CN115865988A - Passenger ship passenger treading event monitoring system and method utilizing mobile phone sensor network - Google Patents
Passenger ship passenger treading event monitoring system and method utilizing mobile phone sensor network Download PDFInfo
- Publication number
- CN115865988A CN115865988A CN202310143014.8A CN202310143014A CN115865988A CN 115865988 A CN115865988 A CN 115865988A CN 202310143014 A CN202310143014 A CN 202310143014A CN 115865988 A CN115865988 A CN 115865988A
- Authority
- CN
- China
- Prior art keywords
- crowd
- data
- module
- passenger
- mobile phone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000008447 perception Effects 0.000 claims abstract description 40
- 238000004364 calculation method Methods 0.000 claims abstract description 32
- 230000008859 change Effects 0.000 claims abstract description 11
- 230000009471 action Effects 0.000 claims abstract description 9
- 238000012800 visualization Methods 0.000 claims abstract description 9
- 230000006399 behavior Effects 0.000 claims description 76
- 230000033001 locomotion Effects 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 15
- 230000001133 acceleration Effects 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 8
- 230000003542 behavioural effect Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 206010039740 Screaming Diseases 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005428 wave function Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 208000001431 Psychomotor Agitation Diseases 0.000 description 1
- 206010038743 Restlessness Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses a passenger ship passenger trampling event monitoring system and method using a mobile phone sensor network, wherein the system comprises an environment and crowd state data sensing module: the system is used for capturing physical space environment data and crowd situation perception data; perception calculation reasoning module: the system is used for fusing physical space environment data and crowd situation perception data, extracting crowd behavior characteristics, calculating crowding degree and predicting occurrence probability of trampling accidents; an action execution visualization module: the intelligent mobile phone is used for outputting the stepping accident occurrence probability, starting an alarm when the probability exceeds a threshold value, and transmitting an instruction for dealing with the dynamic change of the environment to each individual smart mobile phone in the crowd in the passenger ship. The invention can realize dynamic monitoring on the evacuation environment and crowd behavior of the ship by the regional sensor and the mobile phone embedded sensor, and converts the spatial phenomenon into a numerical model which can be processed, stored and executed, thereby improving the precision and reliability of the system.
Description
Technical Field
The invention relates to the technical field of ships, in particular to a passenger ship passenger trampling event monitoring system and method utilizing a mobile phone sensor network.
Background
Shipping is used as a main transportation mode of domestic and international trade, and particularly in recent years, with deep implementation of the ocean strong strategy in China, the shipping industry is rapidly developed. In order to improve the shipping conveying capacity and the passenger service quality, the passenger ship tends to be large-sized and modernized, and the capacity and the number of the passenger ship are increased, so that the risk of travel at sea is increased. If an emergency accident occurs, passengers of a passenger ship are gathered in a large amount at bottleneck positions such as corridors, stairs and the like to cause a congestion and detention phenomenon in the escape process, and then the ship body moves obliquely, so that the passengers are easy to fall down at the positions, and the crowd congestion and treading accident is caused, and the safe evacuation of people on the ship is not facilitated.
The current means for judging the flow of people mainly comprises image and video identification and computer vision identification, and because infrastructure (such as a camera and a communication system) is static, long-term effective work cannot be kept, or unforeseen key areas can be monitored. The disadvantages of the dynamic acquisition, the low processing speed and the like cause the disadvantages of the dynamic acquisition in the application level. The real-time information and communication are key factors for preventing crowd disasters, so that the crowd evacuation environment and the crowd dynamics are effectively monitored, and the real-time information and the communication information are very necessary to be provided for passengers.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a passenger ship passenger trampling event monitoring system and method using a mobile phone sensor network, which convert the spatial phenomenon into a numerical model capable of being processed, stored and executed, and improve the precision and reliability of the system.
In order to achieve the above object, the passenger ship passenger tread event monitoring system using a mobile phone sensor network according to the present invention is characterized in that the system comprises:
the environment and crowd state data sensing module: the system comprises a passenger ship, a data acquisition module and a data acquisition module, wherein the data acquisition module is used for acquiring physical space environment data and crowd situation perception data, the physical space environment data comprises temperature data, sound data and visual data of a fragile narrow area in the passenger ship, and the crowd situation perception data comprises position, speed and moving direction data of each individual in crowd in the passenger ship;
perception calculation reasoning module: the system is used for fusing the physical space environment data and the crowd situation perception data, extracting crowd behavior characteristics, calculating crowding degree and predicting the occurrence probability of trampling accidents;
an action execution visualization module: the intelligent mobile phone is used for outputting the stepping accident occurrence probability, starting an alarm when the probability exceeds a threshold value, and transmitting an instruction for dealing with the dynamic change of the environment to each individual smart mobile phone in the crowd in the passenger ship.
Furthermore, the physical space environment data is collected through a sensor, the sensor comprises an optical sensor, a temperature sensor, a sound sensor and a visual sensor, the sensor is arranged in a vulnerable narrow area in the passenger ship, and the collected data is transmitted to the perception calculation reasoning module after being preprocessed;
the crowd situation perception data is collected through a smart phone of each individual in the crowd in the passenger ship, the data is collected through an acceleration sensor, a gyroscope and a position sensor which are embedded into the smart phone, and the data is preprocessed and then remotely transmitted to the perception calculation reasoning module through the smart phone.
Furthermore, the perception calculation reasoning module comprises a crowd characteristic extraction module, a local individual behavior difference analysis module and a global crowd movement analysis module;
the crowd characteristic extraction module: method for extracting crowd behavior characteristics X based on machine learning method for sensor preprocessing time sequence received from environment and crowd state data sensing module i ；
The local individual behavior difference analysis module: for characterizing the behavior of a population X i Mapping to individual behavior b i Thereby forming a ground-based location markerA signed individual behavior classification dataset D;
the global crowd motion analysis module: the method is used for calculating the behavior difference among individuals in the crowd, calculating the local density and the crowd flow of the crowd and outputting the occurrence probability of the trampling accident by comparing with a set threshold value.
Furthermore, the physical space environment data and the crowd situation perception data are preprocessed and then transmitted to the perception calculation reasoning module, and the preprocessing process includes the steps of obtaining a relative time sequence S according to the sensor data, calibrating, denoising, vector acceleration calculating and acceleration amplitude calculating the time sequence S data, and generating a preprocessed signal preprocessing time sequence P.
Furthermore, data communication is realized between the sensors of the environment and crowd state data sensing module and the sensing calculation reasoning module through the HUB multi-port repeater.
Further, the local individual behavior difference analysis module analyzes the feature vector X i Mapping individual behaviors b i ，b i For the behavior detection probability of the individual behavior at the time T, mapping the behavior characteristics of the population comprises: crowd moves toward a common destination to gather, crowd meets rejection of obstacles to generate backward force, crowd pushing and falling monitoring, crowd density increase to cause heat rise, and crowd screaming to cause high noise.
Further, the global population motion analysis module employs an individual difference matrix C T Calculating behavioral differences between individuals in the population:
in the formula, C T Representing a disparity matrix based on time T, f () representing a preprocessing function, corr () representing a crowd behavior similarity comparison function, c representing a disparity value,
representing the disparity value between the individuals u and v, and n, m are the rows and columns of the matrix.
Furthermore, the global crowd motion analysis module calculates local density of the crowd and the crowd flow according to the following formulas:
by using
Representing the local position, x, y are planar coordinates, then the local density is represented as:
by using
Represents the in-zone position ^ of the individual pedestrian j>
In the range of (4), is greater than or equal to>
A threshold value set for congestion;
the crowd speed is determined by a weighted average:
flow of crowd
Expressed as: />
Based on the system, the invention provides a method, which comprises the following steps:
s1, an environment and crowd state data sensing module collects temperature data, sound data and visual data of a vulnerable narrow area in a passenger ship and position, speed and moving direction data of each individual in the crowd in the passenger ship and transmits the data to a sensing calculation reasoning module;
s2, the sensing, calculating and reasoning module fuses data acquired by the environment and crowd state data sensing module, crowd behavior characteristics are extracted based on a machine learning method, crowd behavior patterns based on density pressure are analyzed, crowding degree is calculated, and the occurrence probability of trampling accidents is predicted;
and S3, the action execution visualization module dynamically monitors the crowd density of the vulnerable narrow area in the passenger ship according to the output result of the perception calculation reasoning module, starts an alarm when the probability exceeds a threshold value, and transmits an instruction for dealing with the dynamic change of the environment to the smart phone of each individual in the crowd in the passenger ship.
The invention further proposes a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method.
The invention realizes multi-sensor dynamic acquisition based on embedding the smart phone into the sensor network, and makes data networking and cloud processing possible. The intelligent mobile phone sensor is used for identifying individual and group behaviors, compared with a traditional independent sensor and computer platform binding mode, real-time information and communication acquisition can be achieved, the whole process is more convenient, and high equipment cost and high power consumption can be reduced. In addition, the smart phone is rapidly popularized in daily life, the popularization rate is continuously improved, and almost one mobile phone is used, so that the embedded sensor based on the smart phone becomes feasible. Through mobile phone sensing, data sharing among users can improve the precision and reliability of system judgment; the user uploads the data to the cloud, can construct the whole real-time people flow density graph, monitors the behaviors of individuals and groups in real time, and is very meaningful for guiding the crowd to be evacuated in time to avoid the occurrence of the blocking trampling event.
Compared with the prior art, the invention has the following advantages:
1. the method comprises the steps of collecting environment and crowd state data in real time by using a mobile phone embedded sensor, extracting crowd behavior characteristics, carrying out classification processing, constructing a crowd dynamic model, carrying out computational reasoning, analyzing crowd behavior dynamics and risk assessment, and generating a visual action result based on situation dynamic monitoring to project the visual action result to a smart phone screen;
2. the invention converts the physical space phenomenon into a numerical model which can be processed, stored and executed, and adapts to and responds to the dynamic change of the environment, thereby improving the precision and the reliability of the system and having reference value for preventing the occurrence of the trampling event of people;
3. the invention can realize dynamic monitoring on the evacuation environment and the crowd behavior of the ship through the regional sensor and the mobile phone embedded sensor, and converts the spatial phenomenon into a numerical model which can be processed, stored and executed.
Drawings
FIG. 1 is a block diagram of the architecture of the system of the present invention;
FIG. 2 is a schematic diagram of data transmission between the environmental and crowd status data sensing module and the sensing and computational inference module in the system of the present invention;
FIG. 3 is a flow chart of a crowd flow congestion identification and assessment algorithm adopted by the data of the perception calculation reasoning module in the system of the present invention.
Detailed description of the preferred embodiments
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
As shown in figure 1, the passenger ship and passenger trampling event monitoring system utilizing the mobile phone sensor network comprises an environment and crowd state data sensing module, a sensing calculation reasoning module and an action execution visualization module.
The environment and crowd state data sensing module: the system comprises a passenger ship, a data acquisition module and a data acquisition module, wherein the data acquisition module is used for acquiring physical space environment data and crowd situation perception data, the physical space environment data comprises temperature data, sound data and visual data of a fragile narrow area in the passenger ship, and the crowd situation perception data comprises position, speed and moving direction data of each individual in crowd in the passenger ship;
the perception calculation reasoning module: the system is used for fusing the physical space environment data and the crowd situation perception data, extracting crowd behavior characteristics, calculating crowding degree and predicting the occurrence probability of trampling accidents;
an action execution visualization module: the intelligent mobile phone is used for outputting the stepping accident occurrence probability, starting an alarm when the probability exceeds a threshold value, and transmitting an instruction for dealing with the dynamic change of the environment to each individual smart mobile phone in the crowd in the passenger ship.
Specifically, the environment and crowd state data sensing module monitors the environment and crowd state of the fragile and narrow region of the passenger ship stair passageway, and captures and reveals the physical space environment and crowd dynamic data. Physical space environment data are collected through sensors, the sensors comprise optical sensors, temperature sensors, sound sensors and vision sensors, the sensors are arranged in a vulnerable narrow area in a passenger ship, and the collected data are transmitted to the perception calculation reasoning module after being preprocessed;
the crowd situation perception data are acquired through a smart phone of each individual in the crowd in the passenger ship, acquired through an acceleration sensor, a gyroscope and a position sensor embedded in the smart phone, preprocessed and transmitted to the perception calculation reasoning module through the smart phone in a remote mode, and are used for capturing crowd situation perception data including user positions, speeds and moving directions, and monitoring crowd dynamics including congestion and abnormal behavior conditions.
And the physical space environment data and the crowd situation perception data are preprocessed and then transmitted to the perception calculation reasoning module. The temperature sensor captures heat and heat rise due to increased crowd density, the sound sensor captures high noise levels caused by screech of crowd during evacuation, the vision sensor captures crowd density and flow pattern estimates, and the position sensor is used to provide dynamic positions of individuals. The individual behavior recognition and the people flow dynamic crowd monitoring are realized by an accelerometer and a gyroscope sensor.
Data communication is realized between the sensors of the environment and crowd state data sensing module and the sensing calculation reasoning module through a HUB multi-port transponder, as shown in FIG. 2. The environment and crowd state data sensing module preprocesses data collected by the sensors by obtaining relative time series S according to the data of each sensor, calibrating, denoising, vector acceleration calculating and acceleration amplitude calculating the data of the time series S, and generating a preprocessed signal preprocessing time series P.
First, a corresponding time series S is obtained from each sensor data.
S={S 1 ，S 2 ，S 3 ，…} （1）
Wherein S is a sensor time series data set, S 1 ，S 2 ，S 3 Respectively, representing data collected by each sensor.
Then, preprocessing is performed on the data in the sensor time series data set S, such as calibration, denoising, acceleration amplitude calculation with vector acceleration, and the like, to generate a signal preprocessing time series P.
P={P 1 ，P 2 ，P 3 ，…} （2）
The perception calculation reasoning module is used for judging the crowd flow congestion degree and identifying abnormal behaviors, and analyzing the crowd congestion behavior identification and predicting the occurrence probability of the crowd trampling event based on the multi-sensor data set. The perception calculation reasoning module comprises crowd characteristic extraction, local individual behavior difference analysis and crowd movement parallax matrix calculation, and the analyzed sensor data is mapped to crowd movement to obtain the crowd congestion and trampling event occurrence probability.
The perception calculation reasoning module comprises a crowd characteristic extraction module, a local individual behavior difference analysis module and a global crowd motion analysis module;
wherein, crowd's feature extraction module: for preprocessing time sequence P of signals received from environment and crowd state data sensing module and extracting crowd behavior characteristics X based on machine learning method i ：
X i = ψ(b i ) （3）
In the formula, X i Representing a behavioral feature vector, b i Representing individual behavior characteristics, i =1,2, \ 8230N, N representing the total number of people/number of sensors in the monitored area, psi () representing the wave function of individual characteristics for characterizingIndividual behavioral patterns. Individual behavioral characteristics b i According to a behaviour pattern P i Analyzed to obtain a behavior pattern P i Obtained from the i-th individual/sensor monitored by the signal preprocessing time series P, i.e. X i And b i 、P i Has a mapping relationship.
The wave function of the individual characteristics comprises five conditions, and corresponding behavior characteristic vectors X are output i : (1) people moving toward a common destination; (2) the crowd can generate a retreating force by meeting the rejection of the obstacle; (3) crowd tumble monitoring; (4) the population density is constantly rising; (5) the heat in the crowd rises greatly, screaming generates high noise and the like. The behavior mode (1) is described as that the density at an outlet rapidly rises and congestion effect occurs, and the density of people reaches a preset threshold rho when the density is acquired by a mobile phone signal position sensor 1 When the crowd moves freely and enters a crowded state, a first behavior feature vector X is output i (ii) a The (2) behavior pattern describes that the retreating force is generated by repulsion when the crowd meets an obstacle, and the density reaches a preset threshold value rho 1 Then the crowd density shows fluctuation change, shows crowding and meanwhile the crowd density shows imbalance, and outputs a second behavior characteristic vector X i (ii) a The behavior pattern (3) is described as crowd pushing and falling monitoring, collected by a visual sensor, output is judged through a trained computer model, target individuals in a falling area are marked, and a third row feature vector X is output i (ii) a Behavior pattern P of (4) i Described as the population density reaching a certain threshold p 2 The crowd moving speed is almost 0, the fact that the crowd stops moving due to the fact that the crowd is extremely crowded is reflected, and the fourth line feature vector X is output i (ii) a Behavior pattern P of (5) i Describing abnormal behaviors and chaotic phenomena possibly occurring in anxiety and restlessness of individuals, acquiring by a temperature sensor and a sound sensor, and outputting a fifth behavior feature vector X when acquired values of the temperature sensor and the sound sensor simultaneously meet a set threshold value i 。
Local individual behavior difference analysis module: for characterizing a behavior vector X i Mapping to specific locations to form individuals based on ground location tagsBehavior classification dataset D:
in the formula, li is a feature vector X i And a corresponding ground location tag, N represents the total number of people/sensors in the monitored area. Thus, the individual behavior classification dataset D refers to the set of individual behaviors at the li location.
Global crowd motion analysis module: the method is used for calculating the behavior difference among individuals in the crowd, calculating the local density and the crowd flow of the crowd, and outputting the occurrence probability of the trampling accident by comparing with a set threshold value.
Individual behavior is the result of their participation in the common group behavior of the system. Therefore, the crowd movement can be obtained by calculating and comparing the individual behavior difference. Time Tslave behavior B u And B v Inferring a measure of difference between a pair of individuals u and v using a difference matrix C T And (4) showing.
The global crowd motion analysis module adopts an individual difference matrix C T Calculating behavioral differences between individuals in the population:
in the formula, C T Representing a disparity matrix based on time T, f () representing a pre-processing function, corr () representing a crowd behavior similarity comparison function, c representing a disparity value,
representing the disparity value between the individuals u and v, and n, m are the rows and columns of the matrix.
Further, the global crowd movement analysis module calculates local density and crowd flow of the crowd according to the following formulas:
by using
Representing the local position, x, y are planar coordinates, then the local density is represented as:
by using
Represents the in-zone position ^ of the individual pedestrian j>
In the range of (4), is greater than or equal to>
A threshold set for congestion;
the crowd speed is determined by a weighted average:
flow of crowd
Expressed as:
deducing global group behaviors based on the system, firstly setting the overall characteristics of the group behaviors, and when the behavior parallax CT between the individuals u and v is low, indicating that the behaviors of the individuals u and v are the same as those of the group, and indicating that the group behaviors are normal; when the behavioral parallax CT between the individuals u and v is high, the behavior difference CT between the individuals u and v is different from that of the crowd, the possible abnormal behavior pattern Pi is deduced, the crowd density is monitored based on the individual parallax, the crowding degree is calculated, and the occurrence probability of the trampling accidents is predicted.
An action execution visualization module: the intelligent mobile phone is used for outputting the stepping accident occurrence probability, starting an alarm when the probability exceeds a threshold value, and transmitting an instruction for dealing with the dynamic change of the environment to each individual smart mobile phone in the crowd in the passenger ship.
Based on the system, the invention also provides a method for monitoring the trampling event of the passenger ship passenger by using the mobile phone sensor network, which comprises the following steps:
s1, an environment and crowd state data sensing module collects temperature data, sound data and visual data of a fragile narrow area in a passenger ship and position, speed and moving direction data of each individual in the crowd in the passenger ship and transmits the data to a sensing calculation reasoning module;
s2, the sensing, calculating and reasoning module fuses data acquired by the environment and crowd state data sensing module, crowd behavior characteristics are extracted based on a machine learning method, crowd behavior patterns based on density pressure are analyzed, crowding degree is calculated, and the occurrence probability of trampling accidents is predicted;
and S3, the action execution visualization module dynamically monitors the crowd density of the vulnerable narrow area in the passenger ship according to the output result of the perception calculation reasoning module, starts an alarm when the probability exceeds a threshold value, and transmits an instruction for dealing with the dynamic change of the environment to the smart phone of each individual in the crowd in the passenger ship. When the crowd movement analysis shows the abnormal congestion effect, an alarm system is started, the sensing calculation and the wireless network smart phone signal are integrated through the smart phone, and the instruction for dealing with the dynamic change of the environment is transmitted to the screen of the smart phone through the wireless network to guide crowd evacuation.
The embodiment of the invention provides a crowd flow congestion identification and evaluation algorithm which is shown in fig. 3, and comprises the steps of collecting dynamic data of environment and crowds through a sensor, carrying out filtering preprocessing on the collected original data, extracting behavior characteristics, and comparing and classifying individual behavior characteristic differences to obtain crowd behavior characteristic values.
It should be understood that the above-mentioned preferred embodiments are illustrative and not restrictive, and those skilled in the art can make substitutions and modifications without departing from the scope of the invention as claimed.
Claims (10)
1. A passenger ship passenger trampling event monitoring system utilizing a mobile phone sensor network is characterized in that: the system comprises:
the environment and crowd state data sensing module: the system comprises a passenger ship, a data acquisition module and a data acquisition module, wherein the data acquisition module is used for acquiring physical space environment data and crowd situation perception data, the physical space environment data comprises temperature data, sound data and visual data of a fragile narrow area in the passenger ship, and the crowd situation perception data comprises position, speed and moving direction data of each individual in crowd in the passenger ship;
perception calculation reasoning module: the system is used for fusing the physical space environment data and the crowd situation perception data, extracting crowd behavior characteristics, calculating crowding degree and predicting the occurrence probability of trampling accidents;
an action execution visualization module: the intelligent mobile phone is used for outputting the stepping accident occurrence probability, starting an alarm when the probability exceeds a threshold value, and transmitting an instruction for dealing with the dynamic change of the environment to each individual smart mobile phone in the crowd in the passenger ship.
2. The system for monitoring the stepping event of a passenger ship passenger using a mobile phone sensor network as claimed in claim 1, wherein: the physical space environment data is collected through a sensor, the sensor comprises an optical sensor, a temperature sensor, a sound sensor and a vision sensor, the sensor is arranged in a vulnerable narrow area in a passenger ship, and the collected data is transmitted to the perception calculation reasoning module after being preprocessed;
the crowd situation perception data is collected through a smart phone of each individual in the crowd in the passenger ship, the data is collected through an acceleration sensor, a gyroscope and a position sensor which are embedded into the smart phone, and the data is preprocessed and then remotely transmitted to the perception calculation reasoning module through the smart phone.
3. The system for monitoring the stepping event of a passenger ship passenger using a mobile phone sensor network as claimed in claim 1, wherein: the perception calculation reasoning module comprises a crowd characteristic extraction module, a local individual behavior difference analysis module and a global crowd motion analysis module;
the crowd characteristic extraction module: method for extracting crowd behavior characteristics X based on machine learning method for sensor preprocessing time sequence received from environment and crowd state data sensing module i ；
The local individual behavior difference analysis module: for characterizing the behavior of a population X i Mapping to individual behavior b i Thereby forming an individual behavior classification data set D based on the ground position label;
the global crowd motion analysis module: the method is used for calculating the behavior difference among individuals in the crowd, calculating the local density and the crowd flow of the crowd and outputting the occurrence probability of the trampling accident by comparing with a set threshold value.
4. The passenger ship passenger pedaling event monitoring system utilizing mobile phone sensor network as claimed in claim 2, wherein: the physical space environment data and the crowd situation perception data are transmitted to the perception calculation reasoning module after being preprocessed, the preprocessing process includes the steps of obtaining relative time series S according to the data of each sensor, calibrating, denoising, vector acceleration calculating and acceleration amplitude calculating are conducted on the data of the time series S, and a preprocessed signal preprocessing time series P is generated.
5. The system for monitoring the stepping event of a passenger ship passenger using a mobile phone sensor network as claimed in claim 1, wherein: and the sensors of the environment and crowd state data sensing module and the sensing calculation reasoning module realize data communication through the HUB multi-port transponder.
6. The system and method for monitoring the stepping event of a passenger ship using the mobile phone sensor network as claimed in claim 3, wherein: the local individual behavior difference analysis module analyzes the feature vector X i Mapping individual behaviors b i ，b i The method for detecting the probability of the behavior of the individual behavior at the T moment and mapping the behavior characteristics of the crowd comprises the following steps: crowd moves toward a common destination to gather, crowd meets rejection of obstacles to generate backward force, crowd pushing and falling monitoring, crowd density increase to cause heat rise, and crowd screaming to cause high noise.
7. The system for monitoring the stepping event of a passenger ship passenger using a mobile phone sensor network as claimed in claim 3, wherein: the global crowd motion analysis module adopts an individual difference matrix C T Calculating behavioral differences between individuals in the population:
in the formula, C T Representing a disparity matrix based on time T, f () representing a preprocessing function, corr () representing a crowd behavior similarity comparison function, c representing a disparity value,
representing the disparity value between individuals u and v, and n, m are the rows and columns of the matrix.
8. The system and method for monitoring the stepping event of a passenger ship using the mobile phone sensor network as claimed in claim 3, wherein: the global crowd motion analysis module calculates local density of crowd and crowd flow according to formulas as follows:
by using
Representing the local position, x, y are planar coordinates, then the local density is represented as:
by using
Represents the in-zone position ^ of the individual pedestrian j>
In the range of (4), is greater than or equal to>
A threshold value set for congestion;
the crowd speed is determined by a weighted average:
flow of crowd
Expressed as:
9. a passenger ship passenger trampling event monitoring system method based on any one of claims 1 to 8 and utilizing a mobile phone sensor network, which is characterized in that: the method comprises the following steps:
s1, an environment and crowd state data sensing module collects temperature data, sound data and visual data of a fragile narrow area in a passenger ship and position, speed and moving direction data of each individual in the crowd in the passenger ship and transmits the data to a sensing calculation reasoning module;
s2, the sensing, calculating and reasoning module fuses data acquired by the environment and crowd state data sensing module, crowd behavior characteristics are extracted based on a machine learning method, crowd behavior patterns based on density pressure are analyzed, crowding degree is calculated, and the occurrence probability of trampling accidents is predicted;
and S3, the action execution visualization module dynamically monitors the crowd density of the vulnerable narrow area in the passenger ship according to the output result of the perception calculation reasoning module, starts an alarm when the probability exceeds a threshold value, and transmits an instruction for dealing with the dynamic change of the environment to the smart phone of each individual in the crowd in the passenger ship.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310143014.8A CN115865988B (en) | 2023-02-21 | 2023-02-21 | Passenger ship passenger tread event monitoring system and method by utilizing mobile phone sensor network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310143014.8A CN115865988B (en) | 2023-02-21 | 2023-02-21 | Passenger ship passenger tread event monitoring system and method by utilizing mobile phone sensor network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115865988A true CN115865988A (en) | 2023-03-28 |
| CN115865988B CN115865988B (en) | 2023-05-26 |
Family
ID=85658549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310143014.8A Active CN115865988B (en) | 2023-02-21 | 2023-02-21 | Passenger ship passenger tread event monitoring system and method by utilizing mobile phone sensor network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115865988B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854008A (en) * | 2024-01-16 | 2024-04-09 | 浙江威星电子系统软件股份有限公司 | Intelligent sports stadium management system based on digital twinning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140372348A1 (en) * | 2011-12-15 | 2014-12-18 | Northeastern University | Real-time anomaly detection of crowd behavior using multi-sensor information |
| CN107609682A (en) * | 2017-08-22 | 2018-01-19 | 上海世脉信息科技有限公司 | Population agglomeration middle or short term method for early warning under a kind of big data environment |
| CN112199747A (en) * | 2020-09-29 | 2021-01-08 | 西安交通大学 | Indoor personnel evacuation method and evacuation system based on queuing network |
| CN113361825A (en) * | 2021-07-19 | 2021-09-07 | 青岛理工大学 | Early warning method and system for trampling accident |
| US20220254162A1 (en) * | 2021-02-10 | 2022-08-11 | Umm Al-Qura University | Deep learning framework for congestion detection and prediction in human crowds |
-
2023
- 2023-02-21 CN CN202310143014.8A patent/CN115865988B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140372348A1 (en) * | 2011-12-15 | 2014-12-18 | Northeastern University | Real-time anomaly detection of crowd behavior using multi-sensor information |
| CN107609682A (en) * | 2017-08-22 | 2018-01-19 | 上海世脉信息科技有限公司 | Population agglomeration middle or short term method for early warning under a kind of big data environment |
| CN112199747A (en) * | 2020-09-29 | 2021-01-08 | 西安交通大学 | Indoor personnel evacuation method and evacuation system based on queuing network |
| US20220254162A1 (en) * | 2021-02-10 | 2022-08-11 | Umm Al-Qura University | Deep learning framework for congestion detection and prediction in human crowds |
| CN113361825A (en) * | 2021-07-19 | 2021-09-07 | 青岛理工大学 | Early warning method and system for trampling accident |
Non-Patent Citations (1)
| Title |
|---|
| 黄丽蒂;刘德明;赵文艳;: "提高体育场抵抗人群事故发生能力的新视点" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854008A (en) * | 2024-01-16 | 2024-04-09 | 浙江威星电子系统软件股份有限公司 | Intelligent sports stadium management system based on digital twinning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115865988B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110649B (en) | Selective human face detection method based on speed direction | |
| US8744125B2 (en) | Clustering-based object classification | |
| KR101748121B1 (en) | System and method for detecting image in real-time based on object recognition | |
| CN111582201A (en) | Lane line detection system based on geometric attention perception | |
| JP6598746B2 (en) | Apparatus, program, and method for tracking an object in consideration of an image area of another object | |
| CN112861635B (en) | Fire disaster and smoke real-time detection method based on deep learning | |
| KR101116273B1 (en) | Apparatus and Method for Traffic Accident Recognition | |
| KR101877294B1 (en) | Smart cctv system for crime prevention capable of setting multi situation and recognizing automatic situation by defining several basic behaviors based on organic relation between object, area and object's events | |
| CN103258427A (en) | Urban expressway traffic real-time monitoring system and method based on information physical network | |
| CN115761537B (en) | Power transmission line foreign matter intrusion identification method oriented to dynamic feature supplementing mechanism | |
| CN110633643A (en) | Abnormal behavior detection method and system for smart community | |
| Rabiee et al. | IVOA: Introspective vision for obstacle avoidance | |
| WO2021043126A1 (en) | System and method for event recognition | |
| CN107330414A (en) | Act of violence monitoring method | |
| CN115865988B (en) | Passenger ship passenger tread event monitoring system and method by utilizing mobile phone sensor network | |
| CN116664359A (en) | Intelligent fire early warning decision system and method based on multi-sensor fusion | |
| CN111460917B (en) | Airport abnormal behavior detection system and method based on multi-mode information fusion | |
| CN112686111B (en) | Attention mechanism-based multi-view adaptive network traffic police gesture recognition method | |
| CN117115752A (en) | Expressway video monitoring method and system | |
| CN116740649A (en) | Deep learning-based real-time detection method for behavior of crewman falling into water beyond boundary | |
| CN114677647A (en) | Safety monitoring system and method for road running state | |
| JPWO2018105195A1 (en) | Video failure detection device, video failure detection method, and program | |
| CN110084146B (en) | Pedestrian detection method and device based on shielding perception self-supervision learning | |
| CN113887634A (en) | Improved two-step detection-based electric safety belt detection and early warning method | |
| CN110333517B (en) | Obstacle sensing method, obstacle sensing device and storage medium |
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 |