CN112738468B - Safety early warning method for intelligent park - Google Patents
Safety early warning method for intelligent park Download PDFInfo
- Publication number
- CN112738468B CN112738468B CN202011564454.3A CN202011564454A CN112738468B CN 112738468 B CN112738468 B CN 112738468B CN 202011564454 A CN202011564454 A CN 202011564454A CN 112738468 B CN112738468 B CN 112738468B
- Authority
- CN
- China
- Prior art keywords
- early warning
- person
- data
- garden
- electronic fence
- 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 24
- 238000001514 detection method Methods 0.000 claims abstract description 59
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 230000001815 facial effect Effects 0.000 claims description 57
- 230000007613 environmental effect Effects 0.000 claims description 37
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 238000013480 data collection Methods 0.000 description 6
- 239000007789 gas Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000003912 environmental pollution Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a safety early warning method for an intelligent park, which comprises the steps of acquiring environment detection data and a detection area in the park, judging an early warning state when the environment detection data does not accord with a normal value, and setting a first electronic fence for the detection area; acquiring identity information and a destination of the person entering the garden, and pushing a destination path for the person entering the garden according to the first electronic fence and the destination; monitoring the distance between the position of an unregistered person in the garden entering persons and the destination path boundary, and if the distance between the position of the unregistered person and the destination path boundary is greater than a first distance threshold, sending first early warning information; and monitoring the distance between the position of a registered person or an unregistered person in the park entering persons and the boundary of the first electronic fence, and if the distance between the position of the registered person or the unregistered person and the boundary of the first electronic fence is smaller than a second distance threshold, sending second early warning information.
Description
Technical Field
The invention relates to the technical field of monitoring systems, in particular to a safety early warning method and system for an intelligent park.
Background
The intelligent park refers to a standard building or building group which is generally planned and constructed by governments (cooperation of civil enterprises and governments), has complete water supply, power supply, gas supply, communication, roads, storage and other supporting facilities and reasonable layout, and can meet the requirements of production and scientific experiments in a certain specific industry, and comprises an industrial park, a logistics park, a metropolitan industrial park, a scientific and technological park, an creative park and the like.
All can pass in and out a lot of people every day in the garden, whether the security guard personnel of garden can not effectual resolution be the inside personnel of garden, have now a lot of gardens to set up entrance guard and distinguish, but this kind of method still has certain defect, for example: the behavior of non-garden personnel entering the garden cannot be effectively monitored, and potential safety hazards exist; the people can not be informed to avoid the road sections which have environmental pollution or can not normally pass such as road construction and the like in the park; the potential danger exists for people who enter the garden and have potential threats, and people can not be evacuated effectively.
Content of application
The invention aims to provide an intelligent park safety early warning system and method, which overcome the defects of the prior art, distinguish whether personnel entering a park are personnel in the park through a safety early warning system, actively track and monitor non-park personnel, avoid the situation that the personnel cannot find the personnel entering the park, reasonably plan a path for the personnel entering the park, avoid the situation that the personnel cannot normally pass through the road sections with environmental pollution or road construction and the like, and effectively evacuate high-risk suspects entering the park, so that the potential safety hazard of the park is reduced.
The embodiment of the invention is realized by the following technical scheme: a safety early warning method for an intelligent park comprises the following steps:
s1, acquiring environment detection data and a detection area in a park, judging an early warning state when the environment detection data is not in accordance with a normal value, and setting a first electronic fence for the detection area;
s2, acquiring identity information and a destination of the person entering the garden, and pushing a destination path for the person entering the garden according to the first electronic fence and the destination;
s3, monitoring the distance between the position of an unregistered person in the garden entering persons and the destination path boundary, and if the distance between the position of the unregistered person and the destination path boundary is larger than a first distance threshold value, sending first early warning information;
and monitoring the distance between the position of a registered person or an unregistered person in the park entering persons and the boundary of the first electronic fence, and if the distance between the position of the registered person or the unregistered person and the boundary of the first electronic fence is smaller than a second distance threshold value, sending second early warning information.
According to a preferred embodiment, step S1 further includes: acquiring an environment detection data type, and extracting a corresponding early warning model from a preset environment data early warning model library according to the detection area and the environment detection data type;
and analyzing whether the detection data meet the detection data early warning rule or not according to the early warning model.
According to a preferred embodiment, step S1 further includes: the detection data are in a changing trend, so that the environmental detection data and the detection area in the park are obtained in real time, the early warning state is judged according to the early warning rules of the environmental detection data and the detection data which are obtained in real time, and the first electronic fence is updated in real time.
According to a preferred embodiment, step S2 further includes: acquiring image data of the person entering the garden, extracting facial features of the person entering the garden according to the image data, and comparing the facial features with facial feature data in the configuration file;
if the facial features of the person entering the garden are matched with the facial feature data in the configuration file, the person entering the garden is a registered person, a first early warning path is displayed for the registered person in a display unit, and the first early warning path is generated according to the first electronic fence and a destination matched with the facial feature data in the configuration file;
if the facial features of the park entering personnel are not matched with the facial feature data in the configuration file, the park entering personnel are unregistered personnel, audio data of the unregistered personnel are obtained, keywords containing position information are extracted from the audio data, an expected destination corresponding to the keywords is obtained from the configuration file, and a second early warning path is generated according to the first electronic fence and the expected destination and is displayed in a display unit.
According to a preferred embodiment, step S3 further includes: starting a second early warning path along-the-way camera to track and early warn non-registered personnel, and when the non-registered personnel deviate from the acquisition range of the second early warning path along-the-way camera and are greater than a first distance threshold value, sending first early warning information to a terminal platform;
and starting a first electronic fence periphery camera to monitor the periphery environment, and sending second early warning information to the terminal platform when the registered person or the unregistered person approaches the first electronic fence boundary and is smaller than a second distance threshold.
According to a preferred embodiment, the method further comprises: comparing the facial features of the unregistered person with data in a preset face database;
and if the facial features of the unregistered personnel are matched with the data, sending alarm information to a safety platform.
According to a preferred embodiment, the position information is obtained in real time through a camera on the second early warning path of the unregistered person matched with the data, a second electronic fence is arranged on the second early warning path of the unregistered person matched with the data, and the second electronic fence is updated in real time;
the display unit displays a third early warning path for subsequent personnel entering the garden, and the method comprises the following steps: and acquiring a destination corresponding to the facial features or keywords of the subsequent persons entering the garden in the configuration file, and generating a path respectively positioned outside a certain distance range from the first electronic fence boundary and the second electronic fence boundary according to the destination to acquire a third early warning path.
According to a preferred embodiment, the method further comprises: temporarily registering non-registered person information whose facial features do not match the facial feature data in the profile, the non-registered person information including facial features, image data, audio data, and an intended destination of the non-registered person.
According to a preferred embodiment, the temporarily registered non-registered person information is automatically deleted after a period of time without confirmation.
The invention also provides a safety early warning system for the intelligent park, which comprises: a data acquisition unit, an access control system and a terminal platform,
the data acquisition unit comprises a face image acquisition module, a pickup module and an environment data acquisition module, wherein the face image acquisition module is used for acquiring image data of people entering the garden, the pickup module is used for acquiring audio data of the people entering the garden, and the environment data acquisition module is used for acquiring environment data in the garden;
the access control system includes: the system comprises a face recognition unit, a voice recognition unit, a display unit and a configuration file unit, wherein the face recognition unit is connected with a face image acquisition module, a pickup module is connected with the voice recognition unit, the face recognition unit and the voice recognition unit are both connected with the configuration file unit, the face recognition unit is used for recognizing facial features of persons entering a garden in image data and comparing the facial features with facial feature data in the configuration file unit, and the voice recognition unit is used for recognizing keywords containing positioning information in audio data and indexing destinations corresponding to the keywords in the configuration file;
the system also comprises an electronic fence generating module and a path generating module, wherein the environmental data acquisition module is used for acquiring detection data and analyzing whether the detection data accord with normal values or not through an early warning model; the electronic fence generating module is used for setting a first electronic fence for the detection area according to the early warning result output by the early warning model; the path generation module is connected with the display unit and the electronic fence generation module, and is used for generating a destination path according to the first electronic fence and a destination and displaying the destination path in the display unit;
and the terminal platform is connected with the electronic fence generation module and the path generation module and is used for tracking and early warning the position information of the registered personnel or the unregistered personnel according to the destination path and the first electronic fence.
The technical scheme of the embodiment of the invention at least has the following advantages and beneficial effects: the invention can distinguish whether the person entering the park is a registered person, and actively track and monitor the unregistered person and the registered person, thereby avoiding that the person cannot find the person after entering the park or enters a dangerous area; and reasonably planning a path for the personnel entering the park, avoiding the road sections with environmental pollution and the like which cannot normally pass, and effectively evacuating the personnel entering the park with potential threats, thereby reducing the potential safety hazard of the park.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of a safety precaution method provided in embodiment 1 of the present invention;
fig. 2 is a schematic structural diagram of a safety warning system provided in embodiment 1 of the present invention;
icon: the system comprises a face image acquisition module, a face recognition unit, a configuration file unit, an environment data acquisition module, an electronic fence generation module, a terminal platform, a path generation module, a display unit, a pickup module and a voice recognition unit, wherein the face image acquisition module is 2, the face recognition unit is 3, the environment data acquisition module is 4, the electronic fence generation module is 5, the terminal platform is 6, the path generation module is 7, the display unit is 8, the pickup module is 9, and the voice recognition unit is 10.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
Example 1
Referring to fig. 1 and 2, the present embodiment provides a security early warning method and system for a smart campus, where the security early warning system includes a plurality of access control systems configured at entrances and exits of the campus, and the access control systems are controlled by a terminal platform 6 in the campus in a unified manner. The terminal platform 6 is responsible for unified management of the monitoring data of the access control system and other monitoring data in the park. The access control system may be implemented using a microprocessor-based device (e.g., computer, server) that executes a computer program stored in memory to perform the functions described in this embodiment. The access control system may be implemented using an existing campus access control system in the access control system. In this embodiment, access control system can go on the safety precaution of different degrees to different personnel of going into the garden, and concrete function is realized through further detailed description in this embodiment.
As described in the present embodiment, the access control system acquires the destination of the registered person in the campus based on the face recognition and acquires the expected destination of the unregistered person in the campus based on the voice recognition.
The access control system comprises a face recognition unit 2, a voice recognition unit 10, a display unit 8 and a configuration file unit 3; both the face recognition unit 2 and the voice recognition unit 10 may be implemented by software executed on an access control system. The profile unit 3 is used to store historical data, and in this embodiment, the historical data includes data of face characteristics of people entering the garden, voice keywords including positioning information, destinations corresponding to the voice keywords, and the like.
Further, the configuration file unit 3 may be replaced by a cloud storage or both of them may be collocated and used according to different situations (for example, selection is performed according to different network conditions), which is not described in detail again.
Although the present embodiment shows an access control system including a face recognition unit 2, a voice recognition unit 10, and a profile unit 3, one or more of these units or the functions provided by these units may be implemented by one or more systems (e.g., the terminal platform 6 and/or the cloud computing system in the present embodiment) at a remote location of the access control system.
The present embodiment provides a plurality of facial image capturing modules 1 (e.g., high definition cameras) which can be dispersedly disposed at a plurality of positions of a door so as to acquire image data from a plurality of viewpoints (and viewpoints for simultaneously viewing by people entering a garden to provide more detection opportunities). Facial recognition is simplified by the image of the person entering the garden from multiple viewpoints, whereby it is easier to acquire a view of the facial features corresponding to each person entering the garden in the profile unit 3. Further, the face recognition unit 2 is executed on the access control system to acquire image data, facial features of the person entering the garden are extracted from the image data and compared with the stored facial feature data in the configuration file unit 3, and if the facial features of the person entering the garden are matched with the stored facial feature data in the cloud storage unit, the person entering the garden is judged to be a registered person in the garden; if not, the person entering the garden is judged to be an unregistered person, and in order to reduce the potential safety hazard of the garden, safety early warning measures are executed for the unregistered person in the embodiment. The facial features of the persons entering the garden are also uploaded to the terminal platform 6, which is used for providing a face capturing basis for subsequent safety precaution measures, as described in further detail in this embodiment.
A plurality of pickup modules 9 (e.g., pickup microphones) may be distributed at various locations at the door access so as to acquire audio data from a plurality of audio collection points. Speech recognition is simplified by the plurality of audio acquisition points, whereby the intended destination of the corresponding keyword in the profile unit 3 is more easily acquired by the higher definition audio data. Further, the voice recognition unit 10 is executed on the access control system to acquire the audio data, and the voice keywords in the audio data of the unregistered person are extracted from the audio data and indexed in the voice keyword data stored in the configuration file unit 3 to acquire the expected destination corresponding to the voice keywords. In order to reduce the potential safety hazard of the campus, the safety precaution measures executed for the unregistered people in the embodiment include that the camera is started to an expected destination to capture the faces of the unregistered people based on the facial features of the unregistered people received by the terminal platform 6; further, the terminal platform 6 may also detect the traveling direction of the unregistered person based on image data collected by the cameras along the way. The unregistered person's movement may be tracked within the acquisition range of the camera along the way to determine whether the unregistered person is heading toward or deviating from an intended destination.
A plurality of environmental data collection modules 4 are installed in the garden, and in this embodiment, environmental data collection modules 4 set up on the guide rail to make can follow the guide rail and carry out diversified automatic environmental factor data acquisition. Environmental factor data in a campus range can be acquired more easily through a plurality of environmental data acquisition modules 4, and real-time acquisition of the environmental factor data is realized.
In this embodiment, the environmental detection data in the campus and the detection areas corresponding to the plurality of environmental data collection modules 4 are obtained by the plurality of environmental data collection modules 4; the early warning model is connected with the environmental data acquisition module 4, the early warning model is used for receiving abnormal detection data sent by the environmental data acquisition module 4 and analyzing whether the abnormality of the environmental detection data accords with a normal value or not, if the environmental detection data does not accord with the normal value, the early warning state is judged, namely, danger or potential safety hazard possibly exists in the detection area, an electronic fence generating instruction is sent to the electronic fence generating module 5, and the electronic fence generating module 5 is used for setting a first electronic fence for the detection area according to the detection data; the normal value in the environmental detection data is based on the concentration standard of various chemical gases in national standard which are harmless to human body.
Further, the environmental data acquisition module 4 also acquires an environmental detection data type, and extracts a corresponding early warning model from a preset environmental data early warning model library according to the detection area and the environmental detection data type; in this embodiment, the early warning model in the environmental data early warning model library is associated with the detection area and the environmental monitoring data type, for example, the detection area is in a chemical industry park, and the acquired environmental detection data type is gas leakage, then the corresponding chemical industry park gas leakage early warning model is extracted from the environmental data early warning model library, and whether the detection data meet normal values or not is analyzed according to the early warning model.
In the embodiment, a face image acquisition module 1 acquires image data of people entering a garden, and facial features of the people entering the garden are extracted through a facial recognition unit 2 and compared with facial feature data in a configuration file;
if the facial features of the person entering the garden are matched with the facial feature data in the configuration file, the person entering the garden is a registered person, and a first early warning path is displayed for the registered person in the display unit 8. The first early warning path is generated by the path generating module 7 according to the destination matched with the facial feature data in the configuration file and the first electronic fence boundary, so that the first early warning path can keep a certain safety distance from the first electronic fence boundary, and potential safety hazards are reduced.
If the facial features of the person entering the garden are not matched with the facial feature data in the configuration file, the person entering the garden is a non-registered person, audio data of the non-registered person are obtained, keywords containing position information are extracted from the audio data, an expected destination corresponding to the keywords is obtained from the configuration file, and a second early warning path is generated according to the first electronic fence and the expected destination and is displayed in the display unit 8. In this embodiment, the audio recognition model based on artificial intelligence may recognize keywords from audio data, and further, the keywords include "a certain company", "a certain park", or "a certain contact", and the audio recognition model is obtained by training a training sample including the keywords. Further, in the configuration file of the present embodiment, the keywords "a certain company", "a certain campus", or "a certain contact" correspond to location information associated therewith, for example, the expected destination of "a certain company" is located in building No. 1, zone E, in the campus; in this embodiment, the expected destination of the unregistered person is obtained from the audio data of the unregistered person in the manner of obtaining the keyword, and then a second warning path capable of keeping a certain safety distance from the boundary of the electronic fence is generated by the path generating module 7.
By planning paths for the garden entering personnel in the implementation, the garden entering personnel can reasonably avoid potential safety hazard areas in the garden or road sections which cannot normally pass, for example, the environmental data acquisition module 4 acquires that construction is carried out on a certain road section in the garden or that thorny gas is detected on the road section or fire disasters are likely to occur nearby the certain road section, and the environmental data acquisition module 4 sends the acquired information to the terminal platform 6 in real time to carry out environmental early warning; and the access control system recommends an early warning path which can bypass the road section based on the environment early warning information and the destination of the people entering the garden. So that personnel entering the garden can avoid the road sections, and the potential safety hazard of the garden is reduced. It is to be understood that, although the embodiment shows that the access control system recommends an early warning path that can bypass the above-mentioned road segment based on the environmental early warning information and the destination of the entering person, the function provided by the access control system may be implemented by one or more systems (e.g., the terminal platform 6 and/or the cloud computing system in the embodiment) at a remote location of the access control system.
Further, the terminal platform 6 is connected with the path generating module 7 and the face recognition unit 2, the terminal platform 6 receives the second early warning path, starts a camera along the second early warning path to perform tracking monitoring after non-registered people enter the park, monitors the distance between the position of the non-registered people in the park and the destination path boundary, if the distance between the position of the non-registered people and the destination path boundary is greater than a first distance threshold, sends first early warning information to the terminal platform 6, the terminal platform 6 starts a camera at the expected destination of the non-registered people to determine whether the non-registered people reach the expected destination, and if the non-registered people exceed a time threshold for reaching the expected destination, the security personnel start to correctly guide the non-registered people.
Further, the terminal platform 6 receives the first early warning path and the second early warning path to start a camera around the first electronic fence to monitor surrounding information, the distance between the position of a registered person or an unregistered person in the personnel entering the garden and the boundary of the first electronic fence is monitored, if the distance between the position of the registered person or the unregistered person and the boundary of the first electronic fence is smaller than a second distance threshold value, the second early warning information is sent to the terminal platform 6, and the terminal platform 6 receives the second early warning information to arrange that a security protection person moves out and runs into the boundary of the first electronic fence to be correctly guided.
Further, because the detected data that environmental data collection module 4 gathered are the trend of change, for example can volatilize etc. after certain gas leakage in chemical industry garden, so this embodiment acquires the environmental detection data and the detection area in the garden in real time through environmental data collection module 4, judge the early warning state according to the environmental detection data that acquire in real time and detection data early warning rule, cancel the early warning state when environmental detection data accords with the normal value, real-time update or relieve first fence, avoid setting up the normal current that first fence influences personnel in the garden for a long time.
Further, in the embodiment, the image of the unregistered person collected by the face image collection module 1 is identified by the face identification unit 2 and then compared with data in a preset face database; and if the facial features of the unregistered personnel are matched with the data, sending alarm information to the safety platform.
Further, position information is obtained in real time through a camera on a second early warning path of the unregistered person matched with the data, a second electronic fence is arranged on the second early warning path of the unregistered person matched with the data, and the second electronic fence is updated in real time;
the display unit 8 displays a third early warning path for subsequent personnel entering the garden, and the method comprises the following steps: and acquiring a destination corresponding to the facial features or keywords of the subsequent user in the configuration file, generating a path respectively outside a certain distance range from the first electronic fence boundary and the second electronic fence boundary according to the destination, and acquiring a third early warning path. So that subsequent personnel entering the garden can reasonably avoid the dangerous personnel entering the garden before, and the risk of being clamped is reduced; and dangerous personnel can be placed in the park, and the extension of actions can be conveniently caught on the premise of not causing personal injury to the personnel in the park.
Furthermore, in order to further reduce the potential safety hazard of the campus and facilitate follow-up of follow-up accidents, the access control system of the embodiment further includes a temporary registration module, where the temporary registration module is configured to temporarily register information of non-registered people whose facial features do not match facial feature data in the configuration file, and store the temporary registration information after information confirmation in the configuration file, where the information of the non-registered people includes facial features, image data, audio data, and an expected destination of the non-registered people.
Further, in order to improve the face feature matching efficiency and the voice keyword indexing speed, the temporarily registered non-registered person information is not confirmed in the present embodiment and is automatically deleted after a certain period of time (for example, 24 hours). By erasing the stored data in the configuration file so that the amount of data that needs to be indexed in an attempt to match facial features with voice keywords is reduced.
Referring to fig. 2, the present embodiment further provides a safety precaution system for an intelligent park, using the above method, in the present embodiment, the system includes: a data acquisition unit, an access control system and a terminal platform 6,
the data acquisition unit comprises a face image acquisition module 1, a pickup module 9 and an environment data acquisition module 4, wherein the face image acquisition module 1 is used for acquiring image data of people entering the garden, the pickup module 9 is used for acquiring audio data of the people entering the garden, and the environment data acquisition module 4 is used for acquiring environment data in the garden;
the access control system includes: the voice recognition system comprises a face recognition unit 2, a voice recognition unit 10, a display unit 8 and a configuration file unit 3, wherein the face recognition unit 2 is connected with a face image acquisition module 1, a pickup module 9 is connected with the voice recognition unit 10, both the face recognition unit 2 and the voice recognition unit 10 are connected with the configuration file unit 3, the face recognition unit 2 is used for recognizing facial features of persons entering a garden in image data and comparing the facial features with facial feature data in the configuration file unit 3, and the voice recognition unit 10 is used for recognizing keywords containing positioning information in audio data and performing destination indexing of the corresponding keywords in the configuration file;
the system also comprises an electronic fence generating module 5 and a path generating module 7, wherein the environmental data acquisition module 4 is used for acquiring detection data and analyzing whether the detection data accord with normal values or not through an early warning model; the electronic fence generating module 5 is used for setting a first electronic fence for the detection area according to the early warning result output by the early warning model; the path generating module 7 is connected with the display unit 8 and the electronic fence generating module 5, and the path generating module 7 is used for generating a destination path according to the first electronic fence and the destination and displaying the destination path in the display unit 8;
the terminal platform 6 is connected with the electronic fence generation module 5 and the path generation module 7, and is used for tracking and early warning the position information of the registered person or the unregistered person according to the destination path and the first electronic fence.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A safety early warning method for an intelligent park is characterized by comprising the following steps:
s1, acquiring environment detection data and a detection area in a park, judging an early warning state when the environment detection data is not in accordance with a normal value, and setting a first electronic fence for the detection area;
s2, acquiring identity information and a destination of a person entering the garden, and pushing a destination path for the person entering the garden according to the first electronic fence and the destination;
s3, monitoring the distance between the position of an unregistered person in the garden entering persons and the destination path boundary, and if the distance between the position of the unregistered person and the destination path boundary is larger than a first distance threshold value, sending first early warning information;
monitoring the distance between the position of a registered person or an unregistered person in the park entering persons and the boundary of the first electronic fence, and if the distance between the position of the registered person or the unregistered person and the boundary of the first electronic fence is smaller than a second distance threshold, sending second early warning information;
step S2 further includes: acquiring image data of the person entering the garden, extracting facial features of the person entering the garden according to the image data, and comparing the facial features with facial feature data in the configuration file;
if the facial features of the person entering the garden are matched with the facial feature data in the configuration file, the person entering the garden is a registered person, a first early warning path is displayed for the registered person in a display unit (8), and the first early warning path is generated according to the first electronic fence and a destination matched with the facial feature data in the configuration file;
if the facial features of the person entering the garden are not matched with the facial feature data in the configuration file, the person entering the garden is a non-registered person, audio data of the non-registered person are obtained, keywords containing position information are extracted from the audio data, an expected destination corresponding to the keywords is obtained from the configuration file, and a second early warning path is generated according to the first electronic fence and the expected destination and is displayed in a display unit (8);
the method further comprises the following steps:
comparing the facial features of the unregistered person with data in a preset face database;
if the facial features of the unregistered personnel are matched with the data, sending alarm information to a safety platform;
the method comprises the steps that position information is obtained in real time through a camera along a second early warning path of a non-registered person matched with data, a second electronic fence is arranged on the second early warning path of the non-registered person matched with the data, and the second electronic fence is updated in real time;
the display unit (8) displays a third early warning path for subsequent personnel entering the garden, and the method comprises the following steps: and acquiring a destination corresponding to the facial features or keywords of the subsequent persons entering the garden in the configuration file, and generating a path respectively positioned outside a certain distance range from the first electronic fence boundary and the second electronic fence boundary according to the destination to acquire a third early warning path.
2. The intelligent park safety precaution method according to claim 1, wherein the step S1 further includes: acquiring an environment detection data type, and extracting a corresponding early warning model from a preset environment data early warning model library according to the detection area and the environment detection data type;
and analyzing whether the detection data accord with normal values or not according to the early warning model.
3. The intelligent park safety precaution method according to claim 2, wherein the step S1 further includes: the detection data are in a changing trend, so that the environmental detection data and the detection area in the park are obtained in real time, the early warning state is judged according to the early warning rules of the environmental detection data and the detection data which are obtained in real time, and the first electronic fence is updated in real time.
4. The intelligent campus security precaution method of claim 1, wherein the step S3 further comprises:
starting a second early warning path along-the-way camera to track and early warn non-registered personnel, and when the non-registered personnel deviate from the acquisition range of the second early warning path along-the-way camera and are greater than a first distance threshold value, sending first early warning information to a terminal platform (6);
and starting a first electronic fence periphery camera to monitor the periphery environment, and sending second early warning information to a terminal platform (6) when the registered person or the unregistered person approaches the first electronic fence boundary and is smaller than a second distance threshold.
5. The intelligent park safety precaution method according to claim 1, wherein the method further includes:
temporarily registering non-registered person information whose facial features do not match the facial feature data in the profile, the non-registered person information including facial features, image data, audio data, and an intended destination of the non-registered person.
6. The intelligent campus security precaution method of claim 5 wherein said non-registered personnel information that is temporarily registered is automatically deleted after a period of time without confirmation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011564454.3A CN112738468B (en) | 2020-12-25 | 2020-12-25 | Safety early warning method for intelligent park |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011564454.3A CN112738468B (en) | 2020-12-25 | 2020-12-25 | Safety early warning method for intelligent park |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112738468A CN112738468A (en) | 2021-04-30 |
| CN112738468B true CN112738468B (en) | 2022-07-08 |
Family
ID=75616645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011564454.3A Active CN112738468B (en) | 2020-12-25 | 2020-12-25 | Safety early warning method for intelligent park |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112738468B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269124B (en) * | 2021-06-09 | 2023-05-09 | 重庆中科云从科技有限公司 | Object recognition method, system, equipment and computer readable medium |
| CN113689648B (en) * | 2021-08-25 | 2022-10-18 | 深圳市润立方科技有限公司 | Intelligent community security management system and method based on Internet of things |
| CN114973153B (en) * | 2022-07-27 | 2022-11-04 | 广州宏途数字科技有限公司 | Smart campus security detection method, device, equipment and storage medium |
| CN115909617A (en) * | 2023-01-06 | 2023-04-04 | 之江实验室 | Visitor early warning method, system and device based on multi-source heterogeneous data |
| CN116070989A (en) * | 2023-03-06 | 2023-05-05 | 知鱼智联科技股份有限公司 | Smart park outside personnel management method, system and storage medium |
| CN117172463A (en) * | 2023-08-28 | 2023-12-05 | 湖北顺安伟业科技有限公司 | Park monitoring data management system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101419752A (en) * | 2008-12-04 | 2009-04-29 | 山东警察学院 | Real-time positioning scheduling management terminal device for police motorcycle |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886427B (en) * | 2014-04-04 | 2017-10-17 | 四川天翼网络服务有限公司 | The sealed system and method for flattening Command Information System ring layer |
| CN107240226B (en) * | 2017-07-26 | 2020-11-10 | 广州安电测控技术有限公司 | Nearly electric early warning device and system |
| CN109462840A (en) * | 2017-08-16 | 2019-03-12 | 苏州米辰科技有限公司 | A kind of garden intelligence guidance system |
| CN107590891A (en) * | 2017-09-26 | 2018-01-16 | 四川仪岛科技有限公司 | A kind of recognition of face access control system of residential community and control method |
| CN110060442A (en) * | 2019-03-20 | 2019-07-26 | 云南电网有限责任公司文山供电局 | Personnel are anti-in station based on UWB is strayed into region modeling method |
| DE212020000603U1 (en) * | 2019-04-25 | 2022-01-25 | Guangxi Xijao Rail Transit Industry Technology R&D Co., Ltd. | Open Intelligent Screening Channel System |
| CN110191424B (en) * | 2019-05-16 | 2021-06-15 | 武汉数矿科技有限公司 | Specific suspect track generation method and apparatus |
| CN111144534A (en) * | 2019-12-23 | 2020-05-12 | 王常亮 | Temporary access control card for navigation and use method thereof |
| CN111539579B (en) * | 2020-04-30 | 2022-08-16 | 陕西金合信息科技股份有限公司 | Method and device for determining emergency escape route |
-
2020
- 2020-12-25 CN CN202011564454.3A patent/CN112738468B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101419752A (en) * | 2008-12-04 | 2009-04-29 | 山东警察学院 | Real-time positioning scheduling management terminal device for police motorcycle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112738468A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112738468B (en) | Safety early warning method for intelligent park | |
| KR101949525B1 (en) | Safety management system using unmanned detector | |
| AU2020203351B2 (en) | Drone-augmented emergency response services | |
| CN112132045B (en) | Community personnel abnormal behavior monitoring scheme based on computer vision | |
| CN113706355A (en) | Method for building intelligent emergency system of chemical industry park | |
| CN112785798B (en) | Behavior analysis method for constructors of power substation engineering construction project | |
| CN116962460B (en) | Intelligent park operation management system and method | |
| CN103259206A (en) | Transformer substation operation safety management and control system based on computer vision locating technology | |
| CN112112629A (en) | Safety business management system and method in drilling operation process | |
| CN110674761B (en) | Regional behavior early warning method and system | |
| CN111753780B (en) | Transformer substation violation detection system and violation detection method | |
| CN111294561A (en) | Video-based online patrol method, electronic device, storage medium and system | |
| CN210222962U (en) | Intelligent electronic fence system | |
| CN112866647A (en) | Intelligent property management system based on smart community | |
| CN115457449B (en) | Early warning system based on AI video analysis and monitoring security protection | |
| CN112885013A (en) | Monitoring and early warning method and device and readable storage medium | |
| CN112381435A (en) | Gridding directional pushing management method for dynamic risk in hydropower station operation process | |
| CN109345787A (en) | A kind of anti-outer damage monitoring and alarming system of the transmission line of electricity based on intelligent image identification technology | |
| CN114329106A (en) | Big data analysis system and method for community | |
| CN117975614A (en) | Intelligent maintenance method, system and storage medium for power transformation and distribution room | |
| CN117912186A (en) | Intelligent security linkage early warning system based on big data service | |
| CN113112744A (en) | Security management method and device, electronic equipment and storage medium | |
| CN112541656A (en) | Intelligent security integrated platform with risk potential prediction capability | |
| KR101516672B1 (en) | Method for detecting video that utilize smarter video control center using the same system | |
| CN118015811B (en) | Intelligent land remote supervision method, system, device and medium thereof |
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 |