CN116977934A - Cloud-edge combined people flow early warning control method and system - Google Patents
Cloud-edge combined people flow early warning control method and system Download PDFInfo
- Publication number
- CN116977934A CN116977934A CN202310971579.5A CN202310971579A CN116977934A CN 116977934 A CN116977934 A CN 116977934A CN 202310971579 A CN202310971579 A CN 202310971579A CN 116977934 A CN116977934 A CN 116977934A
- Authority
- CN
- China
- Prior art keywords
- module
- people flow
- traffic
- early warning
- cloud platform
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000005206 flow analysis Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 239000000779 smoke Substances 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract 1
- 238000012806 monitoring device Methods 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Computer Security & Cryptography (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a cloud-edge combined people flow early warning control method and system, which utilize an edge terminal processing device of artificial intelligence and the Internet of things technology, and can detect crowd density at each entrance position in a cluster mode in real time by combining with the use of a cloud platform, when the crowd density at a certain entrance reaches a certain value, the cloud platform is automatically reported to inform a place manager, meanwhile, the cloud platform inquires people at other entrances and exits of the place, the crowd at the entrance of the large people flow is guided to other low people flow entrances and exits in a local voice reminding mode, so that the place manager can be helped to control the crowd density in the place in a range capable of being accommodated and being convenient to evacuate, and when the crowd density exceeds a controllable range, a monitoring device can adopt an alarm action to remind the place manager and control third party equipment to be closed to limit the entrance and evacuation of the crowd, and the people flow can be led to a low-density area through the local voice reminding mode.
Description
Technical Field
The invention discloses a people flow early warning control method and system, belongs to the technical field of people flow early warning control, and particularly relates to a cloud-edge combined people flow early warning control method and system.
Background
In modern urban public places, a large number of people are very common. For example, the spring transportation and various important festival activities in China every year are thought of as people, people and sea, and crowded. Crowd crowding is particularly likely to occur in places including transportation stations, stadiums, exhibitions, office buildings, malls, and the like. Excessive crowding reduces the flow speed and transportation efficiency of normal people, and even a crowded trampling accident can happen when the crowd concentration in a certain place reaches a certain value, and the risk is increased along with the increase of the crowd concentration, so that if an effective control and management method is lacking, larger casualties can be caused at all times when an emergency happens.
Disclosure of Invention
The invention aims to: the cloud-edge combined people flow early warning control method and system are provided, and the problems are solved.
The technical scheme is as follows: a cloud-edge combined people flow early warning control system, the control system comprising:
the people flow statistics module is used for carrying out statistics, identification and quantity calibration on people in the monitoring area in real time by using the camera;
the people flow analysis module is used for analyzing the people flow increase and decrease conditions in real time and judging whether the crowd concentration exceeds the controllable range or has a trend of exceeding the controllable range of the area;
the disaster risk identification module is used for monitoring dangerous events existing in the area;
the multi-device linkage module is used for mutually inquiring people flow statistics and analysis results among a plurality of devices;
and an alarm module: the cloud platform is used for reporting an alarm to the cloud platform and sending a voice prompt to the local terminal;
and a third party control module: the device is used for sending command signals for starting, closing, switching operation modes and the like to the third party equipment;
in a further embodiment, the disaster risk identification module includes a smoke sensor, a fire sensor, and a gyro sensor for identifying whether a fire, a seismic event, or not is occurring at the location.
In a further embodiment, the control system is externally connected with a cloud platform, and the cloud platform is used for centrally managing the edge devices of the traffic early warning system of each person, receiving and displaying the alarm information of each edge device in real time.
The cloud-edge combined people flow early warning control method adopts the cloud-edge combined people flow early warning control system, and the control method comprises the following steps:
collecting a traffic image in a target area through a traffic statistics module and a traffic analysis module, and analyzing and counting the traffic;
when the people flow is too large, the alarm module sends out voice prompt of crowded people flow to the site personnel, and meanwhile reports to the cloud platform;
after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt; a multi-device linkage module and a third party control module send a query instruction to the edge devices of the traffic early warning system of other entrances and exits of the place to query traffic conditions of the corresponding entrances and exits;
in a further embodiment, the method for counting the traffic of people comprises the following specific steps:
firstly, processing an image by using a model to obtain coordinates of a person in the image;
step two, judging whether the frame is a first frame or not;
step three, if the frame is the first frame, giving the coordinates of the person to the Kalman filtering to predict the coordinates assigned id and be_count of the next step, and continuing to let the model predict the coordinates of the person of the next frame;
step four, if the frame is not the first frame, matching the coordinate predicted by the model in the previous step with the coordinate predicted by Kalman filtering;
step five, calculating IOU of people and statistical areas, filtering out IOU=1, and if the IOU <1 people approach is +1;
step six, the coordinates of the person identified by the model in the third step are transmitted to a Kalman filtering algorithm to predict the coordinates of the person in the next frame;
and seventhly, returning to the first step to acquire the coordinates of the person, and performing fourth step matching on the Kalman filtering in the sixth step and the coordinates of the person.
In a further embodiment, the draining step in the control method is as follows:
step one, a video module acquires monitoring pictures of all entrances and exits for facts, and sends continuous video frames to a traffic statistics module;
step two, after receiving the video frame, the people flow statistics module intercepts the video frame and obtains a plurality of continuous pictures, decodes the pictures, and then identifies and counts the number of human bodies in the pictures, thereby obtaining the number of human bodies in a unit time range;
and thirdly, judging whether the crowd concentration of the corresponding entrance and exit reaches the crowding standard or not by the people flow analysis module according to the preset value. If the congestion standard is met, notifying an alarm module, and if the congestion standard is not met, the step I is achieved;
step four, after receiving the signal, the alarm module sends out voice prompt of crowded people flow to the site personnel through the voice module at the site end, and meanwhile, the voice prompt is reported to the cloud platform;
step five, after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt;
step six, sending a query instruction to the edge devices of the traffic early warning system of other entrances and exits of the place through the multi-equipment linkage module, and querying traffic conditions of the corresponding entrances and exits;
if the traffic of other entrances and exits is crowded, reporting the cloud platform, and sending an alarm to inform a site manager of manual intervention; if the traffic of other entrances and exits does not reach the congestion standard or is idle, sending an instruction to a traffic early warning system edge device corresponding to the congestion event;
step seven, the edge device of the traffic early warning system corresponding to the occurrence of the crowding event guides the traffic to other entrances and exits without occurrence of traffic crowding through a local voice reminding mode; and meanwhile, a third party control module is called to send a closing instruction to other equipment at the entrance and exit where the crowding event occurs, so that new crowds are prevented from continuously rushing into the entrance and exit where the crowding event occurs.
In a further embodiment, the control method includes the following steps:
step one, a video module acquires monitoring pictures of elevator cabs of all floors for facts and sends continuous video frames to a traffic statistics module;
step two, after receiving the video frame, the people flow statistics module intercepts the video frame and obtains a plurality of continuous pictures, decodes the pictures, and then identifies and counts the number of human bodies in the pictures, thereby obtaining the number of human bodies in a unit time range;
and thirdly, judging whether the crowd density of the elevator cabs of the corresponding floors reaches the crowding standard or not by the people flow analysis module according to the preset value. If the congestion standard is met, notifying an alarm module, and if the congestion standard is not met, the step I is achieved;
step four, after receiving the signal, the alarm module sends out voice prompt of crowded people flow to the site personnel through the voice module at the site end, and meanwhile, the voice prompt is reported to the cloud platform;
step five, after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt;
step six, a query instruction is sent to the people flow early warning system edge devices of other floors of the place through the multi-equipment linkage module, and people flow conditions of the elevator cabs of the corresponding floors are queried;
step seven, sorting according to the crowding condition of each floor, and calling a third party control module;
step eight, the third party control module controls to close an external elevator calling box, and passengers on all floors are forbidden to call the elevator through an external calling button;
and step nine, dispatching the elevators to more crowded floors in sequence according to the crowded conditions of all floors, and improving the crowd transportation efficiency.
In a further embodiment, the control method may monitor the dangerous event in the area according to the disaster risk identification module, and specifically includes the following steps:
step one, a smoke sensor, a fire sensor and a gyroscope sensor send data to a disaster risk identification module in real time;
step two, after receiving the data, the disaster risk identification module judges whether events such as fire, earthquake and the like occur or not through a preset data value;
if yes, notifying an alarm module; if not, returning to the step one;
step three, after receiving the signal, the alarm module sends out a disaster event voice prompt to site personnel through a voice module at the site end, and meanwhile, the alarm module reports to the cloud platform;
step four, after receiving the alarm signal, the cloud platform pops up an alarm popup window to remind a place manager to send out disaster event reminding;
step five, inquiring whether disaster events occur at other entrances and exits and floors through a multi-equipment linkage module;
and step six, controlling the third party equipment through a third party control module.
The beneficial effects are that: the patent judges whether security events such as crowding, disaster danger and the like occur at each access opening through automatic identification and reports the notification, and compared with the traditional manual judgment mode, the method is quicker and safer. By combining the application of the Internet of things display platform, the system can help place management personnel to know the people flow condition of the places in real time more intuitively and conveniently. Meanwhile, by utilizing the characteristic of quick data communication of the Internet of things, the third party equipment can be controlled immediately after a security event occurs, and the traditional processing mode is used for limiting the entry of people due to uncertainty of sensing duration of people and the need of manual intervention, and meanwhile, people cannot acquire people flow conditions of other entrances and exits at the first time. .
Drawings
FIG. 1 is a diagram of a logic architecture of the traffic early warning system of the present invention.
Fig. 2 is a flow chart of people flow statistics identification of the present invention.
Fig. 3 is an intelligent drainage flow chart of the people flow early warning system of the invention.
Fig. 4 is a flow chart of intelligent ladder assignment for the traffic early warning system of the present invention.
FIG. 5 is a flow chart of disaster identification control for the traffic early warning system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
A cloud-edge combined people flow early warning control system, as shown in figure 1, comprises: and a people flow statistics module: carrying out statistics, identification and quantity calibration on the crowd in the monitoring area in real time by using a camera; and a people flow analysis module: analyzing the condition of people flow increase and decrease in real time, and judging whether the crowd concentration exceeds the controllable range or has the trend of exceeding the controllable range of the area; disaster risk identification module: the system comprises a smoke sensor, a fire sensor and a gyroscope sensor, and is used for identifying whether events such as fire, earthquake and the like occur in a place; the multi-equipment linkage module comprises: the system is used for mutually inquiring people flow statistics and analysis results among a plurality of devices; and an alarm module: the cloud platform is used for reporting an alarm to the cloud platform and sending a voice prompt to the local terminal; and a third party control module: for use in connection with third party devices such as: the gate, the elevator, the escalator and the electric control door send instruction signals for opening, closing, switching operation modes and the like. The cloud platform is used for centrally managing the edge devices of the traffic early warning system of each person, so that place management personnel can conveniently and intensively know the conditions of each entrance and exit, and alarm information of each edge device is received and displayed in real time.
A cloud-edge combined people flow early warning control method comprises the following steps:
collecting a traffic image in a target area through a traffic statistics module and a traffic analysis module, and analyzing and counting the traffic;
when the people flow is too large, the alarm module sends out voice prompt of crowded people flow to the site personnel, and meanwhile reports to the cloud platform;
after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt; a multi-device linkage module and a third party control module send a query instruction to the edge devices of the traffic early warning system of other entrances and exits of the place to query traffic conditions of the corresponding entrances and exits;
in one embodiment, as shown in fig. 2, the method for counting the people flow comprises the following specific steps:
firstly, processing an image by using a model to obtain coordinates of a person in the image;
step two, judging whether the frame is a first frame or not;
step three, if the frame is the first frame, giving the coordinates of the person to the Kalman filtering to predict the coordinates assigned id and be_count of the next step, and continuing to let the model predict the coordinates of the person of the next frame;
step four, if the frame is not the first frame, matching the coordinate predicted by the model in the previous step with the coordinate predicted by Kalman filtering;
step five, calculating IOU of people and statistical areas, filtering out IOU=1, and if the IOU <1 people approach is +1;
step six, the coordinates of the person identified by the model in the third step are transmitted to a Kalman filtering algorithm to predict the coordinates of the person in the next frame;
and seventhly, returning to the first step to acquire the coordinates of the person, and performing fourth step matching on the Kalman filtering in the sixth step and the coordinates of the person.
In one embodiment, as shown in fig. 3, the drainage step in the control method is as follows:
step one, a video module acquires monitoring pictures of all entrances and exits for facts, and sends continuous video frames to a traffic statistics module;
step two, after receiving the video frame, the people flow statistics module intercepts the video frame and obtains a plurality of continuous pictures, decodes the pictures, and then identifies and counts the number of human bodies in the pictures, thereby obtaining the number of human bodies in a unit time range;
and thirdly, judging whether the crowd concentration of the corresponding entrance and exit reaches the crowding standard or not by the people flow analysis module according to the preset value. If the congestion standard is met, notifying an alarm module, and if the congestion standard is not met, the step I is achieved;
step four, after receiving the signal, the alarm module sends out voice prompt of crowded people flow to the site personnel through the voice module at the site end, and meanwhile, the voice prompt is reported to the cloud platform;
step five, after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt;
step six, sending a query instruction to the edge devices of the traffic early warning system of other entrances and exits of the place through the multi-equipment linkage module, and querying traffic conditions of the corresponding entrances and exits;
if the traffic of other entrances and exits is crowded, reporting the cloud platform, and sending an alarm to inform a site manager of manual intervention; if the traffic of other entrances and exits does not reach the congestion standard or is idle, sending an instruction to a traffic early warning system edge device corresponding to the congestion event;
step seven, the edge device of the traffic early warning system corresponding to the occurrence of the crowding event guides the traffic to other entrances and exits without occurrence of traffic crowding through a local voice reminding mode; and meanwhile, a third party control module is called to send a closing instruction to other equipment at the entrance and exit where the crowding event occurs, so that new crowds are prevented from continuously rushing into the entrance and exit where the crowding event occurs.
In one embodiment, as shown in fig. 4, the control method intelligently sends steps as follows:
step one, a video module acquires monitoring pictures of elevator cabs of all floors for facts and sends continuous video frames to a traffic statistics module;
step two, after receiving the video frame, the people flow statistics module intercepts the video frame and obtains a plurality of continuous pictures, decodes the pictures, and then identifies and counts the number of human bodies in the pictures, thereby obtaining the number of human bodies in a unit time range;
and thirdly, judging whether the crowd density of the elevator cabs of the corresponding floors reaches the crowding standard or not by the people flow analysis module according to the preset value. If the congestion standard is met, notifying an alarm module, and if the congestion standard is not met, the step I is achieved;
step four, after receiving the signal, the alarm module sends out voice prompt of crowded people flow to the site personnel through the voice module at the site end, and meanwhile, the voice prompt is reported to the cloud platform;
step five, after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt;
step six, a query instruction is sent to the people flow early warning system edge devices of other floors of the place through the multi-equipment linkage module, and people flow conditions of the elevator cabs of the corresponding floors are queried;
step seven, sorting according to the crowding condition of each floor, and calling a third party control module;
step eight, the third party control module controls to close an external elevator calling box, and passengers on all floors are forbidden to call the elevator through an external calling button;
and step nine, dispatching the elevators to more crowded floors in sequence according to the crowded conditions of all floors, and improving the crowd transportation efficiency.
In one embodiment, as shown in fig. 5, the control method may monitor the dangerous event in the area according to the disaster risk identification module, and specifically includes the following steps:
step one, a smoke sensor, a fire sensor and a gyroscope sensor send data to a disaster risk identification module in real time;
step two, after receiving the data, the disaster risk identification module judges whether events such as fire, earthquake and the like occur or not through a preset data value;
if yes, notifying an alarm module; if not, returning to the step one;
step three, after receiving the signal, the alarm module sends out a disaster event voice prompt to site personnel through a voice module at the site end, and meanwhile, the alarm module reports to the cloud platform;
step four, after receiving the alarm signal, the cloud platform pops up an alarm popup window to remind a place manager to send out disaster event reminding;
step five, inquiring whether disaster events occur at other entrances and exits and floors through a multi-equipment linkage module;
and step six, controlling the third party equipment through a third party control module.
In one embodiment, against the problems posed by the background, the prior art solutions are for example the issued patent numbers: CN116385974a mentions that user portraits are established for people using features such as faces and clothes, and is used for assisting people flow detection. Compared with various published patents, the invention simplifies the method for identifying the people flow, only analyzes and identifies the number of 'heads' in continuous video frames, thereby obtaining the crowd concentration in unit time. This is advantageous in reducing the computational effort requirements and costs of the edge device. In addition, the prior patent disclosed by the publication and authorized is not started from the requirement of overall management in public places like the method, the method not only reports the congestion identification result to the place manager, but also introduces a multi-equipment linkage method, and guides the flow of people to the low-concentration entrance and exit for diversion through local-end voice reminding. In addition, the third party control module can be used for quickly linking other devices in the public place and automatically controlling the crowd before the crowd manager finds out the crowd condition to manually control and dredge. Compared with other technical schemes, the invention can more effectively prevent occurrence of crowded event of people flow and more effectively inhibit trend of people flow increase in places.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the invention.
Claims (8)
1. Cloud edge combined people flow early warning control system, which is characterized in that the control system comprises:
the people flow statistics module is used for carrying out statistics, identification and quantity calibration on people in the monitoring area in real time by using the camera;
the people flow analysis module is used for analyzing the people flow increase and decrease conditions in real time and judging whether the crowd concentration exceeds the controllable range or has a trend of exceeding the controllable range of the area;
the disaster risk identification module is used for monitoring dangerous events existing in the area;
the multi-device linkage module is used for mutually inquiring people flow statistics and analysis results among a plurality of devices;
and an alarm module: the cloud platform is used for reporting an alarm to the cloud platform and sending a voice prompt to the local terminal;
and a third party control module: and the device is used for sending command signals for opening, closing, switching the operation modes and the like to the third party equipment.
2. The cloud-edge integrated traffic warning control system of claim 1, wherein the disaster risk identification module comprises a smoke sensor, a fire sensor and a gyro sensor for identifying whether a fire or earthquake event occurs in the location.
3. The cloud-edge combined people flow early warning control system of claim 1, wherein the control system is externally connected with a cloud platform, and the cloud platform is used for centrally managing the edge devices of the people flow early warning system, receiving and displaying the warning information of the edge devices in real time.
4. The cloud-edge combined people flow early warning control method is characterized by adopting the cloud-edge combined people flow early warning control system according to any one of claims 1 to 3, and the control method comprises the following steps:
collecting a traffic image in a target area through a traffic statistics module and a traffic analysis module, and analyzing and counting the traffic;
when the people flow is too large, the alarm module sends out voice prompt of crowded people flow to the site personnel, and meanwhile reports to the cloud platform;
after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt; and sending a query instruction to the edge devices of the traffic early warning system of other entrances and exits of the place through the multi-equipment linkage module and the third party control module, and querying the traffic situation of the corresponding entrance and exit.
5. The cloud-edge combined traffic early warning control method according to claim 4, characterized in that the traffic statistics method comprises the following specific steps:
firstly, processing an image by using a model to obtain coordinates of a person in the image;
step two, judging whether the frame is a first frame or not;
step three, if the frame is the first frame, giving the coordinates of the person to the Kalman filtering to predict the coordinates assigned id and be_count of the next step, and continuing to let the model predict the coordinates of the person of the next frame;
step four, if the frame is not the first frame, matching the coordinate predicted by the model in the previous step with the coordinate predicted by Kalman filtering;
step five, calculating IOU of people and statistical areas, filtering out IOU=1, and if the IOU <1 people approach is +1;
step six, the coordinates of the person identified by the model in the third step are transmitted to a Kalman filtering algorithm to predict the coordinates of the person in the next frame;
and seventhly, returning to the first step to acquire the coordinates of the person, and performing fourth step matching on the Kalman filtering in the sixth step and the coordinates of the person.
6. The cloud-edge combined people flow early warning control method according to claim 4, wherein the drainage steps in the control method are as follows:
step one, a video module acquires monitoring pictures of all entrances and exits for facts, and sends continuous video frames to a traffic statistics module;
step two, after receiving the video frame, the people flow statistics module intercepts the video frame and obtains a plurality of continuous pictures, decodes the pictures, and then identifies and counts the number of human bodies in the pictures, thereby obtaining the number of human bodies in a unit time range;
and thirdly, judging whether the crowd concentration of the corresponding entrance and exit reaches the crowding standard or not by the people flow analysis module according to the preset value. If the congestion standard is met, notifying an alarm module, and if the congestion standard is not met, the step I is achieved;
step four, after receiving the signal, the alarm module sends out voice prompt of crowded people flow to the site personnel through the voice module at the site end, and meanwhile, the voice prompt is reported to the cloud platform;
step five, after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt;
step six, sending a query instruction to the edge devices of the traffic early warning system of other entrances and exits of the place through the multi-equipment linkage module, and querying traffic conditions of the corresponding entrances and exits;
if the traffic of other entrances and exits is crowded, reporting the cloud platform, and sending an alarm to inform a site manager of manual intervention; if the traffic of other entrances and exits does not reach the congestion standard or is idle, sending an instruction to a traffic early warning system edge device corresponding to the congestion event;
step seven, the edge device of the traffic early warning system corresponding to the occurrence of the crowding event guides the traffic to other entrances and exits without occurrence of traffic crowding through a local voice reminding mode; and meanwhile, a third party control module is called to send a closing instruction to other equipment at the entrance and exit where the crowding event occurs, so that new crowds are prevented from continuously rushing into the entrance and exit where the crowding event occurs.
7. The cloud-edge combined people flow early warning control method according to claim 4, wherein the intelligent ladder sending step of the control method is as follows:
step one, a video module acquires monitoring pictures of elevator cabs of all floors for facts and sends continuous video frames to a traffic statistics module;
step two, after receiving the video frame, the people flow statistics module intercepts the video frame and obtains a plurality of continuous pictures, decodes the pictures, and then identifies and counts the number of human bodies in the pictures, thereby obtaining the number of human bodies in a unit time range;
and thirdly, judging whether the crowd density of the elevator cabs of the corresponding floors reaches the crowding standard or not by the people flow analysis module according to the preset value. If the congestion standard is met, notifying an alarm module, and if the congestion standard is not met, the step I is achieved;
step four, after receiving the signal, the alarm module sends out voice prompt of crowded people flow to the site personnel through the voice module at the site end, and meanwhile, the voice prompt is reported to the cloud platform;
step five, after receiving the signal, the cloud platform pops up an alarm popup window to remind a place manager to send out a prompt;
step six, a query instruction is sent to the people flow early warning system edge devices of other floors of the place through the multi-equipment linkage module, and people flow conditions of the elevator cabs of the corresponding floors are queried;
step seven, sorting according to the crowding condition of each floor, and calling a third party control module;
step eight, the third party control module controls to close an external elevator calling box, and passengers on all floors are forbidden to call the elevator through an external calling button;
and step nine, dispatching the elevators to more crowded floors in sequence according to the crowded conditions of all floors, and improving the crowd transportation efficiency.
8. The cloud-edge combined traffic early warning control method according to claim 4, wherein the control method can monitor dangerous events in an area according to a disaster risk identification module, and comprises the following specific steps:
step one, a smoke sensor, a fire sensor and a gyroscope sensor send data to a disaster risk identification module in real time;
step two, after receiving the data, the disaster risk identification module judges whether events such as fire, earthquake and the like occur or not through a preset data value;
if yes, notifying an alarm module; if not, returning to the step one;
step three, after receiving the signal, the alarm module sends out a disaster event voice prompt to site personnel through a voice module at the site end, and meanwhile, the alarm module reports to the cloud platform;
step four, after receiving the alarm signal, the cloud platform pops up an alarm popup window to remind a place manager to send out disaster event reminding;
step five, inquiring whether disaster events occur at other entrances and exits and floors through a multi-equipment linkage module;
and step six, controlling the third party equipment through a third party control module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310971579.5A CN116977934A (en) | 2023-08-02 | 2023-08-02 | Cloud-edge combined people flow early warning control method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310971579.5A CN116977934A (en) | 2023-08-02 | 2023-08-02 | Cloud-edge combined people flow early warning control method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116977934A true CN116977934A (en) | 2023-10-31 |
Family
ID=88472926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310971579.5A Pending CN116977934A (en) | 2023-08-02 | 2023-08-02 | Cloud-edge combined people flow early warning control method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116977934A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1031061A (en) * | 1987-08-06 | 1989-02-15 | 三菱电机株式会杜 | The group control device of elevator |
CN105000035A (en) * | 2015-06-26 | 2015-10-28 | 中交机电工程局有限公司 | Comprehensive monitoring and joint debugging system for electromechanical equipment |
CN105763853A (en) * | 2016-04-14 | 2016-07-13 | 北京中电万联科技股份有限公司 | Emergency early warning method for stampede accident in public area |
CN105787853A (en) * | 2016-04-14 | 2016-07-20 | 北京中电万联科技股份有限公司 | Public area congestion and stampede emergency early-warning system |
WO2018014873A1 (en) * | 2016-07-21 | 2018-01-25 | 深圳奇迹智慧网络有限公司 | Crowd early warning method based on mac codes and face recognition |
CN111104907A (en) * | 2019-12-20 | 2020-05-05 | 金桓毅 | Automatic gardens road bootstrap system who opens according to flow of people |
CN112541440A (en) * | 2020-12-16 | 2021-03-23 | 中电海康集团有限公司 | Subway pedestrian flow network fusion method based on video pedestrian recognition and pedestrian flow prediction method |
CN115410155A (en) * | 2022-08-31 | 2022-11-29 | 珠海数字动力科技股份有限公司 | Pedestrian flow statistical method based on multi-target tracking |
-
2023
- 2023-08-02 CN CN202310971579.5A patent/CN116977934A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1031061A (en) * | 1987-08-06 | 1989-02-15 | 三菱电机株式会杜 | The group control device of elevator |
CN105000035A (en) * | 2015-06-26 | 2015-10-28 | 中交机电工程局有限公司 | Comprehensive monitoring and joint debugging system for electromechanical equipment |
CN105763853A (en) * | 2016-04-14 | 2016-07-13 | 北京中电万联科技股份有限公司 | Emergency early warning method for stampede accident in public area |
CN105787853A (en) * | 2016-04-14 | 2016-07-20 | 北京中电万联科技股份有限公司 | Public area congestion and stampede emergency early-warning system |
WO2018014873A1 (en) * | 2016-07-21 | 2018-01-25 | 深圳奇迹智慧网络有限公司 | Crowd early warning method based on mac codes and face recognition |
CN111104907A (en) * | 2019-12-20 | 2020-05-05 | 金桓毅 | Automatic gardens road bootstrap system who opens according to flow of people |
CN112541440A (en) * | 2020-12-16 | 2021-03-23 | 中电海康集团有限公司 | Subway pedestrian flow network fusion method based on video pedestrian recognition and pedestrian flow prediction method |
CN115410155A (en) * | 2022-08-31 | 2022-11-29 | 珠海数字动力科技股份有限公司 | Pedestrian flow statistical method based on multi-target tracking |
Non-Patent Citations (3)
Title |
---|
WEIZHE LIU 等: "Estimating People Flows to Better Count Them in Crowded Scenes", ARXIV:1911.10782V4, 31 July 2020 (2020-07-31), pages 1 - 18 * |
夏菁: "城市轨道交通枢纽站客流组织优化与仿真", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, vol. 02, 15 February 2014 (2014-02-15), pages 033 - 145 * |
陈冲;白硕;黄丽达;王晓萌;刘春慧;: "基于视频分析的人群密集场所客流监控预警研究", 中国安全生产科学技术, vol. 16, no. 04, 30 April 2020 (2020-04-30), pages 143 - 148 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JPH0527920B2 (en) | ||
CN107337044B (en) | The detection method and system of elevator components failure | |
CN110304513B (en) | Risk avoiding method and device, terminal equipment and storage medium | |
CN110203803A (en) | Escalator safeguard method and device based on AI intelligent monitoring | |
CN110335437A (en) | A kind of wisdom house security system based on block chain | |
CN207209627U (en) | Troublesome monitoring system is prevented outside a kind of elevator hall | |
CN112478963A (en) | Elevator control auxiliary system and elevator control method | |
CN116977934A (en) | Cloud-edge combined people flow early warning control method and system | |
CN112203052A (en) | Security protection monitoring platform | |
CN115065812B (en) | Real-time monitoring method based on user behavior and related equipment | |
CN115367583A (en) | Elevator safety guarantee system based on edge calculation | |
CN216486694U (en) | Building falling object intelligent detection and interception system based on CPU | |
CN111768588A (en) | Intelligent online monitoring and alarming system based on fire safety | |
CN215207906U (en) | Operation monitoring system of construction elevator | |
CN207209628U (en) | Calling elevator system outside a kind of elevator hall | |
CN212933288U (en) | Safety control platform system for intelligent elevator | |
CN114281656A (en) | Intelligent central control system | |
CN109785567B (en) | Centralized prompting device for fireproof door and fireproof door system | |
KR20100000246A (en) | Security system for apartment complex and service method thereof | |
CN112837519B (en) | Alarm processing method and system | |
JPH0613393B2 (en) | Elevator monitoring control device | |
CN114655801B (en) | Elevator control method and device, computer equipment and storage medium | |
CN211630284U (en) | First floor hall security protection monitored control system | |
CN212276524U (en) | A linkage of property talkbacking for wisdom community | |
CN217787875U (en) | Community fire alarm monitoring system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |