CN113627407B - 5G emergency area crowd identification method, device and equipment - Google Patents
5G emergency area crowd identification method, device and equipment Download PDFInfo
- Publication number
- CN113627407B CN113627407B CN202111190074.2A CN202111190074A CN113627407B CN 113627407 B CN113627407 B CN 113627407B CN 202111190074 A CN202111190074 A CN 202111190074A CN 113627407 B CN113627407 B CN 113627407B
- Authority
- CN
- China
- Prior art keywords
- personnel
- emergency
- information
- area
- user
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 238000007726 management method Methods 0.000 claims abstract description 5
- 238000003066 decision tree Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract 1
- 239000000284 extract Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method, a device and equipment for identifying 5G emergency region crowd, relating to the technical field of safety management and comprising the following steps: face snapshot is carried out on a plurality of users appearing in the same area through a camera, a snapshot timestamp, a snapshot place and identity information corresponding to each face image are combined to form data records based on time-space information of each user, and user portraits are obtained through analysis according to the data records of a plurality of users; integrating all user figures in the same area, and analyzing to obtain people flow information of each area; acquiring people flow information of a corresponding accident area, and then planning an optimal emergency evacuation route scheme for personnel of the corresponding accident area; in the evacuation process, tracking the track of personnel in the accident area, carrying out clustering analysis on the set M of people falling behind based on time and space, and if the clustering characteristics are met, generating early warning information; the evacuation efficiency is effectively improved, and the safety of maintenance personnel is effectively improved.
Description
Technical Field
The invention relates to the technical field of safety management, in particular to a method, a device and equipment for identifying 5G emergency region people.
Background
With the continuous advance of the urbanization process, the population of a city is continuously increased, the travel safety problem of the population in the city is more prominent, when large-scale group-based gathering activities are held in some landmark buildings and public places of the city, a large number of people are often gathered, especially the people flow is more concentrated during holidays, the density is relatively further increased, and once an emergency happens, the serious accident of group death and group injury is very easy to occur.
At present, video monitoring technology is adopted in many public places to help security personnel to manage, but frequent pedaling events reflect that people only depend on manpower to judge the safety problem of the people, and the problem is a great burden. In addition, the crowd has the characteristics of strong mobility, uneven distribution, large shielding area and unfixed moving direction, so that the crowd monitoring video is difficult to analyze only by manpower, and therefore, a 5G emergency area crowd identification method, device and equipment are provided.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides a method, a device and equipment for identifying 5G emergency area people.
The purpose of the invention can be realized by the following technical scheme:
A5G emergency area crowd identification method comprises the following steps:
the method comprises the following steps: the method comprises the steps that a plurality of users appearing in the same area are subjected to face snapshot through a camera, the face images of the users are respectively compared with background information, and user identity information corresponding to the face images is further identified;
step two: combining the snapshot timestamp, the snapshot place and the identity information corresponding to each user face image to form a data record based on the spatio-temporal information of each user, and analyzing and acquiring the user portrait according to the data records of a plurality of users;
step three: integrating all user figures in the same area, and analyzing to obtain people flow information of each area;
step four: aiming at a specific area of a sudden emergency accident, acquiring people flow information of a corresponding accident area, and then planning an optimal emergency evacuation route scheme for personnel of the corresponding accident area;
step five: in the evacuation process, tracking the trajectory of personnel in an accident area, comparing the actual trajectory of the personnel movement with the optimal emergency evacuation route scheme, extracting personnel who do not meet evacuation characteristics to form a team-falling personnel set M, and recording team-falling information of the team-falling personnel;
step six: clustering analysis is carried out on the falling staff set M based on time and space, and if the clustering characteristics are met, early warning information is generated; and after receiving the early warning information, the emergency center sends out emergency personnel to a clustering place to evacuate and guide the personnel falling behind.
Further, the planning method of the optimal emergency evacuation route scheme comprises the following steps:
s41: collecting data of each safety exit and historical emergency evacuation route scheme data; the safety exit data comprises a safety exit position and a safety exit size;
s42: establishing an index system according to the acquired data, wherein the index system comprises index factors and samples; the index factors comprise emergency demands, evacuation distances, evacuation times and evacuation paths; the sample comprises historical emergency evacuation route plan data;
s43: on the basis of a decision tree analysis method, taking each index factor as a leaf node of a decision tree, taking a sample as a root node, respectively establishing all emergency evacuation route schemes corresponding to accident areas, calculating the occurrence probability of each node in each emergency evacuation route scheme on the basis of a decision tree C4.5 algorithm, and further calculating the information gain rate of the corresponding emergency evacuation route scheme;
s44: selecting an emergency evacuation route scheme with the highest information gain rate as an optimal emergency evacuation route scheme of the accident area, sharing the optimal emergency evacuation route scheme of the accident area to an emergency center, broadcasting the optimal emergency evacuation route scheme by the emergency center through voice, distributing emergency personnel to corresponding route nodes according to the optimal emergency evacuation route scheme, and carrying out evacuation guidance on the personnel in the accident area; wherein the route nodes are represented as routed safe exits in the emergency evacuation route scheme.
Further, the emergency demand is matched with the people flow information of the corresponding accident area in a correlation mode, the evacuation distance and the evacuation time are matched with the data of each safety exit in a correlation mode, and the evacuation path is matched with the people flow information of each area in a correlation mode.
Further, the data record comprises identity information, a snapshot timestamp and a snapshot location; the user representation comprises the age, the moving direction, the moving speed and the route track of the user; the people flow information comprises position dynamic information, people flow density and people flow quantity of each user.
Further, wherein the non-satisfaction of the evacuation feature manifests as: the deviation coefficient of the actual route track of the personnel movement relative to the optimal emergency evacuation route scheme exceeds a preset value; or simultaneously, the user stay time is longer than the preset time threshold and the moving distance is shorter than the preset space threshold.
Further, the calculation method of the deviation coefficient comprises the following steps:
v1: acquiring an actual path track of movement of personnel in an accident area, marking coordinates of a real-time position of the personnel in the accident area as (X 'i, Y' i), and marking a point (X 'i, Y' i) as a verification point;
v2: acquiring a reference point corresponding to the real-time position of personnel in an accident area in the optimal emergency evacuation route scheme, wherein the reference point acquisition criterion is that a plurality of non-coincident corresponding points with points (X 'i, Y' i) in the optimal emergency evacuation route scheme are acquired, the distance between the corresponding points and the verification points is calculated, and the corresponding point with the closest distance is marked as the reference point;
v3: marking the reference point in the optimal emergency evacuation route scheme as (Xi, Yi); i =1,.., n; wherein i represents the ith point;
using formulas
The deviation coefficient PL is calculated.
Further, carrying out clustering analysis on the falling staff set M based on time and space, and if the clustering characteristics are met, generating early warning information; the method specifically comprises the following steps:
extracting the personnel with the difference value of the queue falling time within a preset value T1 and the difference value of the queue falling position within a preset value W1 from the queue falling personnel set M to form a clustering personnel set JU;
judging whether the number of the personnel in the clustered personnel set JU is greater than a preset number threshold; if so, generating early warning information; the early warning information includes: clustering occurs time, location, and personnel information.
Further, a 5G emergency area crowd identification device includes:
an identification module: the system comprises a camera, a background information acquisition module, a display module and a display module, wherein the camera is used for capturing face images of a plurality of users appearing in the same area and respectively comparing the face images with background information, and further identifying user identity information corresponding to each face image;
a data sorting module: the face image capturing device is used for combining the capturing time stamp, the capturing place and the identity information corresponding to each face image to form a data record based on the time-space information of each user;
a data analysis module: the system comprises a data acquisition module, a data analysis module, a user portrait acquisition module, a user portrait analysis module and a user portrait management module, wherein the data acquisition module is used for acquiring user portraits according to data record analysis of a plurality of users, integrating all the user portraits in the same area and analyzing to acquire people stream flow information of each area;
a route planning module: aiming at a specific area of a sudden emergency accident, acquiring people flow information of the corresponding accident area, and then planning an optimal emergency evacuation route scheme for personnel of the corresponding accident area;
evacuation early warning module: the system is used for tracking the track of personnel in the accident area, extracting the personnel which do not meet evacuation characteristics from the track to form a fallen personnel set M, carrying out clustering analysis on the fallen personnel set M based on time and space, and generating early warning information if the clustering characteristics are met;
an emergency center: and sending out emergency personnel to the clustering place after receiving the early warning information, and evacuating and guiding the personnel falling behind.
Further, a 5G emergency area crowd identification device comprising a processor, a memory, and a computer program stored in the memory; the processor executes the computer program to execute the 5G emergency area crowd identification method.
Compared with the prior art, the invention has the beneficial effects that:
1. firstly, combining a snapshot timestamp, a snapshot place and identity information corresponding to each user face image to analyze and obtain a user portrait; integrating all user figures in the same area, and analyzing to obtain people flow information of each area; aiming at a specific region of a sudden emergency, according to people flow information of each region, based on a decision tree analysis method, taking each index factor as a leaf node of a decision tree, taking a sample as a root node, and based on a decision tree C4.5 algorithm, calculating an information gain rate corresponding to an emergency evacuation route scheme, selecting the emergency evacuation route scheme with the highest information gain rate as an optimal emergency evacuation route scheme, carrying out evacuation guidance on personnel in the accident region, improving evacuation efficiency, and maintaining personnel safety;
2. in the evacuation process, the invention extracts the personnel which do not meet the evacuation characteristics from the accident area by tracking the track of the personnel in the accident area to form a team falling personnel set M; clustering analysis is carried out on the falling staff set M based on time and space, and if the clustering characteristics are met, early warning information is generated; after receiving the early warning information, the emergency center sends out emergency personnel to the clustering place, evacuation guiding is carried out on the personnel falling behind, evacuation efficiency is improved, and personnel safety is maintained.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a 5G emergency area crowd identification method according to the present invention.
Fig. 2 is a system block diagram of a 5G emergency area crowd identification device according to the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a method for identifying 5G emergency area people includes the following steps:
the method comprises the following steps: the method comprises the steps of carrying out face snapshot on a plurality of users appearing in the same area through a camera, comparing the face image of each user obtained through face snapshot with background information respectively, and further identifying user identity information corresponding to each face image.
Step two: combining the snapshot timestamp, the snapshot place and the identity information corresponding to each user face image to form a data record based on the time-space information of each user, wherein the data record comprises the identity information, the snapshot timestamp and the snapshot place;
analyzing and acquiring a user portrait according to data records of a plurality of users; the user representation includes the user's age, direction of movement, speed of movement, and trajectory of the route.
Step three: integrating all user figures in the same area, and analyzing to obtain people stream flow information of each area, wherein the people stream flow information comprises position dynamic information, people stream density and people stream quantity of each user.
Step four: aiming at a specific area of a sudden emergency accident, acquiring people flow information of a corresponding accident area, and then planning an optimal emergency evacuation route scheme for personnel of the corresponding accident area, wherein the method specifically comprises the following steps:
s41: collecting data of each safety exit and historical emergency evacuation route scheme data; the safety exit data comprises a safety exit position and a safety exit size;
s42: establishing an index system according to the acquired data, wherein the index system comprises index factors and samples; the index factors comprise emergency demands, evacuation distances, evacuation times and evacuation paths, wherein the emergency demands are matched with the people flow information of corresponding accident areas in a correlation mode, the evacuation distances and the evacuation times are matched with the data of all safety exits in a correlation mode, the evacuation paths are matched with the people flow information of the areas in a correlation mode, and the people flow information of the areas is the people flow information of the areas; the sample comprises historical emergency evacuation route plan data;
s43: on the basis of a decision tree analysis method, taking each index factor as a leaf node of a decision tree, taking a sample as a root node, respectively establishing all emergency evacuation route schemes corresponding to accident areas, calculating the occurrence probability of each node in each emergency evacuation route scheme on the basis of a decision tree C4.5 algorithm, and further calculating the information gain rate of the corresponding emergency evacuation route scheme; wherein the nodes are represented as safe exits of the routes in the emergency evacuation route scheme;
s44: the emergency evacuation route scheme with the highest information gain rate is selected as the optimal emergency evacuation route scheme of the accident area, then the optimal emergency evacuation route scheme of the accident area is shared to an emergency center, the emergency center broadcasts the optimal emergency evacuation route scheme through voice and distributes emergency personnel to route nodes according to the optimal emergency evacuation route scheme, evacuation guidance is conducted on personnel in the accident area, evacuation efficiency is improved, and personnel safety is maintained;
in this embodiment, the method further includes: tracking the track of personnel in the accident area, extracting personnel which do not meet evacuation characteristics from the track to form a straggling personnel set M, and recording straggling information of the straggling personnel, wherein the straggling information comprises straggling time and straggling position;
wherein the non-satisfaction of the evacuation feature manifests as: the deviation coefficient of the actual route track of the personnel movement relative to the optimal emergency evacuation route scheme exceeds a preset value; or simultaneously, the user stays for a time longer than a preset time threshold and the moving distance is less than a preset space threshold;
the calculation method of the deviation coefficient comprises the following steps:
v1: acquiring an actual path track of movement of personnel in an accident area, marking coordinates of a real-time position of the personnel in the accident area as (X 'i, Y' i), and marking a point (X 'i, Y' i) as a verification point;
v2: acquiring a reference point corresponding to the real-time position of personnel in an accident area in the optimal emergency evacuation route scheme, wherein the reference point acquisition criterion is that a plurality of non-coincident corresponding points with points (X 'i, Y' i) in the optimal emergency evacuation route scheme are acquired, the distance between the corresponding points and the verification points is calculated, and the corresponding point with the closest distance is marked as the reference point;
v3: marking the reference point in the optimal emergency evacuation route scheme as (Xi, Yi); i =1,.., n; wherein i represents the ith point;
using formulas
Calculating to obtain a deviation coefficient PL;
clustering analysis is carried out on the falling staff set M based on time and space, and if the clustering characteristics are met, early warning information is generated; the method specifically comprises the following steps:
extracting the personnel with the difference value of the queue falling time within a preset value T1 and the difference value of the queue falling position within a preset value W1 from the queue falling personnel set M to form a clustering personnel set JU; and marking the queue falling time with the most occurrence times as clustering occurrence time, and marking the queue falling position with the most occurrence times as a clustering occurrence place.
In this embodiment, there may be a plurality of clustering personnel sets JU, and when the clustering personnel sets JU are generated, the number of personnel in the clustering personnel sets JU is compared with a preset number threshold.
Judging whether the number of the personnel in the clustered personnel set JU is greater than a preset number threshold; if so, generating early warning information; the early warning information includes: clustering occurs time, location, and personnel information.
And after receiving the early warning information, the emergency center sends out emergency personnel to a clustering place, and evacuates and guides the people falling behind, so that the safety of the personnel is maintained.
The method can track the actual route tracks of the persons in evacuation, extracts the persons which do not meet evacuation characteristics from the actual route tracks to form a fallen-behind person set M by combining an optimal emergency evacuation route scheme, then performs clustering analysis on the fallen-behind person set M based on time and space, generates early warning information if the clustering characteristics are met, and timely dispatches emergency persons to conduct evacuation guidance on the fallen-behind persons, so that the evacuation efficiency is improved, and the safety of the persons is maintained.
As shown in fig. 2, a 5G emergency area crowd identification device includes:
an identification module: the system comprises a camera, a background information acquisition module, a face capturing module, a background information acquisition module and a display module, wherein the camera is used for capturing faces of a plurality of users in the same area, comparing the captured face images of the users with background information respectively, and further identifying user identity information corresponding to the face images;
a data sorting module: the system comprises a snapshot time stamp, a snapshot place and identity information which correspond to each user face image, and further forms a data record based on the time-space information of each user;
a data analysis module: the system comprises a data acquisition module, a data analysis module, a user portrait acquisition module, a user portrait analysis module and a user portrait management module, wherein the data acquisition module is used for acquiring user portraits according to data record analysis of a plurality of users, integrating all the user portraits in the same area and analyzing to acquire people stream flow information of each area;
a route planning module: aiming at a specific area of a sudden emergency accident, acquiring people flow information of the corresponding accident area, and then planning an optimal emergency evacuation route scheme for personnel of the corresponding accident area;
evacuation early warning module: the system is used for tracking the track of personnel in the accident area, extracting the personnel which do not meet evacuation characteristics from the track to form a fallen team personnel set M, carrying out clustering analysis on the fallen team personnel set M based on time and space, and generating early warning information if the clustering characteristics are met;
and after receiving the early warning information, the emergency center sends out emergency personnel to a clustering place to evacuate and guide the personnel falling behind.
A 5G emergency area crowd identification device comprising a processor, a memory, and a computer program stored in the memory; the processor executes the computer program to execute the 5G emergency area crowd identification method.
The working principle of the invention is as follows:
A5G emergency region crowd identification method, device and equipment, during operation, firstly, a plurality of users appearing in the same region are subjected to face snapshot through a camera, and user identity information corresponding to each face image is identified; combining the snapshot timestamp, the snapshot place and the identity information corresponding to each user face image to form a data record based on the time-space information of each user, and analyzing and acquiring the user portrait according to the data records of a plurality of users; integrating all user figures in the same area, and analyzing to obtain people flow information of each area; aiming at a specific area of a sudden emergency accident, acquiring people flow information, safety exit data and historical emergency evacuation route scheme data of the corresponding accident area; establishing an index system according to the acquired data, respectively taking each index factor as a leaf node of a decision tree based on a decision tree analysis method, taking a sample as a root node, respectively establishing all emergency evacuation route schemes corresponding to the accident area, calculating an information gain rate of the corresponding emergency evacuation route scheme based on a decision tree C4.5 algorithm, selecting the emergency evacuation route scheme with the highest information gain rate as an optimal emergency evacuation route scheme of the accident area, then allocating emergency personnel to the corresponding route nodes, and carrying out evacuation guidance on the personnel in the accident area, thereby improving the evacuation efficiency and maintaining the safety of the personnel;
in the evacuation process, the trajectory tracking is carried out on the personnel in the accident area, and the personnel which do not meet the evacuation characteristics are extracted from the trajectory tracking to form a queue-falling personnel set M; clustering analysis is carried out on the falling staff set M based on time and space, and if the clustering characteristics are met, early warning information is generated; after receiving the early warning information, the emergency center sends out emergency personnel to the clustering place, evacuation guiding is carried out on the personnel falling behind, evacuation efficiency is improved, and personnel safety is maintained.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (3)
1. A5G emergency area crowd identification method is characterized by comprising the following steps:
the method comprises the following steps: the method comprises the steps that a plurality of users appearing in the same area are subjected to face snapshot through a camera, the face images of the users are respectively compared with background information, and user identity information corresponding to the face images is further identified;
step two: combining the snapshot timestamp, the snapshot place and the identity information corresponding to each user face image to form a data record based on the time-space information of each user, wherein the data record comprises the identity information, the snapshot timestamp and the snapshot place;
analyzing and acquiring a user portrait according to data records of a plurality of users; the user portrait comprises the age, the moving direction, the moving speed and the route track of the user;
step three: integrating all user figures in the same area, and analyzing to obtain people stream flow information of each area, wherein the people stream flow information comprises position dynamic information, people stream density and people stream quantity of each user;
step four: aiming at a specific area of a sudden emergency accident, acquiring people flow information of a corresponding accident area, and then planning an optimal emergency evacuation route scheme for personnel of the corresponding accident area, wherein the method specifically comprises the following steps:
s41: collecting data of each safety exit and historical emergency evacuation route scheme data; the safety exit data comprises a safety exit position and a safety exit size;
s42: establishing an index system according to the acquired data, wherein the index system comprises index factors and samples; the index factors comprise emergency demands, evacuation distances, evacuation times and evacuation paths, wherein the emergency demands are matched with the people flow information of corresponding accident areas in a correlation mode, the evacuation distances and the evacuation times are matched with the data of all safety exits in a correlation mode, the evacuation paths are matched with the people flow information of the areas in a correlation mode, and the people flow information of the areas is the people flow information of the areas; the sample comprises historical emergency evacuation route plan data;
s43: on the basis of a decision tree analysis method, taking each index factor as a leaf node of a decision tree, taking a sample as a root node, respectively establishing all emergency evacuation route schemes corresponding to accident areas, calculating the occurrence probability of each node in each emergency evacuation route scheme on the basis of a decision tree C4.5 algorithm, and further calculating the information gain rate of the corresponding emergency evacuation route scheme; wherein the nodes are represented as safe exits of the routes in the emergency evacuation route scheme;
s44: selecting an emergency evacuation route scheme with the highest information gain rate as an optimal emergency evacuation route scheme of the accident area, sharing the optimal emergency evacuation route scheme of the accident area to an emergency center, broadcasting the optimal emergency evacuation route scheme by voice through the emergency center, distributing emergency personnel to route nodes according to the optimal emergency evacuation route scheme, and carrying out evacuation guidance on the personnel in the accident area;
the method further comprises the following steps: tracking the track of personnel in the accident area, extracting personnel which do not meet evacuation characteristics from the track to form a straggling personnel set M, and recording straggling information of the straggling personnel, wherein the straggling information comprises straggling time and straggling position;
wherein the non-satisfaction of the evacuation feature manifests as: the deviation coefficient of the actual route track of the personnel movement relative to the optimal emergency evacuation route scheme exceeds a preset value; or simultaneously, the user stays for a time longer than a preset time threshold and the moving distance is less than a preset space threshold; the calculation method of the deviation coefficient comprises the following steps:
v1: acquiring an actual path track of movement of personnel in an accident area, marking coordinates of a real-time position of the personnel in the accident area as (X 'i, Y' i), and marking a point (X 'i, Y' i) as a verification point;
v2: acquiring a reference point corresponding to the real-time position of personnel in an accident area in the optimal emergency evacuation route scheme, wherein the reference point acquisition criterion is that a plurality of non-coincident corresponding points with points (X 'i, Y' i) in the optimal emergency evacuation route scheme are acquired, the distance between the corresponding points and the verification points is calculated, and the corresponding point with the closest distance is marked as the reference point;
v3: marking the reference point in the optimal emergency evacuation route scheme as (Xi, Yi); i =1,.., n; wherein i represents the ith point;
using formulas
Calculating to obtain a deviation coefficient PL;
clustering analysis is carried out on the falling staff set M based on time and space, and if the clustering characteristics are met, early warning information is generated; the method specifically comprises the following steps:
extracting the personnel with the difference value of the queue falling time within a preset value T1 and the difference value of the queue falling position within a preset value W1 from the queue falling personnel set M to form a clustering personnel set JU; marking the queue falling time with the most occurrence times as clustering occurrence time, and marking the queue falling position with the most occurrence times as a clustering occurrence place;
comparing the number of the personnel in the clustered personnel set JU with a preset number threshold; if the number of the alarm messages is larger than the preset number threshold, generating early warning information; the early warning information includes: clustering occurrence time, location, and personnel information; and after receiving the early warning information, the emergency center sends out emergency personnel to a clustering place to evacuate and guide the personnel falling behind.
2. An emergency area crowd identification device for implementing the method of claim 1, comprising:
an identification module: the system comprises a camera, a background information acquisition module, a display module and a display module, wherein the camera is used for capturing face images of a plurality of users appearing in the same area and respectively comparing the face images with background information, and further identifying user identity information corresponding to each face image;
a data sorting module: the face image capturing device is used for combining the capturing time stamp, the capturing place and the identity information corresponding to each face image to form a data record based on the time-space information of each user;
a data analysis module: the system comprises a data acquisition module, a data analysis module, a user portrait acquisition module, a user portrait analysis module and a user portrait management module, wherein the data acquisition module is used for acquiring user portraits according to data record analysis of a plurality of users, integrating all the user portraits in the same area and analyzing to acquire people stream flow information of each area;
a route planning module: aiming at a specific area of a sudden emergency accident, acquiring people flow information of the corresponding accident area, and then planning an optimal emergency evacuation route scheme for personnel of the corresponding accident area;
evacuation early warning module: the system is used for tracking the track of personnel in the accident area, extracting the personnel which do not meet evacuation characteristics from the track to form a fallen personnel set M, carrying out clustering analysis on the fallen personnel set M based on time and space, and generating early warning information if the clustering characteristics are met;
an emergency center: and sending out emergency personnel to the clustering place after receiving the early warning information, and evacuating and guiding the personnel falling behind.
3. A 5G emergency area crowd identification device comprising a processor, a memory, and a computer program stored in the memory; the processor, when executing the computer program, performs a 5G emergency area crowd identification method as recited in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111190074.2A CN113627407B (en) | 2021-10-13 | 2021-10-13 | 5G emergency area crowd identification method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111190074.2A CN113627407B (en) | 2021-10-13 | 2021-10-13 | 5G emergency area crowd identification method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627407A CN113627407A (en) | 2021-11-09 |
| CN113627407B true CN113627407B (en) | 2022-02-11 |
Family
ID=78391215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111190074.2A Active CN113627407B (en) | 2021-10-13 | 2021-10-13 | 5G emergency area crowd identification method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627407B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663755B (en) * | 2023-05-24 | 2023-11-28 | 宏威智慧科技(广东)有限公司 | Emergency evacuation monitoring management system based on data analysis |
| CN116668962B (en) * | 2023-08-01 | 2023-10-03 | 深圳市博朗耐技术有限公司 | Evacuation rescue remote monitoring method and system based on 5G communication |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913360A (en) * | 2016-04-07 | 2016-08-31 | 东南大学 | Large-scale event accident emergency preparedness generation method and device |
| CN109858365A (en) * | 2018-12-28 | 2019-06-07 | 深圳云天励飞技术有限公司 | A kind of special population Assembling Behavior analysis method, device and electronic equipment |
| CN113298390A (en) * | 2021-05-28 | 2021-08-24 | 长安大学 | Burst heterogeneous passenger flow multi-type collaborative evacuation scheme set construction method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106205042A (en) * | 2016-08-26 | 2016-12-07 | 王起全 | Subway crowded trampling accident early warning linkage system and early warning linkage method |
-
2021
- 2021-10-13 CN CN202111190074.2A patent/CN113627407B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913360A (en) * | 2016-04-07 | 2016-08-31 | 东南大学 | Large-scale event accident emergency preparedness generation method and device |
| CN109858365A (en) * | 2018-12-28 | 2019-06-07 | 深圳云天励飞技术有限公司 | A kind of special population Assembling Behavior analysis method, device and electronic equipment |
| CN113298390A (en) * | 2021-05-28 | 2021-08-24 | 长安大学 | Burst heterogeneous passenger flow multi-type collaborative evacuation scheme set construction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627407A (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113627407B (en) | 5G emergency area crowd identification method, device and equipment | |
| CN111291699B (en) | Substation personnel behavior identification method based on monitoring video time sequence action positioning and abnormity detection | |
| CN115272037B (en) | Smart city based on Internet of things regional public security management early warning method and system | |
| CN108053427B (en) | Improved multi-target tracking method, system and device based on KCF and Kalman | |
| CN108009473A (en) | Based on goal behavior attribute video structural processing method, system and storage device | |
| CN108052859B (en) | Abnormal behavior detection method, system and device based on clustering optical flow characteristics | |
| WO2022126669A1 (en) | Subway pedestrian flow network fusion method based on video pedestrian recognition, and pedestrian flow prediction method | |
| CN108062349A (en) | Video frequency monitoring method and system based on video structural data and deep learning | |
| CN106997629A (en) | Access control method, apparatus and system | |
| CN112084963B (en) | Monitoring early warning method, system and storage medium | |
| CN107194030B (en) | Crowd evacuation simulation method and system based on video data driving | |
| CN111353338B (en) | Energy efficiency improvement method based on business hall video monitoring | |
| CN111753651A (en) | Subway group abnormal behavior detection method based on station two-dimensional crowd density analysis | |
| CN112287827A (en) | Complex environment pedestrian mask wearing detection method and system based on intelligent lamp pole | |
| CN110796758A (en) | Forest protection inspection method based on mobile GIS | |
| CN107657232A (en) | A kind of pedestrian's intelligent identification Method and its system | |
| CN112464843A (en) | Accurate passenger flow statistical system, method and device based on human face human shape | |
| CN111079722A (en) | Hoisting process personnel safety monitoring method and system | |
| CN111460940A (en) | Stranger foot drop point studying and judging method and system | |
| Valencia et al. | Vision-based crowd counting and social distancing monitoring using Tiny-YOLOv4 and DeepSORT | |
| CN115294519A (en) | Abnormal event detection and early warning method based on lightweight network | |
| CN210666820U (en) | Pedestrian abnormal behavior detection system based on DSP edge calculation | |
| CN116189439A (en) | Urban intelligent management system | |
| CN113469080A (en) | Individual, group and scene interactive collaborative perception method, system and equipment | |
| CN117011774A (en) | Cluster behavior understanding system based on scene knowledge element |
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 |