CN111540162A - Pedestrian flow early warning system based on raspberry group - Google Patents
Pedestrian flow early warning system based on raspberry group Download PDFInfo
- Publication number
- CN111540162A CN111540162A CN202010306535.7A CN202010306535A CN111540162A CN 111540162 A CN111540162 A CN 111540162A CN 202010306535 A CN202010306535 A CN 202010306535A CN 111540162 A CN111540162 A CN 111540162A
- Authority
- CN
- China
- Prior art keywords
- display
- raspberry
- display module
- signal
- people
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 240000007651 Rubus glaucus Species 0.000 title claims abstract description 40
- 235000011034 Rubus glaucus Nutrition 0.000 title claims abstract description 40
- 235000009122 Rubus idaeus Nutrition 0.000 title claims abstract description 40
- 238000010586 diagram Methods 0.000 claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000011664 signaling Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 241001137251 Corvidae Species 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 235000015108 pies Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0236—Threshold setting
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Child & Adolescent Psychology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a pedestrian flow early warning system based on raspberry group, comprising: the display module and raspberry group, the raspberry group is used for including: acquiring thermodynamic diagrams, and importing the thermodynamic diagrams into a neural network to obtain people flow density data; drawing people stream density data and corresponding time data into a people stream density curve; calculating the average slope of the people flow density curve, and controlling a display module to display a first state when the average slope is more than or equal to 1.8; when the average slope is less than 1.8 and more than or equal to 1, controlling the display module to display a second state; and when the average slope is less than 1 and more than or equal to 0.5, controlling the display module to display a third state. The early warning of the stream density is realized by constructing a stream density curve by utilizing a raspberry group, solving an average slope and setting a certain judgment condition. The problem of current through artifical inaccurate that people stream density early warning brought is solved. The invention is mainly used for the technical field of detection.
Description
Technical Field
The invention relates to the technical field of detection, in particular to a pedestrian flow early warning system based on raspberry pies.
Background
With the development of society, in order to prevent accidents, people flow conditions in hot places need to be monitored and early warned to some extent. For management departments, people flow conditions of hot sites need to be known in time, and the people flow conditions need to be managed and controlled necessarily. The existing people flow condition early warning condition of the hot place generally adopts a manual counting mode, and the mode is inaccurate in people flow condition monitoring and early warning, so that an accurate people flow early warning system is urgently needed for managers of the hot place.
Disclosure of Invention
The invention aims to provide a pedestrian flow early warning system based on raspberry pi, which is used for solving one or more technical problems in the prior art and at least providing a beneficial selection or creation condition.
The solution of the invention for solving the technical problem is as follows: a pedestrian flow early warning system based on raspberry group includes:
a display module;
a raspberry pi storing a neural network for including: acquiring thermodynamic diagrams, and importing the thermodynamic diagrams into a neural network to obtain people flow density data; drawing people stream density data and corresponding time data into a people stream density curve; calculating the average slope of the people flow density curve, and controlling a display module to display a first state when the average slope is more than or equal to 1.8; when the average slope is less than 1.8 and more than or equal to 1, controlling the display module to display a second state; and when the average slope is less than 1 and more than or equal to 0.5, controlling the display module to display a third state.
Further, the personal stream early warning system further comprises an infrared camera, the infrared camera shoots an area to be detected in real time within a preset detection period to obtain a thermodynamic diagram, and the thermodynamic diagram is transmitted to a raspberry group.
Further, when the raspberry pi controls the display module to display the first state, a first signal is output outwards; when the raspberry pi controls the display module to display the second state, a second signal is output outwards; and when the raspberry pi controls the display module to display the third state, the raspberry pi outputs a third signal to the outside.
Further, the system for early warning of the human flow further comprises a preprocessing module, wherein the preprocessing module is used for denoising the thermodynamic diagram before the thermodynamic diagram is guided into the neural network.
Further, the display module is a display screen.
Further, the specific method for drawing the people stream density data and the corresponding time data into the people stream density curve is as follows: the method comprises the steps of establishing a rectangular coordinate system by taking people stream density data as a vertical coordinate and time data as a horizontal coordinate, taking the obtained people stream density data and the corresponding time data as unit points, enabling the unit points to fall into the rectangular coordinate system, and fitting the unit points into a people stream density curve in a curve fitting mode.
Further, the personal stream early warning system also comprises a notification module, and when the raspberry pi outputs a first signal, the notification module sends first information in a broadcasting mode; when the raspberry pi outputs the second signal or the third signal, the notification module sends second information in a point-to-point mode.
The invention has the beneficial effects that: the early warning of the stream density is realized by constructing a stream density curve by utilizing a raspberry group, solving an average slope and setting a certain judgment condition. The problem of current through artifical inaccurate that people stream density early warning brought is solved.
Drawings
In order to more clearly illustrate the technical solution in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below. It is clear that the described figures are only some embodiments of the invention, not all embodiments, and that a person skilled in the art can also derive other designs and figures from them without inventive effort.
Fig. 1 is a schematic system configuration diagram of the mainstream warning system.
Detailed Description
The conception, the specific structure, and the technical effects produced by the present invention will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the features, and the effects of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and those skilled in the art can obtain other embodiments without inventive effort based on the embodiments of the present invention, and all embodiments are within the protection scope of the present invention. In addition, all the coupling/connection relationships mentioned herein do not mean that the components are directly connected, but mean that a better coupling structure can be formed by adding or reducing coupling accessories according to specific implementation conditions. All technical characteristics in the invention can be interactively combined on the premise of not conflicting with each other.
Referring to fig. 1, a pedestrian flow early warning system based on raspberry pi includes: the device comprises a raspberry group, an infrared camera and a display module, wherein a neural network is stored in the raspberry group, and the infrared camera is used for acquiring thermodynamic diagrams of an area to be detected in real time in a preset detection period and transmitting the thermodynamic diagrams to the raspberry group; the raspberry pi comprises: importing the thermodynamic diagram into a neural network to obtain people stream density data; drawing people stream density data and corresponding time data into a people stream density curve; calculating the average slope of the people flow density curve, and outputting a first signal and controlling a display module to display a first state when the average slope is more than or equal to 1.8; when the average slope is less than 1.8 and more than or equal to 1, outputting a second signal and controlling the display module to display a second state; and when the average slope is less than 1 and more than or equal to 0.5, outputting a third signal and controlling the display module to display a third state.
The method specifically comprises the following steps: the neural network is trained in advance, and people flow density data can be extracted from the thermodynamic diagram in real time. Then, the people stream density data and the corresponding time data are drawn into a people stream density curve. The acquisition method of the people flow density curve specifically comprises the following steps: the method comprises the steps of establishing a rectangular coordinate system by taking people stream density data as a vertical coordinate and time data as a horizontal coordinate, taking the obtained people stream density data and the corresponding time data as unit points, enabling the unit points to fall into the rectangular coordinate system, and fitting the unit points into a people stream density curve in a curve fitting mode. And after the people flow density curve is obtained, obtaining the slope of the people flow density curve in a derivative mode. Wherein, the slope of the people flow density curve reflects the information of the change of the people flow density. Therefore, the change of the people flow density in the detection period can be reflected by calculating the average slope of the people flow density curve, and the future people flow density in the region to be detected can be predicted according to the change situation of the people flow density. By setting the judgment conditions, namely: when the average slope is larger than or equal to 1.8, controlling the display module to display a first state; when the average slope is less than 1.8 and more than or equal to 1, controlling the display module to display a second state; and when the average slope is less than 1 and more than or equal to 0.5, controlling the display module to display a third state. The first state reflects the information of extra congestion, the second state reflects the information of more congestion, and the third state reflects the information of general congestion. When the raspberry pi controls the display module to display the first state, a first signal is output outwards; when the raspberry pi controls the display module to display the second state, a second signal is output outwards; and when the raspberry pi controls the display module to display the third state, the raspberry pi outputs a third signal to the outside. Through the mode of externally outputting the first signal, the second signal and the third signal, the system is convenient to communicate with other equipment or systems, and provides a link for the system to be fused with external equipment or systems.
The system realizes early warning on the stream density by constructing a stream density curve by using the raspberry group, solving the average slope and setting certain judgment conditions. The problem of current through artifical inaccurate that people stream density early warning brought is solved.
In some embodiments, the first state, the second state, and the third state are reflected by the display module displaying different colors. The first state is reflected by displaying red, the second state is reflected by displaying orange, and the third state is reflected by displaying yellow. The manager is warned by visual information through different colors, so that the manager can conveniently judge the current situation.
In some preferred embodiments, the system further includes a preprocessing module, and the preprocessing module is configured to denoise the thermodynamic diagram before the thermodynamic diagram is introduced into the neural network. Preliminary denoising is carried out on the thermodynamic diagram through a preprocessing module, and the neural network is convenient to process.
In some preferred embodiments, the display module is a display screen.
In some preferred embodiments, the personal stream early warning system further comprises a notification module, wherein when the raspberry pi outputs a first signal, the notification module sends first information in a broadcast manner; when the raspberry pi outputs the second signal or the third signal, the notification module sends second information in a point-to-point mode. Through two notification modes, the notification is more efficient. Since the current people flow density reflected by the first signal is extremely crowded, the first information is sent in a broadcasting mode, so that all managers can be reminded of the current situation quickly, and all managers can know the current people flow density form at the fastest speed. Since the third signal of the second signal reflects the congestion and the general congestion, respectively, which is not urgent, the second information is sent to the specific object in a point-to-point manner, so that the specific manager can know the current density of people in time. The targeted notification mode can effectively and timely notify the manager to timely process the current people stream density situation.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that the present invention is not limited to the details of the embodiments shown and described, but is capable of numerous equivalents and substitutions without departing from the spirit of the invention and its scope is defined by the claims appended hereto.
Claims (7)
1. The utility model provides a people flow early warning system based on raspberry group which characterized in that includes:
a display module;
a raspberry pi storing a neural network for including: acquiring thermodynamic diagrams, and importing the thermodynamic diagrams into a neural network to obtain people flow density data; drawing people stream density data and corresponding time data into a people stream density curve; calculating the average slope of the people flow density curve, and controlling a display module to display a first state when the average slope is more than or equal to 1.8; when the average slope is less than 1.8 and more than or equal to 1, controlling the display module to display a second state; and when the average slope is less than 1 and more than or equal to 0.5, controlling the display module to display a third state.
2. The system of claim 1, wherein the system comprises: the device comprises a power supply, a power supply controller and a power supply, and further comprises an infrared camera, wherein the infrared camera shoots an area to be detected in real time to obtain a thermodynamic diagram in a preset detection period.
3. The system of claim 1, wherein the system comprises: when the raspberry pi controls the display module to display the first state, a first signal is output outwards; when the raspberry pi controls the display module to display the second state, a second signal is output outwards; and when the raspberry pi controls the display module to display the third state, the raspberry pi outputs a third signal to the outside.
4. The system of claim 1, wherein the system comprises: the device further comprises a preprocessing module, wherein the preprocessing module is used for denoising the thermodynamic diagram before the thermodynamic diagram is imported into the neural network.
5. The system of claim 1, wherein the system comprises: the display module is a display screen.
6. The system of claim 1, wherein the system comprises: the specific method for drawing the people stream density data and the corresponding time data into the people stream density curve comprises the following steps: the method comprises the steps of establishing a rectangular coordinate system by taking people stream density data as a vertical coordinate and time data as a horizontal coordinate, taking the obtained people stream density data and the corresponding time data as unit points, enabling the unit points to fall into the rectangular coordinate system, and fitting the unit points into a people stream density curve in a curve fitting mode.
7. The system of claim 1, wherein the system comprises: the raspberry pi comprises a raspberry pi, a first signal sending module and a second signal sending module, wherein the raspberry pi comprises a first signal and a second signal; when the raspberry pi outputs the second signal or the third signal, the notification module sends second information in a point-to-point mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010306535.7A CN111540162A (en) | 2020-04-17 | 2020-04-17 | Pedestrian flow early warning system based on raspberry group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010306535.7A CN111540162A (en) | 2020-04-17 | 2020-04-17 | Pedestrian flow early warning system based on raspberry group |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111540162A true CN111540162A (en) | 2020-08-14 |
Family
ID=71976781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010306535.7A Pending CN111540162A (en) | 2020-04-17 | 2020-04-17 | Pedestrian flow early warning system based on raspberry group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111540162A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113705382A (en) * | 2021-08-12 | 2021-11-26 | 捻果科技(深圳)有限公司 | Automatic identification method for all-time of passenger leaving aircraft |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463121A (en) * | 2014-12-08 | 2015-03-25 | 北京市新技术应用研究所 | Crowd density information obtaining method |
| CN106251578A (en) * | 2016-08-19 | 2016-12-21 | 深圳奇迹智慧网络有限公司 | Artificial abortion's early warning analysis method and system based on probe |
| JP2017215730A (en) * | 2016-05-31 | 2017-12-07 | 株式会社ナカヨ | Separation alarm device according to congestion state |
| CN108681791A (en) * | 2018-05-16 | 2018-10-19 | 北京理工大学 | A kind of density of stream of people prediction technique, device and storage medium |
| CN109087478A (en) * | 2018-08-22 | 2018-12-25 | 徐自远 | A kind of early warning of the anti-swarm and jostlement of intelligence and method of river diversion and system |
| CN109191841A (en) * | 2018-09-17 | 2019-01-11 | 天津中德应用技术大学 | A kind of urban transportation intelligent management system based on raspberry pie |
| CN109359520A (en) * | 2018-09-04 | 2019-02-19 | 汇纳科技股份有限公司 | People counting method, system, computer readable storage medium and server |
| CN109961166A (en) * | 2017-12-26 | 2019-07-02 | ***通信集团四川有限公司 | Narrow space stream of people's variation prediction method, apparatus calculates equipment and storage medium |
| CN110674750A (en) * | 2019-09-25 | 2020-01-10 | 浪潮软件集团有限公司 | Wisdom city personnel early warning and bootstrap system |
-
2020
- 2020-04-17 CN CN202010306535.7A patent/CN111540162A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463121A (en) * | 2014-12-08 | 2015-03-25 | 北京市新技术应用研究所 | Crowd density information obtaining method |
| JP2017215730A (en) * | 2016-05-31 | 2017-12-07 | 株式会社ナカヨ | Separation alarm device according to congestion state |
| CN106251578A (en) * | 2016-08-19 | 2016-12-21 | 深圳奇迹智慧网络有限公司 | Artificial abortion's early warning analysis method and system based on probe |
| CN109961166A (en) * | 2017-12-26 | 2019-07-02 | ***通信集团四川有限公司 | Narrow space stream of people's variation prediction method, apparatus calculates equipment and storage medium |
| CN108681791A (en) * | 2018-05-16 | 2018-10-19 | 北京理工大学 | A kind of density of stream of people prediction technique, device and storage medium |
| CN109087478A (en) * | 2018-08-22 | 2018-12-25 | 徐自远 | A kind of early warning of the anti-swarm and jostlement of intelligence and method of river diversion and system |
| CN109359520A (en) * | 2018-09-04 | 2019-02-19 | 汇纳科技股份有限公司 | People counting method, system, computer readable storage medium and server |
| CN109191841A (en) * | 2018-09-17 | 2019-01-11 | 天津中德应用技术大学 | A kind of urban transportation intelligent management system based on raspberry pie |
| CN110674750A (en) * | 2019-09-25 | 2020-01-10 | 浪潮软件集团有限公司 | Wisdom city personnel early warning and bootstrap system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113705382A (en) * | 2021-08-12 | 2021-11-26 | 捻果科技(深圳)有限公司 | Automatic identification method for all-time of passenger leaving aircraft |
| CN113705382B (en) * | 2021-08-12 | 2024-02-20 | 捻果科技(深圳)有限公司 | Automatic identification method for constant time of passengers leaving aircraft |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100527178C (en) | Automatic tracking display system for warn | |
| CN204087490U (en) | A kind of giving fatigue pre-warning system based on machine vision | |
| CN206585649U (en) | Passenger flow monitor device for subway station | |
| CN110636281B (en) | Real-time monitoring camera shielding detection method based on background model | |
| CN110154757A (en) | The multi-faceted safe driving support method of bus | |
| CN208984162U (en) | A kind of highway culvert product water monitoring system | |
| CN103517064A (en) | Real-time on-line self-diagnosis method and system for video monitoring equipment failure | |
| CN202939772U (en) | School bus monitoring system based on intelligent video | |
| CN106817560A (en) | It is a kind of to distributed terminal display device real-time monitoring system and monitoring method | |
| CN204946368U (en) | Pass through caution system at crossing | |
| CN107886677A (en) | A kind of the elderly's gait household monitoring system based on Kinect | |
| CN111540162A (en) | Pedestrian flow early warning system based on raspberry group | |
| CN206914320U (en) | A kind of vehicular traffic accident warning system | |
| CN104021653A (en) | Crossing on-duty status video analysis and warning system and method | |
| CN206038056U (en) | Bridge health monitoring system based on ZIGBEE | |
| CN205427566U (en) | Long -range basic station monitor system based on internet | |
| CN106385559A (en) | Three-dimensional monitoring system | |
| CN204904571U (en) | Alarm device is monitored to tunnel calamity danger | |
| CN203968273U (en) | A kind of video failure monitoring system for highway | |
| CN207380871U (en) | A kind of fired power generating unit Realtime Alerts monitoring system based on system subdivision | |
| CN204332069U (en) | A kind of expressway vehicle flowrate supervisory system | |
| CN206921109U (en) | A kind of behavior analysis system | |
| CN203186365U (en) | Station control center communication state monitoring system | |
| CN207588915U (en) | A kind of ward wireless supervisory control system | |
| CN206060981U (en) | Visual intelligent analysis monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |