[go: up one dir, main page]

CN117902415B - Intelligent elevator monitoring method and device based on Internet of things - Google Patents

Intelligent elevator monitoring method and device based on Internet of things Download PDF

Info

Publication number
CN117902415B
CN117902415B CN202410103138.8A CN202410103138A CN117902415B CN 117902415 B CN117902415 B CN 117902415B CN 202410103138 A CN202410103138 A CN 202410103138A CN 117902415 B CN117902415 B CN 117902415B
Authority
CN
China
Prior art keywords
elevator
passenger
passengers
image
floor
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.)
Active
Application number
CN202410103138.8A
Other languages
Chinese (zh)
Other versions
CN117902415A (en
Inventor
易民升
龙峰
王永红
杨桂婷
郑鹏
王志武
曾陈许愿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shaoyang Polytechnic
Original Assignee
Shaoyang Polytechnic
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shaoyang Polytechnic filed Critical Shaoyang Polytechnic
Priority to CN202410103138.8A priority Critical patent/CN117902415B/en
Publication of CN117902415A publication Critical patent/CN117902415A/en
Application granted granted Critical
Publication of CN117902415B publication Critical patent/CN117902415B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B1/00—Control systems of elevators in general
    • B66B1/24—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration
    • B66B1/2408—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration where the allocation of a call to an elevator car is of importance, i.e. by means of a supervisory or group controller
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B1/00—Control systems of elevators in general
    • B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
    • B66B1/3407—Setting or modification of parameters of the control system
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B1/00—Control systems of elevators in general
    • B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
    • B66B1/3415—Control system configuration and the data transmission or communication within the control system
    • B66B1/3446—Data transmission or communication within the control system
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B1/00—Control systems of elevators in general
    • B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
    • B66B1/3476—Load weighing or car passenger counting devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B1/00—Control systems of elevators in general
    • B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
    • B66B1/3492—Position or motion detectors or driving means for the detector
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
    • B66B5/02—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions
    • B66B5/14—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions in case of excessive loads
    • B66B5/145—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions in case of excessive loads electrical
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • 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
    • G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
    • B66B2201/215—Transportation capacity
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
    • B66B2201/222—Taking into account the number of passengers present in the elevator car to be allocated
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/40—Details of the change of control mode
    • B66B2201/402—Details of the change of control mode by historical, statistical or predicted traffic data, e.g. by learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Geometry (AREA)
  • Mechanical Engineering (AREA)
  • Indicating And Signalling Devices For Elevators (AREA)
  • Elevator Control (AREA)

Abstract

The invention provides an intelligent elevator monitoring method and device based on the Internet of things, and relates to the technical field of intelligent elevator monitoring based on the Internet of things, wherein the method comprises the following steps: acquiring an elevator internal image in real time; analyzing the elevator interior image to detect a location of each passenger and a volume of each passenger; monitoring the bearing weight of the elevator in real time, and acquiring the number of passengers waiting on each floor; calculating a passenger carrying plan of the elevator according to the elevator operation data, the bearing weight and the residual carrying space; and sending passenger carrying advice to passengers according to the passenger carrying plan of the elevator, and guiding the passengers to get on or off the elevator according to the passenger selecting updating plan. The intelligent elevator control system can acquire the information of passengers in the elevator in real time, realize intelligent perception of the internal condition of the elevator, is beneficial to intelligent dispatching of the elevator, can accurately monitor the real-time load of the elevator, avoid overload and improve the operation safety of the elevator.

Description

Intelligent elevator monitoring method and device based on Internet of things
Technical Field
The invention relates to the technical field of intelligent elevator monitoring based on the Internet of things, in particular to an intelligent elevator monitoring method and device based on the Internet of things.
Background
With the increase of urban high-rise buildings, the use amount of elevators is increasing. However, the traditional elevator has the problems of single monitoring and dispatching modes and low operation efficiency. The defects of the existing elevator monitoring and scheduling technology include:
The elevator internal condition cannot be monitored in real time, and the passenger quantity and distribution information cannot be acquired. The passengers can not press the buttons by themselves, intelligent scheduling can not be realized, the elevator stopping sequence can not be optimized, effective guiding of the passengers is lacked, and the elevator is not used normally, so that the operation efficiency is affected.
Disclosure of Invention
The invention aims to solve the technical problem of providing an intelligent elevator monitoring method and device based on the Internet of things, which can improve the safety, the use efficiency and the intelligent level of an elevator.
In order to solve the technical problems, the technical scheme of the invention is as follows:
in a first aspect, an intelligent elevator monitoring method based on internet of things, the method comprising:
Acquiring an elevator internal image in real time;
analyzing the elevator interior image to detect a location of each passenger and a volume of each passenger;
Monitoring the bearing weight of the elevator in real time, and acquiring the number of passengers waiting on each floor;
Calculating a passenger carrying plan of the elevator according to the elevator operation data, the bearing weight and the residual carrying space;
And sending passenger carrying advice to passengers according to the passenger carrying plan of the elevator, and guiding the passengers to get on or off the elevator according to the passenger selecting updating plan.
Further, analyzing the elevator interior image to detect a location of each passenger and a volume of each passenger, comprising:
Preprocessing the acquired image to obtain a preprocessed image;
detecting the position of each passenger in the preprocessed image according to the preprocessed image, and identifying the coordinate frame of each passenger in the preprocessed image;
extracting image features from each detected passenger coordinate frame;
Predicting the volume of each passenger according to the image characteristics and a preset volume estimation model;
and obtaining specific position coordinates and volume information of each passenger in the elevator according to the position and the predicted volume of each passenger coordinate frame.
Further, real-time monitoring elevator load weight to acquire every floor and wait for passenger number, include:
Monitoring the bearing weight of the elevator in real time through a weight sensor in the elevator;
the number of passengers waiting for taking the elevator on each floor is obtained through the number counting camera of each floor at the elevator gate, and the number counting result is associated with the floor number and is used as the waiting number data of the floor.
Further, according to the elevator operation data, the load weight and the residual load space, a passenger carrying plan of the elevator is calculated, comprising:
Acquiring real-time operation data of an elevator, wherein the real-time operation data comprise current floor, operation direction and speed parameters;
acquiring real-time load weight data of an elevator, calculating the difference between the rated load weight and the current load weight of the elevator, and determining the residual load space of the elevator;
acquiring the number of waiting passengers on each floor and the target floor of each passenger;
acquiring a service floor conforming to the running direction according to the current position and the running direction of the elevator;
Sequencing the service floors to enable the elevator to stop at the service floors according to the final route;
And predicting the number of passengers to be carried entering the elevator for each service floor, calculating the increment of the bearing weight, judging whether the residual space of the elevator can accommodate the passengers to be carried, and if not, adjusting the sequence of the service floors, and repeating the operation until a final passenger carrying plan is calculated.
Further, according to the passenger carrying plan of the elevator, a passenger carrying suggestion is sent to the passenger, and according to the passenger selection updating plan, the passenger is guided to get on or off the elevator, comprising:
A display screen is arranged at each floor elevator opening and used for issuing passenger carrying advice, and after the elevator calculates a passenger carrying plan, the passenger carrying advice of the corresponding floor is issued on the display screen;
After passengers enter the elevator, detecting the number of people actually entering the elevator and a target floor through a camera in the elevator;
And (3) acquiring the detected actual condition, if the actual condition does not accord with the plan, updating the passenger carrying plan, continuously issuing passenger carrying suggestions of each floor when the elevator stops at the floor, and adjusting the passenger carrying plan in real time through closed loop feedback and updating.
Further, detecting a position of each passenger in the preprocessed image according to the preprocessed image, and identifying a coordinate frame of each passenger in the preprocessed image, including:
Detecting all passengers in the image by using a target detection algorithm according to the preprocessed image;
Constructing a detection model, and training by using an elevator internal image to obtain a detection model for passengers;
and calculating the input preprocessed image by using the trained detection model to obtain a coordinate frame of each passenger.
Further, after giving a passenger carrying suggestion to a passenger according to the passenger carrying plan of the elevator and guiding the passenger to get on or off the elevator according to the passenger selection update plan, the elevator system further comprises:
When the elevator reaches a target floor, continuously monitoring images in the elevator, and detecting the number of passengers actually getting off the elevator and the target floor;
and comparing the number of passengers actually getting off the elevator with the passenger carrying plan, calculating the number of the passengers getting off the elevator and the number of the remaining passengers, and recalculating the passenger carrying plan of the elevator according to the updated number of the passengers in the elevator and the destination floor.
In a second aspect, an intelligent elevator monitoring device based on internet of things, comprising:
the acquisition module is used for acquiring the internal image of the elevator in real time; analyzing the elevator interior image to detect a location of each passenger and a volume of each passenger; monitoring the bearing weight of the elevator in real time, and acquiring the number of passengers waiting on each floor;
The processing module is used for calculating a passenger carrying plan of the elevator according to the elevator operation data, the bearing weight and the residual carrying space; and sending passenger carrying advice to passengers according to the passenger carrying plan of the elevator, and guiding the passengers to get on or off the elevator according to the passenger selecting updating plan.
In a third aspect, a computing device includes:
one or more processors;
And a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the above-described methods.
In a fourth aspect, a computer readable storage medium stores a program that when executed by a processor implements the above method.
The scheme of the invention at least comprises the following beneficial effects:
According to the scheme, the passenger information in the elevator can be obtained in real time, intelligent perception of the internal condition of the elevator is realized, intelligent scheduling of the elevator is facilitated, real-time load of the elevator can be accurately monitored, overload is avoided, the operation safety of the elevator is improved, an optimal passenger carrying plan of the elevator can be intelligently calculated, the passenger carrying efficiency and the operation efficiency of the elevator are improved, active guiding and interaction of passengers can be realized, passenger behaviors are standardized, misoperation is reduced, dynamic closed-loop control of the elevator can be realized through multi-source data fusion, elevator operation is continuously optimized, collaborative scheduling and optimization among multiple elevators can be realized, waiting time of the passengers is reduced, an elevator operation report can be generated, the operation efficiency is evaluated, continuous improvement is realized, the intelligent level and user experience of the elevator are improved, and the elevator is safer, more efficient and more convenient. The invention can promote the intelligent monitoring and operation level of the elevator, and make the elevator system more intelligent and humanized.
Drawings
Fig. 1 is a schematic flow chart of an intelligent elevator monitoring method based on the internet of things, which is provided by an embodiment of the invention.
Fig. 2 is a schematic diagram of an intelligent elevator monitoring device based on the internet of things, which is provided by an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described more closely below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides an intelligent elevator monitoring method based on the internet of things, where the method includes:
Step 11, acquiring an elevator internal image in real time;
Step 12, analyzing the elevator interior image to detect the position of each passenger and the volume of each passenger;
Step 13, monitoring the bearing weight of the elevator in real time, and acquiring the number of passengers waiting on each floor;
Step 14, calculating a passenger carrying plan of the elevator according to the elevator operation data, the bearing weight and the residual carrying space;
And 15, sending passenger carrying advice to passengers according to the passenger carrying plan of the elevator, and guiding the passengers to get on or off the elevator according to the passenger selecting updating plan.
In the embodiment of the invention, the passenger information in the elevator can be acquired in real time, the intelligent perception of the internal condition of the elevator is realized, the intelligent scheduling of the elevator is facilitated, the real-time load of the elevator can be accurately monitored, overload is avoided, the operation safety of the elevator is improved, the optimal passenger carrying plan of the elevator can be intelligently calculated, the passenger carrying efficiency and the operation efficiency of the elevator are improved, the active guiding and interaction of passengers can be realized, the passenger behavior is standardized, misoperation is reduced, the dynamic closed-loop control of the elevator can be realized through multi-source data fusion, the operation of the elevator is continuously optimized, the cooperative scheduling and optimization among multiple elevators can be realized, the waiting time of the passengers is reduced, the operation report of the elevator can be generated, the operation efficiency is evaluated, the continuous improvement is realized, the intelligent level and the user experience of the elevator are improved, and the elevator is safer, more efficient and more convenient. The invention can promote the intelligent monitoring and operation level of the elevator, and make the elevator system more intelligent and humanized.
In a preferred embodiment of the present invention, the step 12 may include:
step 121, preprocessing the acquired image to obtain a preprocessed image;
Step 122, detecting the position of each passenger in the preprocessed image according to the preprocessed image, and identifying the coordinate frame of each passenger in the preprocessed image;
step 123, extracting image features for each detected passenger coordinate frame;
Step 124, predicting the volume of each passenger according to the image features and a preset volume estimation model;
And step 125, obtaining specific position coordinates and volume information of each passenger in the elevator according to the position and the predicted volume of each passenger coordinate frame.
In the embodiment of the invention, the image preprocessing in step 121 can improve the image quality, the coordinate frame of each passenger in the image can be accurately positioned by utilizing the target detection algorithm in step 122, the image characteristics can be extracted in step 123, the visual information of each passenger can be captured, the characteristic input is provided for volume estimation, the volume estimation model is established in step 124, the space volume occupied by each passenger can be estimated, the position and the volume information of the coordinate frame are integrated in step 125, and the space distribution condition of each passenger in the elevator can be accurately obtained. The method has reasonable and refined sequence among the steps, is beneficial to improving the accuracy of detection and volume estimation, provides key passenger information for load calculation, space utilization evaluation and intelligent scheduling of the elevator, is beneficial to analyzing the use condition of the space in the elevator and optimizing the design in the elevator, can improve the intelligent level of elevator monitoring and operation, and greatly optimizes user experience.
In another preferred embodiment of the present invention, the step 121 may include: denoising the acquired image through I′=f(I)=w1I+w2G(I;σ1)+w3M(I;r1)+w4B(I;σ2,r2) to obtain a denoised image, wherein G represents Gaussian filtering, and sigma 1 is Gaussian kernel parameter; m represents median filtering, r 1 is the filter window size; b represents bilateral filtering, sigma 2 represents a control space Gaussian function, r 2 controls gray value similarity, I represents an original input image, w 1、w2、w3 and w 4 are weight coefficients, f represents a denoised image processing function, and I' is a processed image. By passing throughDistortion correction is performed on the processed image I' to obtain a corrected image, a ij represents affine transformation parameters, k i controls the degree of distortion, r is the image point-to-image center distance,AndThe abscissa and the ordinate after the distortion correction image are respectively, and x and y are respectively the abscissa and the ordinate of the original input image. By passing throughAnd carrying out rotation correction on the image after distortion correction, wherein θ is a rotation angle, and t x and t y are control coordinate offsets. By passing throughThe rotation corrected image is resized, where s is the scaling factor and o x and o y are the control offsets. The step 123 may include: by passing throughExtracting image features, wherein G x and G y represent image transverse and longitudinal gradients, n and m represent image block sizes, and w x and w y represent weight coefficients of the transverse and longitudinal gradients, and calculating as follows:， K represents a constant controlling the rate of weight increase, μ x and μ y represent the horizontal-longitudinal gradient mean.
In another preferred embodiment of the present invention, the step 124 may include: by extracting image featuresThe volume v of each passenger is predicted, wherein,N is the number of decision trees in the forest, h i is the output of the ith decision tree, x is the input feature vector,For the parameters of the ith decision tree, w i is the weight of the ith decision tree,As an adjustable parameter of the weight, var (h i) is the variance of the decision tree output, and b is the offset.
In another preferred embodiment of the present invention, the step 125 may include: let the coordinate frame of passenger i be (x i1,yi1,xi2,yi2) and the predicted volume be v i, then: ; the coordinate frame is expanded to encompass the whole body, ，Wherein k is the expansion coefficient; by passing throughCalculating the occupied space area; According to the occupied space areaBy means ofConstruction of a model of the spatial distribution of passengersWhere Z is a normalization factor, σ x and σ y are control distribution ranges, and by calculating the passenger position and volume distribution, and combining the coordinate frame and the predicted volume, accurate spatial information of each passenger inside the elevator can be obtained.
In a preferred embodiment of the present invention, the step 13 may include:
step 131, monitoring the bearing weight of the elevator in real time through a weight sensor in the elevator;
step 132, the number of passengers waiting for taking the elevator on each floor is obtained through the number counting camera of each floor at the elevator gate, and the number counting result is associated with the floor number and is used as the waiting number data of the floor.
In the embodiment of the invention, the real-time weight data in the elevator can be accurately obtained by monitoring the elevator load in real time through the weight sensor, overload is prevented, safety is ensured, the weight data can also be used for calculating the real-time load rate of the elevator, reasonable passenger carrying scheduling is facilitated, the waiting number of each floor is counted through the camera, the important data of the elevator service demand can be obtained, the waiting number is associated with the floor number, the service demand priority of each floor can be intuitively reflected, the weight data is combined with the waiting number, the passenger carrying capacity and the allowance of the elevator can be evaluated, the data acquisition instantaneity is good, the timely scheduling decision of the elevator is facilitated, the operation efficiency of the elevator is facilitated to be improved, and the waiting time of passengers is reduced.
In another preferred embodiment of the present invention, in step 131, the bottom plane of the elevator car is divided into a plurality of identical rectangular detection intervals, for example, divided into 9 detection intervals of 3×3, an independent high-precision electronic pressure sensor is installed at the central position of each detection interval, 9 sensors are all installed, each sensor detects the pressure component of the corresponding detection interval, the precision of the sensor selects 120% of the rated load in the coverage area, the 9 sensors are arranged in parallel, and simultaneously output respective voltage signals in real time, the amplifying circuit amplifies the synthesized total signal, the low-pass filter filters noise, the ADC is converted into digital signals, the elevator control system collects the digital signals of all the sensors, the weight component of each detection interval is calculated in proportion, the total load of the elevator is calculated according to the weight distribution of the detection interval, overload protection is performed, and meanwhile, the center of gravity balance is monitored, the multi-sensor structure can detect the load distribution, the unbalanced load is prevented, the overload area can be positioned, the reliability of the system is improved, each sensor is maintained regularly, long-term stability is ensured, and a more precise and reliable control of the weight balance of the elevator is also facilitated by the bottom multi-area detection mode.
In step 132, a high-definition camera with a face detection function is installed at the center of the top of each floor of the elevator doorway, the field of view of the camera is required to cover the whole elevator doorway area, all waiting passengers are ensured to be detected, image signals collected by the camera are processed and then input into a video analysis module, the video analysis module uses a face detection algorithm to count the number of recognized faces in real time, the number of people statistics results are packaged in a format of floor number-number, such as 5 layers-8 people, and are sent to an elevator control system, the system receives and analyzes the waiting number data of each floor and is related to an elevator operation optimization module, the sufficient light is ensured, the detection effect is maintained under the complex illumination condition, and privacy is protected by fuzzy processing. By adopting network security measures, illegal access is prevented, different crowd samples are regularly used to optimize the detection algorithm, the accuracy is improved, the system maintenance time is reasonably arranged, and reliable operation is ensured.
In a preferred embodiment of the present invention, the step 14 may include:
step 141, acquiring real-time operation data of the elevator, including current floor, operation direction and speed parameters;
step 142, acquiring real-time load bearing weight data of the elevator, calculating the difference between the rated load bearing weight and the current load bearing weight of the elevator, and determining the residual load space of the elevator;
step 143, obtaining the number of waiting passengers on each floor and the destination floor of each passenger;
Step 144, according to the current position and the running direction of the elevator, obtaining a service floor conforming to the running direction;
Step 145, sorting the service floors to enable the elevator to stop the service floors according to the final route;
Step 146, for each service floor, predicting the number of passengers to be carried entering the elevator, calculating the load weight increment, judging whether the residual elevator carrying space can accommodate the passengers to be carried, if not, adjusting the sequence of the service floors, and repeating the operation until the final passenger carrying plan is calculated.
In the embodiment of the invention, real-time operation data are acquired, the current state of the elevator is determined, a basis is provided for making a passenger carrying plan, a residual load space is calculated, the number of additional passengers which can be accommodated by the elevator is judged, overload is prevented, real-time service demand data of each floor are acquired, global waiting conditions are known, service floors conforming to the operation direction are determined, the feasibility of the plan is improved, the floors are ordered, an optimal route can be made, invalid stops are reduced, passenger carrying capacity change is predicted, the plan is dynamically adjusted, optimization is realized, multi-source data fusion is realized, all influence factors are comprehensively considered, an accurate and feasible passenger carrying plan is calculated, the passenger carrying efficiency of the elevator is improved, the energy waste is reduced, the waiting time of passengers is remarkably reduced, and the user satisfaction is improved.
In another preferred embodiment of the invention, in step 141, a laser ranging sensor is installed at the center of the top inside the elevator shaft, aligned to the inner side of the elevator shaft, for detecting the floor where the elevator is located, an encoder is installed on the elevator drive motor shaft, the running direction and speed of the elevator are detected in real time by pulse signals, and the output signals of the sensor and the encoder are amplified and filtered and then input to a signal interface of the elevator control system. The system analyzes the data of the sensor and the encoder, converts the data into three parameters of the current floor, the running direction and the speed of the elevator, compares the current floor data with the floor identification preset in an elevator hoistway, determines the specific floor number, judges whether the running direction is uplink or downlink according to the positive and negative of the pulse of the encoder, calculates the speed data by the pulse frequency of the encoder, updates the three parameters in real time, packages and sends the three parameters to an intelligent scheduling module of the elevator for use, ensures stable and reliable data acquisition and transmission, has small time delay and ensures the real-time performance of the scheduling basis.
In another preferred embodiment of the invention, in step 142, the current load weight data of the elevator is obtained in real time from the pressure sensor inside the elevator; presetting rated load capacity parameters of an elevator in an elevator control system, for example, 1000 kg; the system reads the current bearing weight of the elevator in real time, for example, 750 kg; comparing the current load bearing weight with the rated load bearing weight, and calculating the difference value of the current load bearing weight and the rated load bearing weight, namely the current residual load space of the elevator; in the example, the rated load capacity of the elevator is 1000 kg, the current load capacity is 750 kg, the residual load space is 1000-750=250 kg, the residual load space is updated in real time and is sent to the intelligent dispatching module together with the current floor and running direction parameters of the elevator, when the residual load space reaches zero, an early warning is sent to the inside of the elevator, the possible overload is prompted, the accurate and reliable load data is ensured, and the overload caused by calculation errors is avoided.
In another preferred embodiment of the present invention, in step 143, a camera is set at each elevator doorway to monitor and count the number of waiting passengers in real time, an intelligent terminal is set to provide the input and confirmation functions of the passenger's destination floor, the passenger inputs or confirms his own destination floor on the terminal, the waiting number counted by the camera in real time is related to the destination floor data summary, for example, "3-floor waiting number: 5, 2-, 5-, 7-, 10-, 15-floor" destination floors, and the summarized data packet is sent to the communication interface of the elevator control system; the system analyzes the data packet, updates the waiting number of each floor and the distribution information of the target floors, updates the information in real time, ensures to reflect the current situation, is taken as the basis for making a passenger carrying plan, periodically maintains the terminal, ensures the use experience, optimizes the input flow of the target floors, optimizes the camera statistical algorithm, and ensures the statistics accuracy of the waiting number of people.
In another preferred embodiment of the present invention, in step 144, the current floor and the running direction of the elevator are obtained from the elevator running data, and it is determined whether the running direction is up or down, if the elevator is currently in floor 5, the running direction is up, the service floor is primarily determined to be 6 floors to top floors, if the elevator is currently in floor 10, the running direction is down, the service floor is primarily determined to be 9 floors to 1 floors, and floors conforming to the running direction of the elevator are extracted from the waiting number data of all floors; and extracting the number of people waiting from 6 floors to the top floor under the ascending condition. And extracting the waiting number of the floors from 9 to 1 for the downlink condition, forming a new service floor data set by the extracted floors and the corresponding waiting number, sending the new service floor data set to a subsequent plan optimizing module, and repeating the process in real time to adapt to the change of the running direction of the elevator, so that only the floors conforming to the current running direction are selected, and the time waste caused by invalid stop of the elevator is avoided.
In another preferred embodiment of the present invention, in step 145, the waiting numbers of each service floor are analyzed to order the waiting numbers, for the floors with the same waiting numbers, the floors closer to the current floor of the elevator are preferentially considered, the predicted running time of the elevator from the current floor to each service floor is calculated, the service floors are integrally ordered according to the order of the waiting numbers first and then the running time, a service floor priority ordering result integrating the waiting numbers and the running time is obtained, the optimal parking service order of the elevator is determined according to the ordering result, the optimal running route is formed, when the real-time situation changes, the ordering calculation is re-executed, the optimal route of the elevator is dynamically updated, the passenger carrying efficiency of the elevator is improved, the waiting time of the passengers is shortened as the optimal target, the ordering algorithm is implemented in the control system, and the automatic route optimization calculation is performed.
In another preferred embodiment of the invention, in step 146, for each service floor, the number of passengers to be carried to enter the elevator is predicted based on the known waiting number, assuming an average weight of 60 kg per person, the increment of the load weight of the elevator is predicted based on the number of passengers, the increment is compared with the current spare space of the elevator, and if the increment exceeds the spare space, the passenger carrying requirement of the floor cannot be satisfied; in the service floor sequence, temporarily canceling the stop plan of the floor, recalculating the sequence of the service floor and the passenger capacity increment, and repeatedly comparing the passenger capacity increment with the residual space; and circularly executing the steps until a passenger carrying plan capable of meeting the requirements of all floors is calculated, and continuously repeating the processes to dynamically adjust when the real-time situation changes until a final feasible plan is obtained, and automatically completing passenger carrying capacity prediction and plan adjustment by an algorithm in a control system.
In a preferred embodiment of the present invention, the step 15 may include:
Step 151, setting a display screen at each floor elevator opening for issuing passenger carrying advice, and issuing the passenger carrying advice of the corresponding floor on the display screen after the elevator calculates the passenger carrying plan;
step 152, after the passengers enter the elevator, detecting the number of people actually entering the elevator and the target floor through the camera inside the elevator;
step 153, obtaining the detected actual situation, if the actual situation does not accord with the plan, updating the passenger carrying plan, when the elevator stops at each floor, continuing to issue the passenger carrying suggestion of the floor, and adjusting the passenger carrying plan in real time through closed loop feedback and updating.
In the embodiment of the invention, the passenger carrying advice is issued through the display screen, so that passengers can be effectively guided, the service efficiency of the elevator is improved, the issued passenger carrying advice is from intelligent calculation, and the waiting time of the passengers can be reduced; acquiring actual conditions through a camera, and monitoring the actual passenger carrying conditions; through the closed loop feedback adjustment plan, various abnormal conditions can be processed, the elasticity of the system is ensured, effective information interaction and cooperation with passengers are realized, the user experience is obviously improved, the plan can be updated according to the real-time condition, and the system is more intelligent instead of simply relying on a pre-static plan. The intelligent and humanized elevator system is realized on the whole, and the service quality of the elevator is greatly improved.
In another preferred embodiment of the present invention, in step 151, a small-and-medium-sized LCD display screen is disposed at the position of the doorway of each floor of the elevator, the display screen is connected to the elevator control system in a wired or wireless network, and when the elevator calculates the passenger-carrying plan and advice of the corresponding floor, the elevator is pushed to the floor display screen, and the display screen receives the instruction of the control system to display the text or graphic passenger-carrying advice of the corresponding floor. For example, "suggest 1-5 building passengers to take preferentially", "please 1 building passengers are ready", etc., the waiting number of each floor can also be displayed, so that passengers on other floors can give way, the display screen adopts clear and striking fonts and colors, the visibility of the content under various illumination conditions is ensured, if the display screen is a custom display screen, the compatibility and stability with the data interaction interface of the elevator system are ensured, the display content template is optimized, and more humanized passenger carrying guidance is provided.
In another preferred embodiment of the present invention, in step 152, 1-2 high-definition cameras are installed at the center position of the top inside the elevator to ensure the coverage of the whole elevator interior scene, the cameras collect the elevator interior image in real time and transmit to a video analysis module, when the elevator door is opened, the image is analyzed by using a human statistics algorithm to count the number of people entering the elevator, meanwhile, the identity of passengers entering the elevator is identified by using a face recognition technology, the destination floors of the passengers are determined according to the destination floor reservation information of the passengers, or an interior terminal is set to enable the passengers to verify the destination floors of the passengers, when the elevator door is closed, the actual passenger number and the destination floor information obtained by statistics are summarized, the information is transmitted to an elevator control system to be compared with a predetermined plan, and the process is repeated in real time to continuously update the actual passenger situation.
In another preferred embodiment of the present invention, in step 153, the actual passenger number detected by the internal camera and the information of the destination floor are compared with the calculated original passenger carrying plan, and if there is a difference between the actual situation and the plan, for example, the passenger actually entering a certain floor is less than the planned value, the plan needs to be updated; for the floor, increasing the passenger carrying priority thereof, giving more passenger carrying opportunities in the next round of planning, and when the elevator stops at each floor, continuing to use the display screen to issue the elevator-down suggestion of the floor; after waiting for passengers on the floor to finish boarding and disembarking, repeatedly executing passenger carrying detection of an internal camera; and (3) acquiring a new actual passenger carrying condition, recalculating and updating the whole passenger carrying plan, repeating the optimization and adjustment process until the actual passenger carrying requirements of all floors are met, continuously optimizing the plan through a closed loop feedback mechanism in the whole operation process, realizing dynamic scheduling, ensuring the instantaneity and the intelligence of a plan adjustment algorithm, and rapidly responding to various abnormal conditions.
In a preferred embodiment of the present invention, the step 122 may include:
step 1221, detecting all passengers in the image using a target detection algorithm based on the pre-processed image;
Step 1222, constructing a detection model, training by using the elevator internal image to obtain a detection model for passengers;
and 1223, calculating the input preprocessed image by using the trained detection model to obtain a coordinate frame of each passenger.
In the embodiment of the invention, all passengers in the image can be automatically identified by using a target detection algorithm, intelligent detection is realized, a more accurate passenger detection model can be obtained through data training of a specific scene, the detection precision and recall rate of the passengers can be improved by using a good detection model, the detection and positioning capability of the passengers in the elevator can be obviously improved as a whole, the accurate coordinates of each passenger in the image are obtained, and the method is the basis of analysis such as subsequent volume estimation.
In a preferred embodiment of the present invention, after the step 15, the method may further include:
Step 16, after the elevator reaches the target floor, continuing to monitor the images in the elevator, and detecting the number of passengers actually getting off the elevator and the target floor;
And 17, comparing the number of passengers actually getting off the elevator with the passenger carrying plan, calculating the number of the passengers getting off the elevator and the number of the remaining passengers, and recalculating the passenger carrying plan of the elevator according to the updated number of the passengers in the elevator and the target floor.
In the embodiment of the invention, the number of passengers actually getting off the elevator can be detected, the actual output monitoring in the closed loop process is realized, the actual number of passengers getting off the elevator is calculated, the accuracy of plan execution can be judged, the plan is recalculated by feeding back the actual number of passengers getting off the elevator, the prediction error can be corrected, the intelligent level of the system is improved, the recalculation plan can be dynamically optimized according to the latest condition instead of the dead plate execution original plan, the integrity of the closed loop control flow is realized, the continuous improvement of the system performance is facilitated, the whole elevator dispatching system is more intelligent and automatic, the accumulation of elevator operation data is facilitated, the problem diagnosis and the system optimization are carried out, and the self-monitoring and self-optimizing capabilities of the elevator are improved.
In another preferred embodiment of the present invention, the step 16 may include: let the elevator reach the destination floor at time t, the number of passengers in the car detected at time t-1 be N t−1, and the destination floor set be S t−1, then at time t: number of passengers detected on board: Where I t is the time instant image, f cnn is a convolutional neural network for detecting the number of passengers, and W n is a network parameter. Detected set of on-board passenger destination floors ，Wherein, F t is the portrait characteristic at the t time, g cnn is a convolutional neural network for identifying the target floor, and W s is a network parameter. Predicting number of passengers getting off，; Predicting a set of passenger target floors for getting off，By establishing the convolutional neural network models f cnn and g cnn, the detection and prediction accuracy of the number of passengers getting off and the target floor can be improved. The step 17 may include: let t be D t, and the target floor set be S dt, then: the calculation formula of the remaining planned passenger capacity P t' is: the calculation formula of the remaining planned target floor set S t' is P t′=Pt−Dt: s t′=St−Sdt; updating the plan ：Pt+1=f(Pt′,St′,Nt,Lt;W),St+1=g(Pt′,St′,Nt,Lt;W), according to P t 'and S t', wherein f and g are convolutional neural networks, N t,Lt is the information of the vehicle and waiting passengers at the moment t respectively, and W is a network parameter; checking the feasibility of the update plan, by establishing a detection network and an optimization network, a more intelligent closed-loop plan update can be realized. The network parameters W may be optimized by continuous learning.
As shown in fig. 2, an embodiment of the present invention further provides an intelligent elevator monitoring device 20 based on the internet of things, including:
an acquisition module 21 for acquiring an image of the interior of the elevator in real time; analyzing the elevator interior image to detect a location of each passenger and a volume of each passenger; monitoring the bearing weight of the elevator in real time, and acquiring the number of passengers waiting on each floor;
a processing module 22 for calculating a passenger carrying plan of the elevator according to the elevator operation data, the bearing weight and the residual load space; and sending passenger carrying advice to passengers according to the passenger carrying plan of the elevator, and guiding the passengers to get on or off the elevator according to the passenger selecting updating plan.
Preferably, analyzing the elevator interior image to detect the location of each passenger and the volume of each passenger comprises:
Preprocessing the acquired image to obtain a preprocessed image;
detecting the position of each passenger in the preprocessed image according to the preprocessed image, and identifying the coordinate frame of each passenger in the preprocessed image;
extracting image features from each detected passenger coordinate frame;
Predicting the volume of each passenger according to the image characteristics and a preset volume estimation model;
and obtaining specific position coordinates and volume information of each passenger in the elevator according to the position and the predicted volume of each passenger coordinate frame.
Preferably, the real-time monitoring elevator load weight to acquire the number of passengers waiting on each floor includes:
Monitoring the bearing weight of the elevator in real time through a weight sensor in the elevator;
the number of passengers waiting for taking the elevator on each floor is obtained through the number counting camera of each floor at the elevator gate, and the number counting result is associated with the floor number and is used as the waiting number data of the floor.
Preferably, calculating a passenger carrying plan of the elevator according to elevator operation data, load weight and residual load space comprises:
Acquiring real-time operation data of an elevator, wherein the real-time operation data comprise current floor, operation direction and speed parameters;
acquiring real-time load weight data of an elevator, calculating the difference between the rated load weight and the current load weight of the elevator, and determining the residual load space of the elevator;
acquiring the number of waiting passengers on each floor and the target floor of each passenger;
acquiring a service floor conforming to the running direction according to the current position and the running direction of the elevator;
Sequencing the service floors to enable the elevator to stop at the service floors according to the final route;
And predicting the number of passengers to be carried entering the elevator for each service floor, calculating the increment of the bearing weight, judging whether the residual space of the elevator can accommodate the passengers to be carried, and if not, adjusting the sequence of the service floors, and repeating the operation until a final passenger carrying plan is calculated.
Preferably, according to the passenger carrying plan of the elevator, a passenger carrying suggestion is sent to the passenger, and according to the passenger selection updating plan, the passenger is guided to get on or off the elevator, comprising:
A display screen is arranged at each floor elevator opening and used for issuing passenger carrying advice, and after the elevator calculates a passenger carrying plan, the passenger carrying advice of the corresponding floor is issued on the display screen;
After passengers enter the elevator, detecting the number of people actually entering the elevator and a target floor through a camera in the elevator;
And (3) acquiring the detected actual condition, if the actual condition does not accord with the plan, updating the passenger carrying plan, continuously issuing passenger carrying suggestions of each floor when the elevator stops at the floor, and adjusting the passenger carrying plan in real time through closed loop feedback and updating.
Preferably, detecting the position of each passenger in the preprocessed image according to the preprocessed image, and identifying the coordinate frame of each passenger in the preprocessed image, includes:
Detecting all passengers in the image by using a target detection algorithm according to the preprocessed image;
Constructing a detection model, and training by using an elevator internal image to obtain a detection model for passengers;
and calculating the input preprocessed image by using the trained detection model to obtain a coordinate frame of each passenger.
Preferably, after giving a passenger carrying suggestion to a passenger according to a passenger carrying plan of the elevator and guiding the passenger to get on or off the elevator according to a passenger selection update plan, the elevator system further comprises:
When the elevator reaches a target floor, continuously monitoring images in the elevator, and detecting the number of passengers actually getting off the elevator and the target floor;
and comparing the number of passengers actually getting off the elevator with the passenger carrying plan, calculating the number of the passengers getting off the elevator and the number of the remaining passengers, and recalculating the passenger carrying plan of the elevator according to the updated number of the passengers in the elevator and the destination floor.
It should be noted that the apparatus is an apparatus corresponding to the above method, and all implementation manners in the above method embodiment are applicable to this embodiment, so that the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.

Claims (4)

1. An intelligent elevator monitoring method based on the internet of things is characterized by comprising the following steps:
Acquiring an elevator internal image in real time;
analyzing the elevator interior image to detect a location of each passenger and a volume of each passenger;
Monitoring the bearing weight of the elevator in real time, and acquiring the number of passengers waiting on each floor;
Calculating a passenger carrying plan of the elevator according to the elevator operation data, the bearing weight and the residual carrying space;
According to the passenger carrying plan of the elevator, sending passenger carrying advice to the passengers, and according to the passenger selection updating plan, guiding the passengers to get on or off the elevator;
Analyzing the elevator interior image to detect the location of each passenger and the volume of each passenger, comprising:
Preprocessing the acquired image to obtain a preprocessed image;
detecting the position of each passenger in the preprocessed image according to the preprocessed image, and identifying the coordinate frame of each passenger in the preprocessed image;
extracting image features from each detected passenger coordinate frame;
Predicting the volume of each passenger according to the image characteristics and a preset volume estimation model;
According to the position of each passenger coordinate frame and the predicted volume, specific position coordinates and volume information of each passenger in the elevator are obtained;
Real-time supervision elevator bears weight to acquire every floor and wait for passenger number, include:
Monitoring the bearing weight of the elevator in real time through a weight sensor in the elevator;
the number of passengers waiting for taking the elevator on each floor is obtained through a passenger number counting camera of each floor at the elevator gate, and a passenger number counting result is associated with the floor number and is used as waiting number data of the floor;
According to elevator operation data, load weight and residual load space, calculating the passenger carrying plan of the elevator, comprising:
Acquiring real-time operation data of an elevator, wherein the real-time operation data comprise current floor, operation direction and speed parameters;
acquiring real-time load weight data of an elevator, calculating the difference between the rated load weight and the current load weight of the elevator, and determining the residual load space of the elevator;
acquiring the number of waiting passengers on each floor and the target floor of each passenger;
acquiring a service floor conforming to the running direction according to the current position and the running direction of the elevator;
Sequencing service floors to enable an elevator to stop the service floors according to a final route, and specifically comprising the following steps: analyzing the waiting numbers of each service floor to sort the waiting numbers, calculating the estimated running time of the elevator from the current floor to each service floor according to the floors corresponding to the current floor distance of the elevator for the floors with the same waiting numbers, and integrally sorting the service floors according to the sorting order of the waiting numbers before the service floors are sorted and the running time after the service floors are sorted, so as to obtain a service floor priority sorting result integrating the waiting numbers and the running time;
For each service floor, predicting the number of passengers to be carried entering the elevator, calculating the increment of the bearing weight, judging whether the residual space of the elevator can accommodate the passengers to be carried, if not, adjusting the sequence of the service floors, and repeating the operation until a final passenger carrying plan is calculated;
According to the passenger carrying plan of the elevator, sending passenger carrying advice to the passengers, and according to the passenger selection updating plan, guiding the passengers to get on and get off the elevator, comprising:
A display screen is arranged at each floor elevator opening and used for issuing passenger carrying advice, and after the elevator calculates a passenger carrying plan, the passenger carrying advice of the corresponding floor is issued on the display screen;
after the passenger gets into the elevator, through the inside camera of elevator, detect the number of people and the target floor that actually get into the elevator, specifically include: the camera collects images inside the elevator in real time and transmits the images to the video analysis module, after the elevator door is opened, the images are analyzed by using a human statistics algorithm, the number of people entering the elevator is counted, meanwhile, the identity of the passengers entering the elevator is identified by using a face recognition technology, and the corresponding target floors are determined according to the target floor reservation information of the passengers;
the detected actual situation is obtained, if the actual situation does not accord with the plan, the passenger carrying plan is updated, when the elevator stops at each floor, the passenger carrying suggestion of the floor is continuously issued, and the passenger carrying plan is adjusted in real time through closed loop feedback and updating;
detecting the position of each passenger in the preprocessed image according to the preprocessed image, and identifying the coordinate frame of each passenger in the preprocessed image, wherein the method comprises the following steps:
Detecting all passengers in the image by using a target detection algorithm according to the preprocessed image;
Constructing a detection model, and training by using an elevator internal image to obtain a detection model for passengers;
Calculating the input preprocessed image by using the trained detection model to obtain a coordinate frame of each passenger;
after giving passenger carrying advice to passengers according to the passenger carrying plan of the elevator and guiding passengers to get on or off the elevator according to the passenger selecting updating plan, the elevator system further comprises:
When the elevator reaches a target floor, continuously monitoring images in the elevator, and detecting the number of passengers actually getting off the elevator and the target floor;
Comparing the number of passengers actually getting off the elevator with the passenger carrying plan, calculating the number of the passengers getting off the elevator and the number of the remaining passengers, and recalculating the passenger carrying plan of the elevator according to the updated number of the passengers in the elevator and the target floor;
Preprocessing the acquired image to obtain a preprocessed image, including: denoising the acquired image through I′=f(I)=w1I+w2G(I;σ1)+w3M(I;r1)+w4B(I;σ2,r2) to obtain a denoised image, wherein G represents Gaussian filtering, and sigma 1 is Gaussian kernel parameter; m represents median filtering, r 1 is the filter window size; b represents bilateral filtering, sigma 2 represents a control space Gaussian function, r 2 controls gray value similarity, I represents an original input image, w 1、w2、w3 and w 4 are weight coefficients, f represents a denoising image processing function, and I' is a processed image; by passing through Distortion correction is performed on the processed image I' to obtain a corrected image, a ij represents affine transformation parameters, k i controls the degree of distortion, r is the image point-to-image center distance,AndRespectively an abscissa and an ordinate after the image is corrected for distortion, and x and y are respectively an abscissa and an ordinate of the image which is originally input; by passing throughPerforming rotation correction on the image subjected to distortion correction, wherein θ is a rotation angle, and t x and t y are control coordinate offsets; by passing throughResizing the rotation corrected image, where s is a scaling factor, o x and o y are control offsets; extracting image features for each detected passenger coordinate frame, including: by passing throughExtracting image features, wherein G x and G y represent image transverse and longitudinal gradients, n and m represent image block sizes, and w x and w y represent weight coefficients of the transverse and longitudinal gradients, and calculating as follows:， K represents a constant controlling the rate of weight increase, μ x and μ y represent the horizontal-longitudinal gradient mean; predicting the volume of each passenger according to the image features and a preset volume estimation model, wherein the method comprises the following steps: by extracting image features The volume v of each passenger is predicted, wherein,) N is the number of decision trees in the forest, h i is the output of the ith decision tree, x is the input feature vector,For the parameters of the ith decision tree, w i is the weight of the ith decision tree,As an adjustable parameter of the weight, var (h i) is the variance of the decision tree output, and b is the offset; based on the position and predicted volume of each passenger coordinate frame, obtaining the specific position coordinate and volume information of each passenger in the elevator, comprising: let the coordinate frame of passenger i be (x i1,yi1,xi2,yi2) and the predicted volume be v i, then: ; the coordinate frame is expanded to encompass the whole body, ，Wherein k is the expansion coefficient; by passing throughCalculating the occupied space area; According to the occupied space areaBy means of) Construction of a model of the spatial distribution of passengersWhere Z is a normalization factor, σ x and σ y are control distribution ranges, and by calculating the passenger position and volume distribution and combining the coordinate frame and the predicted volume, accurate spatial information of each passenger inside the elevator is obtained.
2. An intelligent elevator monitoring device based on the internet of things, which is applied to the intelligent elevator monitoring device as claimed in claim 1, and comprises:
the acquisition module is used for acquiring the internal image of the elevator in real time; analyzing the elevator interior image to detect a location of each passenger and a volume of each passenger; monitoring the bearing weight of the elevator in real time, and acquiring the number of passengers waiting on each floor;
The processing module is used for calculating a passenger carrying plan of the elevator according to the elevator operation data, the bearing weight and the residual carrying space; and sending passenger carrying advice to passengers according to the passenger carrying plan of the elevator, and guiding the passengers to get on or off the elevator according to the passenger selecting updating plan.
3. A computing device, comprising:
one or more processors;
Storage means for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the method of claim 1.
4. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to claim 1.
CN202410103138.8A 2024-01-25 2024-01-25 Intelligent elevator monitoring method and device based on Internet of things Active CN117902415B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410103138.8A CN117902415B (en) 2024-01-25 2024-01-25 Intelligent elevator monitoring method and device based on Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410103138.8A CN117902415B (en) 2024-01-25 2024-01-25 Intelligent elevator monitoring method and device based on Internet of things

Publications (2)

Publication Number Publication Date
CN117902415A CN117902415A (en) 2024-04-19
CN117902415B true CN117902415B (en) 2024-07-26

Family

ID=90692143

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410103138.8A Active CN117902415B (en) 2024-01-25 2024-01-25 Intelligent elevator monitoring method and device based on Internet of things

Country Status (1)

Country Link
CN (1) CN117902415B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118723732B (en) * 2024-09-02 2025-02-18 沃克斯迅达电梯有限公司 A distributed scheduling method and system for elevator groups based on machine learning
CN119160725B (en) * 2024-11-21 2025-02-25 兴奥数智科技有限公司 A facial recognition elevator control system for office buildings

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109678014A (en) * 2019-01-18 2019-04-26 深圳壹账通智能科技有限公司 Elevator traffic control method, apparatus, equipment and storage medium
CN110835029A (en) * 2018-08-16 2020-02-25 中国电信股份有限公司 Elevator dispatching method, control device and system
CN115108426A (en) * 2022-05-25 2022-09-27 浙江大华技术股份有限公司 Elevator control method, elevator control device, computer equipment and readable storage medium
CN115676539A (en) * 2023-01-03 2023-02-03 常熟理工学院 Coordinated scheduling method for high-rise elevators based on Internet of Things

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004345790A (en) * 2003-05-21 2004-12-09 Omron Corp Elevator control device
JP5191658B2 (en) * 2005-09-26 2013-05-08 三菱電機株式会社 Elevator control device
JP4737650B2 (en) * 2008-09-11 2011-08-03 東芝エレベータ株式会社 Operation control device for elevator system
JP2013056720A (en) * 2011-09-07 2013-03-28 Toshiba Elevator Co Ltd Elevator operation control method, and device and system for controlling elevator using the same
JP6697334B2 (en) * 2016-06-29 2020-05-20 株式会社日立製作所 Elevator system and group management control device
JP6510596B2 (en) * 2017-08-08 2019-05-08 東芝エレベータ株式会社 Elevator control system
CN112955394A (en) * 2018-11-14 2021-06-11 三菱电机株式会社 Elevator group management device
CN110040592B (en) * 2019-04-15 2020-11-20 福建省星云大数据应用服务有限公司 Elevator car passenger number detection method and system based on double-path monitoring video analysis
KR102515719B1 (en) * 2021-05-10 2023-03-31 현대엘리베이터주식회사 Vision recognition interlocking elevator control system
JP7309839B2 (en) * 2021-12-17 2023-07-18 東芝エレベータ株式会社 elevator group control system
CN114684680B (en) * 2022-03-28 2024-04-19 知鱼智联科技股份有限公司 Elevator control method and terminal
CN116281480A (en) * 2023-04-10 2023-06-23 成都睿瞳科技有限责任公司 Visual detection system, method and storage medium based on intelligent camera

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110835029A (en) * 2018-08-16 2020-02-25 中国电信股份有限公司 Elevator dispatching method, control device and system
CN109678014A (en) * 2019-01-18 2019-04-26 深圳壹账通智能科技有限公司 Elevator traffic control method, apparatus, equipment and storage medium
CN115108426A (en) * 2022-05-25 2022-09-27 浙江大华技术股份有限公司 Elevator control method, elevator control device, computer equipment and readable storage medium
CN115676539A (en) * 2023-01-03 2023-02-03 常熟理工学院 Coordinated scheduling method for high-rise elevators based on Internet of Things

Also Published As

Publication number Publication date
CN117902415A (en) 2024-04-19

Similar Documents

Publication Publication Date Title
CN117902415B (en) Intelligent elevator monitoring method and device based on Internet of things
CN111562745A (en) Intelligent control system and intelligent control method
CN105528891A (en) Traffic flow density detection method and system based on unmanned aerial vehicle monitoring
EP4089647A1 (en) Video surveillance system with crowd size estimation
CN112850396A (en) Elevator foreign matter detection method and system, computer storage medium and elevator
EP3674242A2 (en) Enhancing elevator sensor operation for improved maintenance
CN116665155B (en) Underground trackless man-vehicle getting-off early warning safety management system based on image processing technology
CN111984008A (en) Robot control method, device, terminal and storage medium
CN113044694B (en) System and method for counting number of persons in building elevator based on deep neural network
CN112698660A (en) Driving behavior visual perception device and method based on 9-axis sensor
CN110407045B (en) Method for displaying personnel distribution information in elevator and intelligent elevator system
CN214269821U (en) Elevator safe operation monitoring system based on sensor and artificial intelligence
CN118430106A (en) Smart park security monitoring method and device and electronic equipment
CN113031610A (en) Automatic prison night inspection robot system and control method thereof
CN117172970A (en) Wisdom property management platform
CN112801072B (en) A computer vision-based elevator non-leveling door opening fault identification device and method
CN113903005A (en) Big data-based smart campus security data processing system
CN114890258B (en) Intelligent speed control method and system for elevator
CN116443682A (en) An intelligent elevator control system
CN114906702A (en) Temperature control method and system for sightseeing elevator based on artificial intelligence
CN119117847B (en) Elevator lifting state monitoring method and system
CN114180427B (en) Robot, method and device for controlling robot to ride on elevator, and storage medium
JP7491204B2 (en) Monitoring system, monitoring method, monitoring device, and monitoring program
CN215833945U (en) Elevator-taking cloud charging system applied to digital elevator
CN114538234B (en) Automatic construction system and method for safe operation standard AI of big data elevator of Internet of things

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
GR01 Patent grant
GR01 Patent grant