carries out image procossing, adopts Hog feature extraction algorithm and two Fuzzy neural network classifiers to carry out accurate metering to the inside and outside personnel amount of ladder; Count situation according to personnel, consider each floor and wait the distance that residual capacity in terraced number, each elevator ladder and distance wait terraced position, adopt traffic signal coordination to run elevator and dispatch, realize most ViewSonic ladder, reduce elevator energy consumption and wearing and tearing; Communicated by CAN, realize the coordination of many elevator in parallel operation, make elevator Effec-tive Function at any time.
To achieve these goals, the present invention adopts following technical scheme:
Based on many elevator in parallel operation control method for coordinating of machine vision, comprise the following steps:
(1) image of camera collection inside and outside elevator is converted into gray-scale map, carries out binary conversion treatment, and carry out HOG feature extraction;
(2) according to obtaining characteristics of human body's sample, construct two Fuzzy neural classifiers, utilize the two Fuzzy neural classifiers trained to adjudicate the two-value that it carries out head and non-head, the human body ruled out by segregator carries out statistics and is added, and draws the inside and outside number of ladder;
(3) by the demographics inside and outside elevator, consider each floor and wait residual capacity and the terraced position of distance time in terraced number, each elevator ladder, adopt traffic signal coordination to run elevator and dispatch;
(4) communicate, realize the coordination that elevator runs.
In described step (1), concrete grammar is: first the coloured picture of camera shooting inside and outside elevator is transformed into gray-scale map, and adopts Gamma correction method to carry out normalisation; The basis of gray-scale map calculates each pixel gradient magnitude and gradient direction to catch profile information, original image is divided into cell factory, adds up the histogram of each cell factory; Cell factory is combined into large block, normalized gradient histogram in block; Histogram vectors in all pieces is combined into a large Hog proper vector.
The concrete grammar of described step (1) is: first the coloured picture of camera shooting inside and outside elevator is transformed into gray-scale map, and adopts Gamma correction method to carry out normalisation; The basis of gray-scale map calculates each pixel (x, y) place gradient magnitude
And gradient direction
catch profile information, wherein H (x, y) represents the pixel value at pixel (x, y) place in input picture respectively; Original image is divided into cell factory, adds up the histogram of each cell factory; Cell factory is combined into large block, normalized gradient histogram in block; Histogram vectors in all pieces is combined into a large Hog proper vector, just obtains all feature X=(x of human body head and non-head
1, x
2... x
n)
t, for for the classification learning of two Fuzzy neural classifiers to human body head and non-head.
In described step (2), concrete grammar comprises:
(2-1) training sample set with the number of people and inhuman labeling head is chosen;
(2-2) parameter of stochastic generation two Fuzzy subordinate function layer, and according to the output matrix of training sample set computation rule layer;
(2-3) optimal value that the interval weight vectorial sum training sample set arranging rules layer and output layer is estimated, exports the input/output model of two Fuzzy neural classifiers.
In described step (2-1), choose one with the training sample set of the number of people and inhuman labeling head, be designated as
wherein X
i=(x
i1, x
i2... x
in)
tbe i-th sample characteristics, t
i{ 0,1}, 1 is expressed as number of people profile to ∈, and 0 is that inhuman great wheel is wide, and the class label of N number of sample is combined into a vector T=[t
1..., t
n]
t.
In described step (2-2), the parameter of stochastic generation two Fuzzy subordinate function layer, and according to the output matrix of training sample set computation rule layer:
Wherein
k=1 ..., M,
with
be respectively the kth type-2 fuzzy sets divided for a jth feature to close
subordinate function up and down.
In described step (2-3), the interval weight vector of rules layer and output layer is
estimate that the optimal value of β is according to training sample set
wherein H
+for the Moore-Penrose generalized inverse matrix of output matrix H, can to human body head and non-head feature X=(x
1, x
2... x
n)
tthe input/output model realizing two Fuzzy neural classifiers of classification is
In described step (3), its concrete grammar is:
(3-1) mark the running state of every layer and each elevator, add up number and the residual capacity of each elevator and each floor in building;
(3-2) obtain the essential state data of current elevator, according to elevator operation, the inside and outside demographics of ladder and residual capacity coordinate group's ladder.
Described step (3-1) is specially: the floor that can run is N layer altogether, and elevator number is S, and the basic status of elevator i is (k
i, O
i, F
i), wherein F
ifor elevator i place floor, k
i{ 1,0 ,-1} is running state to ∈, and 1 represents ascending for elevator, and 0 represents elevator parking, and-1 represents that elevator is descending, O
i=U
i-E
ifor residual capacity, E wherein
iexisting number in the ladder that obtained by NI Vision Builder for Automated Inspection, U
ifor elevator i maximum capacity, floor F
jessential state data be (K
j, E
j), wherein E
jthat this layer waits terraced number, K
jfor terraced state set waited by this floor, for
in one, 1 indicates that personnel are up, and-1 indicates personnel descending.
In described step (3-2), its concrete grammar is: according to all elevator operations, and each floor is waited terraced number etc. and carried out coordination group ladder, and send ladder for elevator i, (1) is if now O
i=U
i, in elevator, unmanned boarding, makes k
i=0, namely elevator is out of service; If detect, upward signal makes k
i=1, if downgoing signal detected, make k
i=-1, elevator brings into operation; If O
i≠ U
i, elevator is now in running state; When elevator i runs, according to k
i∈ K
jwhether, determine the time ladder floor with its up-downgoing state consistency, and select the floor F nearest with it
j, wait terraced number E by this floor
jjudge whether further to send elevator i to this floor;
(2) supposition is to floor F
jsend elevator i
1', i
2' ... i
m', if send terraced quantity inadequate, namely satisfy condition
and
time then send elevator i to floor F
j; Returning step (1) continuation execution after sending ladder, when sending enough elevator i
1', i'
2... i'
mto floor F
jtime, if F
jbe top of building N-1 layer or bottom layer second from the bottom, elevator then returns step (1) to be continued to perform; Otherwise at K
jmiddle rejecting k
iafter proceed optimizing next time.
In described step (4), elevator main controller is positioned at elevator(lift) machine room, receive the video image information in each floor, car, floor controller is installed near the elevator panel of each floor, floor controller is by CAN and master controller communication, the group's ladder order receiving master controller is responsible for by floor controller, controls group's ladder, completes calling elevator.
Based on many elevator in parallel operation coordinated control system of said method, comprise camera system, Hog characteristic extracting module, the inside and outside personnel's counting module of ladder, multi-parallel elevator intelligent send terraced module, based on the communication module of CAN and apparatus for controlling elevator;
Wherein, described camera system comprises multiple camera, and camera is installed in elevator and every floor lift port respectively, and collector's information transmission is to Hog characteristic extracting module;
Described Hog characteristic extracting module, for utilizing Hog feature extraction algorithm to extract HOG feature as descriptor, draws the proper vector of Description Image;
Personnel's counting module inside and outside described ladder, for building and training two Fuzzy neural network classifiers, utilizes the segregator trained to identify head and non-head image, counts the inside and outside number of ladder;
Described multi-parallel elevator intelligent sends terraced module, for counting situation according to personnel, consider the distance that each floor waits residual capacity and the terraced position of distance time in terraced number, each elevator ladder, adopt traffic signal coordination to run elevator to dispatch, terraced command realizes most ViewSonic ladder, by will be sent to apparatus for controlling elevator based on the communication module of CAN;
Described apparatus for controlling elevator, for performing the elevator operating instruction that multi-parallel elevator intelligent sends terraced module to be assigned, controls the operation of elevator.
Beneficial effect of the present invention is:
(1) the present invention proposes a kind of method of new accurate metering, by the Hog feature extraction algorithm in machine learning and two Fuzzy neural network classifiers, accurate metering has been carried out to the inside and outside personnel amount of ladder;
(2) situation is counted according to personnel, when waiting terraced personnel and pressing pectus elevator, the distance of residual capacity and the terraced position of distance time in terraced number, each elevator ladder waited by master controller by considering each floor, adopt traffic signal coordination to run elevator to dispatch, realize most ViewSonic ladder, reduce elevator energy consumption and wearing and tearing, save the wait time of people;
(3) communicated by CAN, realize the coordination of many elevator in parallel operation, send terraced realizing circuit to be connected in parallel with floor panel button due to of the present invention; The two can realize the group's ladder application to elevator; Control policy of the present invention does not affect the operation of original elevator.
Accompanying drawing explanation
Fig. 1 is of the present invention based on machine vision two Fuzzy neural network classifier schematic diagram;
Fig. 2 is two Fuzzy neural network schematic diagrams of the present invention;
Fig. 3 is that terraced diagram of circuit is sent in coordination of the present invention;
Fig. 4 is that intelligence of the present invention sends terraced control topology figure;
Fig. 5 of the present inventionly sends terraced realizing circuit figure;
Fig. 6 is the present invention and floor panel interface circuitry schematic diagram;
Fig. 7 is multi-parallel elevator operational system general diagram of the present invention.
Detailed description of the invention:
Below in conjunction with accompanying drawing and embodiment, the invention will be further described.
As shown in Figure 7, a kind of building many elevator in parallel operation control method for coordinating based on machine vision and device, having carried out a large amount of improvement to elevator paired running technology before, is the Inheritance& development to it.The video image of this invention to the pick up camera shooting inside and outside elevator carries out image procossing, adopts Hog feature extraction algorithm and two Fuzzy neural network classifiers to carry out accurate metering to the inside and outside personnel amount of ladder; Count situation according to personnel, consider each floor and wait the distance that residual capacity in terraced number, each elevator ladder and distance wait terraced position, adopt traffic signal coordination to run elevator and dispatch, realize most ViewSonic ladder, reduce elevator energy consumption and wearing and tearing; Communicated by CAN, realize the coordination of many elevator in parallel operation, make elevator Effec-tive Function at any time.
For realizing building many elevator in parallel operation cooperation control, the present invention is mainly based on following three modules:
Module 1: based on personnel's counting module inside and outside the ladder of Hog feature extraction algorithm and two Fuzzy neural network classifiers
In ladder and above every floor lift port, camera is installed, according to the video image that camera collection arrives, Hog feature extraction algorithm is utilized to extract HOG feature as descriptor, draw the proper vector of Description Image, then two Fuzzy neural network classifiers are trained, and identify head and non-head image with the segregator trained, count the inside and outside number of ladder.Algorithm is specific as follows:
1, the step of personnel HOG feature extraction inside and outside elevator:
First the coloured picture of camera shooting inside and outside elevator is transformed into gray-scale map, and adopts Gamma correction method to carry out normalisation; The basis of gray-scale map calculates each pixel (x, y) place gradient magnitude
And gradient direction
catch profile information, wherein H (x, y) represents the pixel value at pixel (x, y) place in input picture respectively; Original image is divided into cell factory, adds up the histogram of each cell factory; Cell factory is combined into large block, normalized gradient histogram in block; Histogram vectors in all pieces is combined into a large Hog proper vector, just obtains all feature X=(x of human body head and non-head
1, x
2... x
n)
t, for for the classification learning of two Fuzzy neural classifiers to human body head and non-head.
, illustrate as outline, the one selection that standardization setting is technical personnel is carried out in use Gamma correction method, and obviously, on basic correction method choice, those skilled in the art does not need pay creative work and complete corresponding conversion meanwhile.
2, according to the sample with the number of people and inhuman labeling head, the structure of two Fuzzy neural classifiers is carried out:
Two Fuzzy neural classifiers adopt the identification of the two Fuzzy neural fusion numbers of people and non-number of people sample, this segregator structure as shown in Figure 1, be made up of input layer, two Fuzzy subordinate function layers, rules layer and output layer four layers altogether, effectively in conjunction with the ability of two fuzzy systems anti-noise jammings and the self-learning capability of neural network, the classification results of superior performance can be obtained.
Adopt following method structure for two Fuzzy neural classifiers of the classify number of people and the non-number of people:
(1) first, choose one with the training sample set of the number of people and inhuman labeling head, be designated as
wherein X
i=(x
i1, x
i2... x
in)
tbe i-th sample characteristics, t
i{ 0,1}, 1 is expressed as number of people profile to ∈, and 0 is that inhuman great wheel is wide.The class label of N number of sample is combined into a vector T=[t
1..., t
n]
t;
(2) parameter of stochastic generation two Fuzzy subordinate function layer, and according to the output matrix of training sample set computation rule layer
Wherein
k=1 ..., M,
with
be respectively the kth type-2 fuzzy sets divided for a jth feature to close
subordinate function up and down.
(3) the interval weight vector of rules layer and output layer is
estimate that the optimal value of β is according to training sample set
wherein H
+for the Moore-Penrose generalized inverse matrix of output matrix H.
(4) thus, can to human body head and non-head feature X=(x
1, x
2... x
n)
tthe input/output model realizing two Fuzzy neural classifiers of classification is
3, count.Video image input inside and outside the ladder that camera is taken, covered in image by the rectangular window less than image to be detected and constantly slide, extract the proper vector of overlay area pixel, the two Fuzzy neural classifiers trained are utilized to adjudicate the two-value that it carries out head and non-head, the human body ruled out by segregator carries out statistics and is added, and draws the inside and outside number of ladder.
Module 2: the multi-parallel elevator intelligent based on machine vision sends terraced module
This module counts situation according to personnel, considers each floor and waits the distance that residual capacity in terraced number, each elevator ladder and distance wait terraced position, adopt traffic signal coordination to run elevator and dispatch, and realizes most ViewSonic ladder, reduces elevator energy consumption and wearing and tearing.
Suppose the floor N layer altogether that building elevator can run, elevator number is S.The basic status of elevator i is (k
i, O
i, F
i), wherein F
ifor elevator i place floor, k
i{ 1,0 ,-1} is running state to ∈, and 1 represents ascending for elevator, and 0 represents elevator parking, and-1 represents that elevator is descending, O
i=U
i-E
ifor residual capacity, E wherein
iexisting number in the ladder that obtained by NI Vision Builder for Automated Inspection in module 1, U
ifor elevator i maximum capacity.Floor F
jessential state data be (K
j, E
j), wherein E
jthat this layer waits terraced number, K
jfor terraced state set waited by this floor, for
in one, 1 indicates that personnel are up, and-1 indicates personnel descending.
According to all elevator operations, each floor is waited terraced number etc. and is carried out coordination group ladder.Send ladder for elevator i, specific algorithm is as follows:
Obtain the current essential state data { k of elevator i
i, O
i, F
i.
(1) if now O
i=U
i, in elevator, unmanned boarding, makes k
i=0, namely elevator is out of service; If detect, upward signal makes k
i=1, if downgoing signal detected, make k
i=-1, elevator brings into operation.If O
i≠ U
i, elevator is now in running state.When elevator i runs, according to k
i∈ K
jwhether, determine the time ladder floor with its up-downgoing state consistency, and select the floor F nearest with it
j, calculate this floor by machine vision module and wait terraced number E
jjudge whether further to send elevator i to this floor.
(2) by with master controller communication, assuming that to floor F
jsend elevator i
1', i'
2... i'
mif send terraced quantity inadequate, namely satisfy condition
and
time then send elevator i to floor F
j.Main program continuation execution is being returned after sending ladder.When sending enough elevator i
1', i'
2... i'
mto floor F
jtime, if F
jbe top of building N-1 layer or bottom layer second from the bottom, elevator then returns main program to be continued to perform; Otherwise at K
jmiddle rejecting k
iafter proceed optimizing next time.
Meanwhile, Ying Zhi, utilizes the conversion of other condition modes, as running state use a, b, c} represent, and etc. the exchange of simple status data phraseology, should belong to that those skilled in the art easily expect.
Module 3: based on the communication-cooperation of CAN
The intelligence based on machine vision that this module is used for realizing proposing sends terraced hardware circuit.
Intelligence sends terraced system mainly to comprise master controller, floor controller, send terraced realizing circuit and CAN.Elevator main controller is positioned at elevator(lift) machine room, receives the video image information in each floor, car, through algorithm statistical analysis intelligent coordinated group ladder.Floor controller is installed near the elevator panel of each floor.Floor controller is by CAN and master controller communication.
The overall topological structure of intelligence group ladder as shown in Figure 4.
Simultaneously, Ying Zhi, in existing elevator controlling mode, using circuit drives to control is one of them, therefore, be understandable that, use control circuit to control elevator just a kind of selection here, and other are selected, comprise software program controls, Control, PLC control, Single-chip Controlling etc. be the alternative that those skilled in the art easily expect.
The group's ladder order receiving master controller is responsible for by floor controller, controls to send ladder to realize hardware circuit, completes calling elevator.
Being implemented as of intelligence group's ladder:
Such as, after the ladder order of a certain floor group assigned by master controller, the floor controller of corresponding floor receives order, and export high level to port Port1, relay adhesive, S1 closes.Complete a call request.
Floor controller realizes the hardware circuit of group's ladder as shown in Figure 5.This circuit drives two parts to form by Phototube Coupling, relay.After master controller is assigned and sent terraced instruction, floor controller PORT port exports high level, relay closes.Complete once group's ladder application.This circuit employs photoelectric isolation method, eliminates the impact of on-the-spot interference on floor controller preferably.Terraced instruction can be sent by actv. execution master controller.
The button of relay contact S1 and floor panel is connected in parallel.Call application of the present invention can be realized by the closed of S1.After taking this mode, control of the present invention does not affect the operation of original electric life controller, can realize calling out elevator.Namely the paired running that control method of the present invention and the original controller of elevator can be good.Relay contacts is connected as shown in Figure 6 with floor panel button.
By reference to the accompanying drawings the specific embodiment of the present invention is described although above-mentioned; but not limiting the scope of the invention; one of ordinary skill in the art should be understood that; on the basis of technical scheme of the present invention, those skilled in the art do not need to pay various amendment or distortion that creative work can make still within protection scope of the present invention.
Claims (10)
1., based on many elevator in parallel operation control method for coordinating of machine vision, it is characterized in that: comprise the following steps:
(1) image of camera collection inside and outside elevator is converted into gray-scale map, carries out binary conversion treatment, and carry out HOG feature extraction;
(2) according to obtaining characteristics of human body's sample, construct two Fuzzy neural classifiers, utilize the two Fuzzy neural classifiers trained to adjudicate the two-value that it carries out head and non-head, the human body ruled out by segregator carries out statistics and is added, and draws the inside and outside number of ladder;
(3) by the demographics inside and outside elevator, consider each floor and wait residual capacity and the terraced position of distance time in terraced number, each elevator ladder, adopt traffic signal coordination to run elevator and dispatch;
(4) communicate, realize the coordination that elevator runs.
2. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 1, it is characterized in that: in described step (1), step comprises: first the coloured picture of camera shooting inside and outside elevator is transformed into gray-scale map, and adopts Gamma correction method to carry out normalisation; The basis of gray-scale map calculates each pixel gradient magnitude and gradient direction to catch profile information, original image is divided into cell factory, adds up the histogram of each cell factory; Cell factory is combined into large block, normalized gradient histogram in block; Histogram vectors in all pieces is combined into a large Hog proper vector.
3. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 1, it is characterized in that: the concrete grammar of described step (1) is: first the coloured picture of camera shooting inside and outside elevator is transformed into gray-scale map, and adopts Gamma correction method to carry out normalisation; The basis of gray-scale map calculates each pixel (x, y) place gradient magnitude
And gradient direction
catch profile information, wherein H (x, y) represents the pixel value at pixel (x, y) place in input picture respectively; Original image is divided into cell factory, adds up the histogram of each cell factory; Cell factory is combined into large block, normalized gradient histogram in block; Histogram vectors in all pieces is combined into a large Hog proper vector, just obtains all feature X=(x of human body head and non-head
1, x
2... x
n)
t, for for the classification learning of two Fuzzy neural classifiers to human body head and non-head.
4. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 1, is characterized in that: in described step (2), concrete grammar comprises:
(2-1) training sample set with the number of people and inhuman labeling head is chosen;
(2-2) parameter of stochastic generation two Fuzzy subordinate function layer, and according to the output matrix of training sample set computation rule layer;
(2-3) optimal value that the interval weight vectorial sum training sample set arranging rules layer and output layer is estimated, exports the input/output model of two Fuzzy neural classifiers.
5. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 4, is characterized in that: in described step (2-1), chooses one with the training sample set of the number of people and inhuman labeling head, is designated as
wherein X
i=(x
i1, x
i2... x
in)
tbe i-th sample characteristics, t
i{ 0,1}, 1 is expressed as number of people profile to ∈, and 0 is that inhuman great wheel is wide, and the class label of N number of sample is combined into a vector T=[t
1..., t
n]
t.
6. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 4, it is characterized in that: in described step (2-2), the parameter of stochastic generation two Fuzzy subordinate function layer, and according to the output matrix of training sample set computation rule layer:
Wherein
k=1 ..., M,
with
be respectively the kth type-2 fuzzy sets divided for a jth feature to close
subordinate function up and down.
7. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 4, it is characterized in that: in described step (2-3), the interval weight vector of rules layer and output layer is
estimate that the optimal value of β is according to training sample set
wherein H
+for the Moore-Penrose generalized inverse matrix of output matrix H, can to human body head and non-head feature X=(x
1, x
2... x
n)
tthe input/output model realizing two Fuzzy neural classifiers of classification is
8. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 1, is characterized in that: in described step (3), its concrete grammar is:
(3-1) mark the running state of every layer and each elevator, add up number and the residual capacity of each elevator and each floor in building;
(3-2) obtain the essential state data of current elevator, according to elevator operation, the inside and outside demographics of ladder and residual capacity coordinate group's ladder.
9. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 8, is characterized in that: described step (3-1) is specially: the floor that can run is N layer altogether, and elevator number is S, and the basic status of elevator i is (k
i, O
i, F
i), wherein F
ifor elevator i place floor, k
i{ 1,0 ,-1} is running state to ∈, and 1 represents ascending for elevator, and 0 represents elevator parking, and-1 represents that elevator is descending, O
i=U
i-E
ifor residual capacity, E wherein
iexisting number in the ladder that obtained by NI Vision Builder for Automated Inspection, U
ifor elevator i maximum capacity, floor F
jessential state data be (K
j, E
j), wherein E
jthat this layer waits terraced number, K
jfor terraced state set waited by this floor, for
{ 1}, {-1}, { one in-1,1}, 1 indicates that personnel are up, and-1 indicates personnel descending.
10. a kind of control method for coordinating of many elevator in parallel operation based on machine vision as claimed in claim 8, it is characterized in that: in described step (3-2), its concrete grammar is: according to all elevator operations, each floor is waited terraced number and is carried out coordination group ladder, send ladder to elevator i, (1) is if now O
i=U
i, in elevator, unmanned boarding, makes k
i=0, namely elevator is out of service; If detect, upward signal makes k
i=1, if downgoing signal detected, make k
i=-1, elevator brings into operation; If O
i≠ U
i, elevator is now in running state; When elevator i runs, according to k
i∈ K
jwhether, determine the time ladder floor with its up-downgoing state consistency, and select the floor F nearest with it
j, wait terraced number E by this floor
jjudge whether further to send elevator i to this floor;
(2) supposition is to floor F
jsend elevator i '
1, i
2' ... i
m', if send terraced quantity inadequate, namely satisfy condition
and
time then send elevator i to floor F
j; Returning step (1) continuation execution after sending ladder, when sending enough elevator i '
1, i '
2... i '
mto floor F
jtime, if F
jbe top of building N-1 layer or bottom layer second from the bottom, elevator then returns step (1) to be continued to perform; Otherwise at K
jmiddle rejecting k
iafter proceed optimizing next time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510279503.1A CN104961009B (en) | 2015-05-27 | 2015-05-27 | Many elevator in parallel operation control method for coordinating based on machine vision and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510279503.1A CN104961009B (en) | 2015-05-27 | 2015-05-27 | Many elevator in parallel operation control method for coordinating based on machine vision and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104961009A true CN104961009A (en) | 2015-10-07 |
CN104961009B CN104961009B (en) | 2016-10-05 |
Family
ID=54215145
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510279503.1A Active CN104961009B (en) | 2015-05-27 | 2015-05-27 | Many elevator in parallel operation control method for coordinating based on machine vision and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104961009B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106241533A (en) * | 2016-06-28 | 2016-12-21 | 西安特种设备检验检测院 | Elevator occupant's comprehensive safety intelligent control method based on machine vision |
CN106241534A (en) * | 2016-06-28 | 2016-12-21 | 西安特种设备检验检测院 | Many people boarding abnormal movement intelligent control method |
CN106976766A (en) * | 2016-08-23 | 2017-07-25 | 深圳达实智能股份有限公司 | Elevator sends method and device with charge free |
CN107273852A (en) * | 2017-06-16 | 2017-10-20 | 华南理工大学 | Escalator floor plates object and passenger behavior detection algorithm based on machine vision |
CN108217352A (en) * | 2018-01-19 | 2018-06-29 | 深圳禾思众成科技有限公司 | A kind of intelligent elevator dispatches system |
CN108545561A (en) * | 2018-05-11 | 2018-09-18 | 金昱西 | elevator control method and elevator control system |
CN108657896A (en) * | 2018-06-12 | 2018-10-16 | 牛东阳 | The safety monitoring assembly of elevator rope |
CN108675071A (en) * | 2018-05-03 | 2018-10-19 | 中国科学院计算技术研究所 | High in the clouds cooperative intelligent chip based on artificial neural network processor |
CN108764468A (en) * | 2018-05-03 | 2018-11-06 | 中国科学院计算技术研究所 | Artificial neural network processor for intelligent recognition |
CN109179101A (en) * | 2018-09-07 | 2019-01-11 | 平安科技(深圳)有限公司 | Elevator control method, device, computer equipment and computer readable storage medium |
CN109626150A (en) * | 2018-11-14 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Elevator concocting method and system |
CN110040586A (en) * | 2019-04-11 | 2019-07-23 | 哈尔滨理工大学 | A kind of Elevator group control method based on recognition of face |
CN111724289A (en) * | 2020-06-24 | 2020-09-29 | 山东建筑大学 | Environmental protection equipment identification method and system based on time sequence |
CN111747247A (en) * | 2020-07-01 | 2020-10-09 | 广州赛特智能科技有限公司 | Method for robot to board elevator |
CN113697620A (en) * | 2021-09-27 | 2021-11-26 | 湖南桅灯智能科技有限公司 | Elevator group control method and device based on visual identification |
CN115303901A (en) * | 2022-08-05 | 2022-11-08 | 北京航空航天大学 | Elevator traffic flow identification method based on computer vision |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002302348A (en) * | 2001-04-04 | 2002-10-18 | Mitsubishi Electric Corp | Elevator control device |
CN101200252A (en) * | 2007-12-10 | 2008-06-18 | 中国科学院计算技术研究所 | Target place optimized dispatching method and system |
CN102126653A (en) * | 2011-01-06 | 2011-07-20 | 南京航空航天大学 | Intelligent Multiple -elevator system based on vision |
-
2015
- 2015-05-27 CN CN201510279503.1A patent/CN104961009B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002302348A (en) * | 2001-04-04 | 2002-10-18 | Mitsubishi Electric Corp | Elevator control device |
CN101200252A (en) * | 2007-12-10 | 2008-06-18 | 中国科学院计算技术研究所 | Target place optimized dispatching method and system |
CN102126653A (en) * | 2011-01-06 | 2011-07-20 | 南京航空航天大学 | Intelligent Multiple -elevator system based on vision |
Non-Patent Citations (3)
Title |
---|
周柯: "基于HOG特征的图像人体检测技术的研究与实现", 《华中科技大学硕士学位论文》 * |
周迅 等: "基于HOG的电梯人数统计方法研究", 《现代计算机(专业版)》 * |
段新美: "基于图像处理的电梯轿厢内人员计数研究", 《山东建筑大学硕士学位论文》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106241534A (en) * | 2016-06-28 | 2016-12-21 | 西安特种设备检验检测院 | Many people boarding abnormal movement intelligent control method |
CN106241534B (en) * | 2016-06-28 | 2018-12-07 | 西安特种设备检验检测院 | More people's boarding abnormal movement intelligent control methods |
CN106241533A (en) * | 2016-06-28 | 2016-12-21 | 西安特种设备检验检测院 | Elevator occupant's comprehensive safety intelligent control method based on machine vision |
CN106976766B (en) * | 2016-08-23 | 2020-05-26 | 深圳达实智能股份有限公司 | Elevator dispatching method and device |
CN106976766A (en) * | 2016-08-23 | 2017-07-25 | 深圳达实智能股份有限公司 | Elevator sends method and device with charge free |
CN107273852A (en) * | 2017-06-16 | 2017-10-20 | 华南理工大学 | Escalator floor plates object and passenger behavior detection algorithm based on machine vision |
CN108217352A (en) * | 2018-01-19 | 2018-06-29 | 深圳禾思众成科技有限公司 | A kind of intelligent elevator dispatches system |
CN108675071A (en) * | 2018-05-03 | 2018-10-19 | 中国科学院计算技术研究所 | High in the clouds cooperative intelligent chip based on artificial neural network processor |
CN108764468A (en) * | 2018-05-03 | 2018-11-06 | 中国科学院计算技术研究所 | Artificial neural network processor for intelligent recognition |
CN108545561A (en) * | 2018-05-11 | 2018-09-18 | 金昱西 | elevator control method and elevator control system |
CN108545561B (en) * | 2018-05-11 | 2020-09-22 | 金昱西 | Elevator control method and elevator control system |
CN108657896A (en) * | 2018-06-12 | 2018-10-16 | 牛东阳 | The safety monitoring assembly of elevator rope |
CN109179101A (en) * | 2018-09-07 | 2019-01-11 | 平安科技(深圳)有限公司 | Elevator control method, device, computer equipment and computer readable storage medium |
CN109626150A (en) * | 2018-11-14 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Elevator concocting method and system |
CN110040586A (en) * | 2019-04-11 | 2019-07-23 | 哈尔滨理工大学 | A kind of Elevator group control method based on recognition of face |
CN111724289A (en) * | 2020-06-24 | 2020-09-29 | 山东建筑大学 | Environmental protection equipment identification method and system based on time sequence |
CN111747247A (en) * | 2020-07-01 | 2020-10-09 | 广州赛特智能科技有限公司 | Method for robot to board elevator |
CN113697620A (en) * | 2021-09-27 | 2021-11-26 | 湖南桅灯智能科技有限公司 | Elevator group control method and device based on visual identification |
CN115303901A (en) * | 2022-08-05 | 2022-11-08 | 北京航空航天大学 | Elevator traffic flow identification method based on computer vision |
CN115303901B (en) * | 2022-08-05 | 2024-03-08 | 北京航空航天大学 | Elevator traffic flow identification method based on computer vision |
Also Published As
Publication number | Publication date |
---|---|
CN104961009B (en) | 2016-10-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104961009A (en) | Multi-elevator parallel operation coordination control method and system based on machine vision | |
CN110451367B (en) | Super high-rise elevator destination layer group control system | |
CN109292579B (en) | Elevator system, image recognition method and operation control method | |
CN106553941A (en) | A kind of intelligent elevator group control method and system | |
EP0565864B1 (en) | Artificially intelligent traffic modelling and prediction system | |
CN100595121C (en) | Target place optimized dispatching method and system | |
CN107187966B (en) | A kind of multi-section elevator control method and system based on number testing result | |
CN103010874B (en) | A kind of elevator scheduling method and system | |
CN106315319A (en) | Intelligent pre-dispatching method and system for elevator | |
CN103440781A (en) | Parking lot reverse car seeking management system based on fuzzy positioning and implementation method of parking lot reverse car seeking management system | |
CN105173930A (en) | Intelligent elevator system based on mobile terminal and intelligent elevator riding method | |
CN102800212B (en) | Intelligent parking system under a kind of environment of internet of things | |
CN104284150A (en) | Smart camera autonomous coordinative tracking method and monitoring system based on road traffic monitoring | |
CN113682908A (en) | Intelligent scheduling method based on deep learning | |
CN112734101B (en) | Sharing bicycle intelligent allocation method based on vehicle demand prediction | |
CN206594817U (en) | Public transport intelligent interaction station board | |
CN109829450A (en) | A kind of building site dump truck intelligent monitoring system and monitoring and managing method | |
CN110415267A (en) | A kind of online thermal infrared target identification device of low-power consumption and working method | |
CN106933585A (en) | A kind of self-adapting multi-channel interface system of selection under distributed cloud environment | |
CN113148782A (en) | Wisdom elevator control system based on thing networking | |
CN116824482A (en) | High-precision elevator traffic pattern recognition method for target detection | |
CN101673423B (en) | Bus passenger number statistical system capable of analyzing by means of video | |
CN111785015A (en) | Public transport real-time regulation and control information system and scheduling method based on genetic algorithm | |
CN107700906B (en) | A kind of complex control system of two layers of Mechanical parking system of file | |
CN115223087A (en) | Group control elevator traffic mode identification method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20171201 Address after: 300202 Xiang year square 1-2-1004 of Dongjiang road and Neijiang Road, Hexi District, Tianjin Patentee after: The Mahdi (Tianjin) Engineering Design Institute Co. Ltd. Address before: Feng Ming Licheng District Lingang Development Zone, 250101 Ji'nan Road, Shandong Province Patentee before: Shandong Construction University |