CN109598885A - Monitoring system and its alarm method - Google Patents
Monitoring system and its alarm method Download PDFInfo
- Publication number
- CN109598885A CN109598885A CN201811578222.6A CN201811578222A CN109598885A CN 109598885 A CN109598885 A CN 109598885A CN 201811578222 A CN201811578222 A CN 201811578222A CN 109598885 A CN109598885 A CN 109598885A
- Authority
- CN
- China
- Prior art keywords
- alert
- monitoring
- video data
- data
- region
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/16—Actuation by interference with mechanical vibrations in air or other fluid
- G08B13/1654—Actuation by interference with mechanical vibrations in air or other fluid using passive vibration detection systems
- G08B13/1672—Actuation by interference with mechanical vibrations in air or other fluid using passive vibration detection systems using sonic detecting means, e.g. a microphone operating in the audio frequency range
-
- 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
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of alarm method, the following steps are included: obtaining monitor video data and monitoring audio data, the monitor video data and the monitoring audio data are acquired the alarm method by being set to the monitoring device in target monitoring region；The monitor video data and the monitoring audio data are inputted into default alert identification model；According to the recognition result of the default alert identification model output, judge whether the target monitoring region alert occurs；When alert occurs in the target monitoring region, alarm signal is exported.The invention also discloses a kind of monitoring systems.The present invention is directed to realize that alert is timely handled, the safety of monitoring area is improved.
Description
Technical field
The present invention relates to field of security technology more particularly to alarm method and monitoring systems.
Background technique
In daily life, it is general by manually reporting when alert occur in the public places such as cell, office building, school, market
It is alert, it may sometimes be helped due to nobody and alarm or be delayed alarm without finding alert in time, which results in many alerts
Do not handled in time.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of alarm methods, it is intended to realize that alert is timely handled, mention
The safety of high monitoring area.
To achieve the above object, the present invention provides a kind of alarm method, the alarm method the following steps are included:
Monitor video data and monitoring audio data are obtained, the monitor video data and the monitoring audio data pass through
Monitoring device set on target monitoring region acquires；
The monitor video data and the monitoring audio data are inputted into default alert identification model；
According to the recognition result of the default alert identification model output, judge whether the target monitoring region warns
Feelings；
When alert occurs in the target monitoring region, alarm signal is exported.
Optionally, the step of output alarm signal includes:
Obtain the location information of the monitoring device；
The alarm signal is generated according to the recognition result and the location information；
The alarm signal is sent to alarm platform.
Optionally, after the step of output alarm signal, further includes:
Receive the feedback information that the alarm platform is returned based on the alarm signal；
When the feedback information is to confirm the information of the alert, the corresponding tracking information of the alert is obtained；
The corresponding tracking information of the alert is sent to the alarm platform.
Optionally, described the step of obtaining the alert corresponding tracking information, includes:
Obtain the first video data and the first audio data that the monitoring device acquires in real time；
Judge whether the alert is currently located in the target monitoring region according to the first video data；
If the alert is currently located in the target monitoring region, by first video data and the first audio data
As the tracking information.
Optionally, described according to the first video data and judge the alert currently whether positioned at the target monitoring region
After interior step, further includes:
If the alert is currently located in the target monitoring region, determine that the migration side of position occurs for the alert
To；
The tracking information is generated according to the migratory direction.
Optionally, described to judge whether the alert is currently located in the target monitoring region according to the first video data
The step of include:
In the monitor video data, the image of the corresponding risk identification of the alert is determined；
Whether the picture frame for judging first video data includes image with the images match of the risk identification；
If the picture frame of first video data includes the image with the images match of the risk identification, institute is determined
Alert is stated to be currently located in the target monitoring region；
If the picture frame of first video data does not include the image with the images match of the risk identification, determine
The alert is currently located in the target monitoring region.
Optionally, the step of migratory direction of determination alert generation position includes:
The video data that the monitoring device acquires in the preset time period before current time is obtained, as the second view
Frequency evidence；
Determine motion profile of the image of the risk identification in second video data；
The migratory direction is determined according to the motion profile.
Optionally, described the step of generating the tracking information according to the migratory direction, includes:
Determine the region of the monitoring device；
Judge in the region of the monitoring device in the migratory direction, if there are other than the monitoring device
Other monitoring devices；
When there are other described monitoring devices, the video data of other monitoring devices acquisition is obtained, as third
Video data obtains the audio data of other monitoring devices acquisition, as the second audio data；
It will be described when the picture frame of the third video data includes the image with the images match of the risk identification
Third video data and the second audio data are as the tracking information.
Optionally, before the step of acquisition monitor video data and monitoring audio data further include:
History monitoring data is obtained, the history monitoring data includes history video data and its corresponding historical acoustic frequency
According to；
The monitoring data in the history monitoring data comprising effective monitoring information is extracted, as data sample；
Determine that the data sample in the data sample comprising alert information determines the number as positive sample training set
According to the data sample for not including alert information in sample, as negative sample training set；
By positive sample training set described in machine learning and the negative sample training set, the default alert identification mould is obtained
Type.
In addition, to achieve the goals above, the application also proposes that a kind of monitoring system, the monitoring system include:
Monitoring device, including video acquisition device and audio frequency acquisition device；
Warning device, including memory, processor and be stored on the memory and can run on the processor
Alert program, the processor connect with the video acquisition device and the audio frequency acquisition device respectively, the alarm journey
The step of as above described in any item alarm methods are realized when sequence is executed by the processor.
A kind of alarm method that the embodiment of the present invention proposes, by preformed default alert identification model, by pre-
If alert identification module analyzes the monitoring device monitor video data collected and monitoring audio data in target monitoring region, root
When determining that alert occurs in target monitoring region according to recognition result, alarm signal is exported, this process can be certainly without artificial participation
Dynamic to identify alert, immediately monitoring region nobody can also export alarm signal when alert occurs in time, obtain alert can
It to timely handling, will not further expand, improve the safety of monitoring area.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the hardware running environment of monitoring system of the embodiment of the present invention；
Fig. 2 is the hardware structural diagram of warning device in Fig. 1；
Fig. 3 is the flow diagram of alarm method of embodiment of the present invention first embodiment；
Fig. 4 is the flow diagram of alarm method of embodiment of the present invention second embodiment；
Fig. 5 is the flow diagram of alarm method of embodiment of the present invention 3rd embodiment；
Fig. 6 is the flow diagram of alarm method of embodiment of the present invention fourth embodiment；
Fig. 7 is the flow diagram of the 5th embodiment of alarm method of the embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are: obtaining monitor video data and monitoring audio data, the monitoring
Video data and monitoring audio data are acquired by being set to the monitoring device 100 in the target monitoring region；The monitoring is regarded
Frequency evidence and the monitoring audio data input default alert identification model；According to the identification knot of the default alert identification model
Fruit, judges whether the target monitoring region alert occurs；When alert occurs in the target monitoring region, alarm signal is exported
Number.
Due to the prior art, alert can be made not handled in time dependent on artificial alarm.
The present invention provides above-mentioned solution, realizes that alert is timely handled, improves the safety of monitoring area.
The present invention proposes a kind of monitoring system, can be set to the public places such as cell, office building, school, market, station, use
In the security situation for monitoring above-mentioned place, is identified and alarmed particularly for the alert to above-mentioned place.Identified alert
It may particularly include the situation of the harm such as fire, robbery, drowned, traffic accident person or property safety.
In embodiments of the present invention, referring to Fig.1, monitoring system includes monitoring device 100 and warning device 200.Monitoring is set
Standby 100 include video acquisition device and audio frequency acquisition device, and video acquisition device is used to acquire the monitor video number of monitoring area
According to audio frequency acquisition device is used to acquire the monitoring audio data of monitoring area.
Monitoring area is the region equipped with monitoring device 100.Wherein, warning device 200 can be for independently of monitoring device 100
And the equipment communicated to connect with monitoring device 100, in addition, warning device 200 is also built-in to be used as monitoring in monitoring device 100
One functional module of equipment 100.According to the security protection requirement of different places, monitoring device 100 can have multiple and distribution to be set to not
Same monitoring area.
Referring to Fig. 2, warning device 200 specifically includes processor 2001, such as CPU, memory 2002,.Memory 2002
It can be high speed RAM memory, be also possible to stable memory (non-volatile memory), such as magnetic disk storage.
Memory 2002 optionally can also be the storage device independently of aforementioned processor 2001.Processor 2001 and memory 2002
Connection.The processor 2001 is connect with the video acquisition device and the audio frequency acquisition device respectively, is adopted with obtaining video
Acquisition means and audio frequency acquisition device data collected.
It will be understood by those skilled in the art that device structure shown in Fig. 1 does not constitute the restriction to equipment, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.
As shown in Fig. 2, as may include alert program in a kind of memory 2002 of computer storage medium.
In equipment shown in Fig. 1, processor 2001 can be used for calling the alert program stored in memory 2002, and
Execute the operation of the correlation step of alarm method in following embodiment.
In addition, the present invention also proposes a kind of alarm method, the identification applied to alert.For example, using alarm of the invention
Method is not gone out for certain owner more days after going home again, and people is in that underwater is motionless, and people collides with vehicle for a long time, is built
Object burning, object falls and its speed of falling can be judged as warning more than pre-set velocity etc. in default alert identification module
Feelings simultaneously export alarm signal.
Specifically, proposing alarm method first embodiment of the present invention referring to Fig. 3.In the present embodiment, the alarm method
Include:
Step S10 obtains monitor video data and monitoring audio data, the monitor video data and monitoring audio data
Monitoring device 100 by being set to target monitoring region acquires；
Specifically, the monitor video data collected of monitoring device 100 set on target monitoring region can be obtained in real time,
Obtain the monitoring audio data collected of monitoring device 100 for being set to target monitoring region in real time simultaneously.
Target monitoring region is the region of the need progress alert monitoring where monitoring device 100.
The monitor video data and the monitoring audio data are inputted default alert identification model by step S20；
It should be noted that default alert identification model can be convolutional neural networks model, super-resolution test sequence mould
At least one of pattern type or region method model based on convolutional neural networks feature model.
Default alert identification model analyzes the monitor video data and monitoring audio data of input.Specifically, pre-
If alert identification model analyzes target object (people, vehicle, object etc.) and its action trail in monitor video data first, adopt simultaneously
The acoustic information (such as sound type, voice messaging) in monitoring audio data is analyzed with default alert identification model.If analysis
The obtained Data Matching in target object and its action trail and acoustic information and positive sample training set, then there are alerts for output
Recognition result；If analyzing the data in obtained target object and its action trail and acoustic information and negative sample training set
Match, then the recognition result of alert is not present in output.
Specifically, target object and its action trail can be calculated according to default alert identification model in different alert types
The first distribution probability in samples of video data.Obtain different types of sound corresponding to the maximum alert type of the first distribution probability
Frequency data sample calculates the second distribution probability that acoustic information is concentrated in different types of audio data.It wherein, can be according to difference
The sound type that alert type is likely to occur classifies to audio data collection, such as explosive sound, shout in fire alert
Deng impact sound, shout, quarrel in traffic accident alert etc..According to the first distribution probability and its corresponding second distribution probability
The total distributed probability of target object and its action trail and acoustic information in different alert types is calculated, when maximum total distributed
When probability is greater than or equal to preset threshold, then the target object and its action trail and acoustic information and positive sample analyzed are instructed
Practice the Data Matching concentrated, exportable includes the recognition result there are alert.Further, the alert class of total distributed maximum probability
Type is as current alert type, in addition, alert rank can be also determined according to alert type, therefore, in addition to including that there are alerts
Recognition result outside, the also exportable recognition result including alert type and alert rank.
Wherein, different scene types can be correspondingly provided with different default alert identification models.Scene type can be wrapped specifically
Include factory, swimming pool, market, road etc..Therefore, it can first determine that scene type locating for the target monitoring region；According to
Identified scene type can obtain corresponding default alert identification module, by monitor video data and monitoring audio data input
It is analyzed in acquired default alert identification model, to improve the accuracy of recognition result.
Step S30 judges that the target monitoring region is according to the recognition result of the default alert identification model output
It is no alert occur；
Recognition result specifically includes alert, alert type, alert rank etc. whether occur.Wherein, alert type can be specific
Including robbery, steals, hurts sb.'s feelings, is traffic accident, fire, drowned etc..Alert rank may particularly include serious alert, medium alert, slight
Alert etc..It can determine whether target monitoring region alert occurs according to recognition result.
Step S40 exports alarm signal when alert occurs in the target monitoring region.
It, can be further according to alert type, the alert rank in recognition result when alert occurs in target monitoring region
The equal corresponding alarm signal of outputs.For example, corresponding alarm platform can be determined according to alert type, output alarm signal to institute is really
Fixed alarm platform.Such as fire corresponds to fire protection warning platform, corresponding public security alarm platform etc. of hurting sb.'s feelings.
In addition, corresponding security protection unit can be also determined according to alert rank, output alarm signal to identified security protection list
Position.For example, when there is slight alert, the security personnel of exportable alarm signal to target monitoring areas adjacent, when in appearance
When equal alerts, exportable alarm signal to public security alarm platform at county level, when there is serious alert, exportable alarm signal is extremely
The public security alarm platform of area's grade.
In addition, can also be by the way that acousto-optic hint equipment, control acousto-optic hint equipment output alarm be arranged in target monitoring region
The corresponding sound and light signal of signal prompts the people of target monitoring areas adjacent to find the alert in target monitoring region, so that alert can
It is handled in time.For example, capable of emitting audio warning when on fire, prompts the personnel of surrounding to come to put out a fire in time, avoids the intensity of a fire
Further expansion.
A kind of alarm method proposed in the present embodiment, by preformed default alert identification model, by pre-
If alert identification module analyzes the monitor video data collected of monitoring device 100 and monitoring audio frequency number in target monitoring region
According to when determining that alert occurs in target monitoring region according to recognition result, output alarm signal, this process is not necessarily to artificial participation just
Alert can be automatically identified, immediately monitoring region nobody can also export alarm signal when alert occurs in time, make alert
It is timely handled, will not further be expanded, improve the safety of monitoring area.
Specifically, in the above-described embodiments, referring to Fig. 4, the step for obtaining monitor video data and monitoring audio data
Before rapid further include:
Step S00, obtains history monitoring data, and the history monitoring data includes history video data and its corresponding goes through
History audio data；
Specifically, the monitoring data collected of monitoring device 100 in different monitoring region can all be stored.History monitoring
Data are monitoring data stored in past preset time period (such as 5 years, 10 years) built-in storage, specifically may include history view
Frequency evidence and its corresponding history audio data.History audio data is the audio data acquired simultaneously with history video data,
The history video data of same time acquisition is corresponded to each other with history audio data.
Step S01 extracts the monitoring data in the history monitoring data comprising effective monitoring information, as data sample
This；
Effective monitoring information includes the sound that dynamic image and decibels are greater than or equal to preset value.Specifically, will include
The history video data of dynamic image further obtains the corresponding historical acoustic frequency of samples of video data as samples of video data
According to by the history audio data comprising decibels more than or equal to the sound of preset value as audio data sample.It is obtained
The data sample of samples of video data and audio data sample as default alert identification model.
Step S02 determines the data sample in the data sample comprising alert information, as positive sample training set, really
The data sample for not including alert information in the fixed data sample, as negative sample training set；
Specifically, the intersection record between memory and alarm platform can be obtained, according to intersection record determining data sample
In the data sample once transferred by public security department be the data sample comprising alert information.It further, will be not by the Ministry of Public Security
The data sample that door is transferred is supplied to professional Security Personnel and obtains the classification information of professional Security Personnel's feedback, according to classification letter
Breath distinguishes the data sample in data sample comprising alert information and the data sample not comprising alert information.Wherein, comprising police
The data sample of feelings information is as positive sample training set.
Step S03 obtains the default police by positive sample training set described in machine learning and the negative sample training set
Feelings identification model.
Classification is carried out to positive sample training set and negative sample training set by machine learning and regression is analyzed, obtains video
Data and audio data with whether there is the correlation of alert.Specifically, in the study of positive sample training set, it can be according to alert
Type, alert rank etc. carry out deep learning to sample data therein, make default alert identification model in addition to may identify whether
Occur outside alert, also exportable alert type, alert rank etc. when there is alert.
In the present embodiment, history monitoring data is obtained, history monitoring data is cleaned, extraction is obtained comprising effective
The monitoring data of monitoring information carries out classification learning as data sample, then to data sample, and machine learning on the one hand can be improved
Efficiency, on the other hand may filter that the monitoring data not comprising effective monitoring information, guarantee is formed by default alert identification
The accuracy of model.
Based on the above embodiment, the second embodiment of the application alarm method is proposed.In a second embodiment, reference Fig. 5,
The step of output alarm signal includes:
Step S41 obtains the location information of the monitoring device 100；
Each monitoring device 100 is associated with the location information of its position, and location information can be stored in warning device
In 200 memory, it can also be stored in the memory of monitoring device 100 itself.Location information may particularly include street information,
Number, enterprise name, cell name etc..
Step S42 generates the alarm signal according to the recognition result and the location information；
When recognition result is that target monitoring region alert occurs, the judgement result of alert, the corresponding monitoring of alert are regarded
Frequency evidence and monitoring audio data, alert type, alert rank, the position for occurring alert encapsulate form alarm signal together.
The alarm signal is sent to alarm platform by step S43.
In the present embodiment, recognition result and location information are sent to alarm platform simultaneously, know policeman person
Dawn occurs quickly to know the position that alert occurs while alert, timely to reach corresponding position processing alert.
Further, in a second embodiment, after the step of reference Fig. 5, the output alarm signal, further includes:
Step S50 receives the feedback information that the alarm platform is returned based on the alarm signal；
After alarm platform receives alarm signal, the personnel of being informed of a case can be to the monitor video data and monitoring sound in alarm signal
Frequency judges whether target monitoring region alert really occurs according to being confirmed, if it is determined that target monitoring region is warned really
Feelings then return to the information of confirmation alert, if it is determined that target monitoring region does not occur alert, then to report to warning device 200
Alert equipment 200 returns to the information of negative alert.
Step S60 obtains the corresponding tracking letter of the alert when the feedback information is to confirm the information of the alert
Breath；
Tracking information may particularly include the corresponding real-time monitoring data of alert, migratory direction of alert etc..
Step S70 sends the corresponding tracking information of the alert to the alarm platform.
In addition, when feedback information is to negate the information of the alert, it can also be by the monitor video corresponding to alarm signal
Data and monitoring audio data are as the sample data in negative sample training set, then carry out machine learning, are known with correcting default alert
Other model keeps the identification of default alert identification model more accurate.
In the present embodiment, secondary judgement is carried out to alert based on feedback information, if it is determined that target monitoring region goes out really
Existing alert, then obtain the tracking information of alert and be sent to alarm platform, since alert may change, as suspect escapes
From target monitoring region etc., the treatment people of alert can execute corresponding disposition according to the tracking information received by alarm platform
Measure, to guarantee the timeliness and validity of alert processing.
Specifically, referring to Fig. 6, described the step of obtaining the alert corresponding tracking information, includes:
Step S61 obtains the first video data and the first audio data that the monitoring device 100 acquires in real time；
Step S62 judges whether the alert is currently located in the target monitoring region according to the first video data；If
The alert is currently located in the target monitoring region, executes step S63；If the alert is currently located at the target prison
It controls in region, executes step S64, executes step S65.
Specifically, default alert identification module can be input to for the first video data and the first audio data, and according to pre-
If the recognition result of alert identification module output judges whether target monitoring region alert occurs, if current goal monitoring area goes out
Existing alert, then the alert that determination step S30 is determined is currently located in the target monitoring region, if current goal monitoring area
There is not alert, then the alert that determination step S30 is determined is currently located in the target monitoring region.In addition, step
S62 may also include that
Step S621 determines the image of the corresponding risk identification of the alert in the monitor video data；
The image of the corresponding risk identification of alert can be determined according to above-mentioned recognition result in monitor video data.To institute
Stating will be corresponding as alert with the matched image of positive sample training set in default alert identification module in monitor video data
Image.The image of risk identification is determined according to alert type in the corresponding image of alert.Specifically, can be to the corresponding figure of alert
As carry out compromising feature identification, using with compromising feature image-region as the image of risk identification.For example, compromising feature can wrap
Attack object image is included, when alert type is to hurt sb.'s feelings alert, can monitor video data be carried out with human bioequivalence and attack object identification
(such as knife-like, stick-like object identification) will hold the human body image of attack object as the image of risk identification.Furthermore alert class
Type, the different compromising feature identification of the progress also accommodated, such as fire alert, then compromising feature then may include the image of fire.
Step S622 judges whether the picture frame of first video data includes images match with the risk identification
Image；
If the picture frame of first video data includes the image with the images match of the risk identification, step is executed
Rapid S623；If the picture frame of first video data does not include the image with the images match of the risk identification, execute
Step S624.
Step S623 determines that the alert is located in the target monitoring region；
Step S624 determines that the alert is not located in the target monitoring region.
The picture frame for analyzing the first video data, judge in picture frame whether include with the color of the image of risk identification,
The image-region that the similarities such as shape are greater than or equal to preset threshold shows that the picture frame of the first video data includes if including
With the image of the images match of the risk identification, it can determine that alert is located in the target monitoring region；If not including, table
The picture frame of bright first video data does not include the image with the images match of the risk identification, can determine that alert is not located at institute
It states in target monitoring region.
Step S63, using first video data and the first audio data as the tracking information.
Step S64 determines that the migratory direction of position occurs for the alert；
Specifically, the video data and/or audio data that can acquire according to monitoring device 100 are analyzed to obtain alert generation position
The migratory direction set.
Step S65 generates the tracking information according to the migratory direction.
It is provided directly to alarm platform using migratory direction as tracking information, makes policeman person can be according to migratory direction
Corresponding alert treatment measures are taken, for example, chasing suspect.
In the present embodiment, after confirming alert, target monitoring region current the first video data and the first sound are obtained
Frequency evidence, according to the first video data judge alert whether still in target monitoring region, if so, by the first video data with
First audio data makes policeman person that can get the situation at alert scene in real time as tracking information, corresponding to take
Measure；In addition, can be obtained if alert leaves target monitoring region into other monitoring areas or when entering other without monitoring area
It takes alert that the migratory direction of position occurs, generates tracking information according to migratory direction, can smoothly be reached convenient for policeman person
Alert scene takes appropriate measures.
Specifically, in the above-described embodiments, the step of migratory direction of position occurs for the determination alert, includes:
Step S641 obtains the video counts that the monitoring device 100 acquires in the preset time period before current time
According to as the second video data；
Preset time period can be configured according to actual needs, such as may be configured as 5min.In addition, preset time period can be excellent
Choosing be set as determining at the time of there is alert in target monitoring region the period between current time.
Step S642 determines motion profile of the image of the risk identification in second video data；
In the second video data in each picture frame, according to the precedence of image frame acquisitions, risk identification is analyzed
Position of the image in each picture frame is fitted to obtain according to the position that analysis obtains the image of risk identification in second view
Motion profile of the frequency in.
Step S643 determines the migratory direction according to the motion profile.
The migratory direction of position occurs using the direction vector of motion profile as alert, migratory direction can be specially geographically
Direction (such as all directions).
In the present embodiment, by the video counts collected of monitoring device 100 in preset time period before current time
According to the motion profile for the image for being analyzed to obtain risk identification, the migration side of position occurs using motion profile characterization alert
To accurately determine that the migratory direction of position occurs for alert.
Further, referring to Fig. 7, described the step of generating the tracking information according to the migratory direction, includes:
Step S651 determines the region of the monitoring device 100；
The region of monitoring device 100 is specially geographically to be less than or equal to preset with 100 position of monitoring device
The region that the range of distance is formed.Wherein, it may be provided with monitoring device 100 in the different places for needing to monitor, it in advance will prison
Control equipment 100 is registered and marks the position of monitoring device 100.
Step S652 judges in the region of the monitoring device 100 in the migratory direction, if exists described
Other monitoring devices 100 other than monitoring device 100；
When there are other described monitoring devices 100, step S653, step S654 are executed；When there is no other described prisons
When controlling equipment 100, step S656 is executed.
Specifically, with all monitoring devices 100 in the region of the monitoring device 100
Step S653, the video data for obtaining other monitoring devices 100 acquisition are obtained as third video data
The audio data of other monitoring devices 100 acquisition, as the second audio data；
Step S654 judges whether the picture frame of the third video data includes images match with the risk identification
Image；
Here deterministic process is similar with the deterministic process of step S622, and therefore not to repeat here.
If the picture frame of the third video data includes the image with the images match of the risk identification, step is executed
Rapid S655 is executed if the picture frame of the third video data does not include the image with the images match of the risk identification
Step S656.
Step S655, using the third video data and the second audio data as the tracking information；
Step S656, using migratory direction as the tracking information.
In the present embodiment, by analyzing the video data of other monitoring devices 100 acquisition in migratory direction,
Judge whether the alert of above-mentioned judgement is transferred in the monitoring area of other monitoring devices 100, if so, other monitoring can be set
The standby tracking information of 100 collected third video datas and the second audio data as found alert, makes policeman
Member can recognize that there is a situation where guarantee the effective of alert processing to take further counter-measure to current alert in real time
Property.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of alarm method, which is characterized in that the alarm method the following steps are included:
Monitor video data and monitoring audio data are obtained, the monitor video data and the monitoring audio data are by being set to
The monitoring device in target monitoring region acquires；
The monitor video data and the monitoring audio data are inputted into default alert identification model；
According to the recognition result of the default alert identification model output, judge whether the target monitoring region alert occurs；
When alert occurs in the target monitoring region, alarm signal is exported.
2. alarm method as described in claim 1, which is characterized in that the step of output alarm signal includes:
Obtain the location information of the monitoring device；
The alarm signal is generated according to the recognition result and the location information；
The alarm signal is sent to alarm platform.
3. alarm method as claimed in claim 2, which is characterized in that after the step of the output alarm signal, further includes:
Receive the feedback information that the alarm platform is returned based on the alarm signal；
When the feedback information is to confirm the information of the alert, the corresponding tracking information of the alert is obtained；
The corresponding tracking information of the alert is sent to the alarm platform.
4. alarm method as claimed in claim 3, which is characterized in that the step for obtaining the corresponding tracking information of the alert
Suddenly include:
Obtain the first video data and the first audio data that the monitoring device acquires in real time；
Judge whether the alert is currently located in the target monitoring region according to the first video data；
If the alert is currently located in the target monitoring region, using first video data and the first audio data as
The tracking information.
5. alarm method as claimed in claim 4, which is characterized in that described according to the first video data and judging the alert
It is current whether to be located at after the step in the target monitoring region, further includes:
If the alert is currently located in the target monitoring region, determine that the migratory direction of position occurs for the alert；
The tracking information is generated according to the migratory direction.
6. alarm method as claimed in claim 5, which is characterized in that described to judge that the alert is worked as according to the first video data
It is preceding that whether the step in the target monitoring region includes:
In the monitor video data, the image of the corresponding risk identification of the alert is determined；
Whether the picture frame for judging first video data includes image with the images match of the risk identification；
If the picture frame of first video data includes the image with the images match of the risk identification, the police is determined
Feelings are currently located in the target monitoring region；
If the picture frame of first video data does not include the image with the images match of the risk identification, described in judgement
Alert is currently located in the target monitoring region.
7. alarm method as claimed in claim 6, which is characterized in that the migratory direction of position occurs for the determination alert
The step of include:
The video data that the monitoring device acquires in the preset time period before current time is obtained, as the second video counts
According to；
Determine motion profile of the image of the risk identification in second video data；
The migratory direction is determined according to the motion profile.
8. alarm method as claimed in claim 7, which is characterized in that described to generate the tracking letter according to the migratory direction
The step of breath includes:
Determine the region of the monitoring device；
Judge in the region of the monitoring device in the migratory direction, if there are its other than the monitoring device
His monitoring device；
When there are other described monitoring devices, the video data of other monitoring devices acquisition is obtained, as third video
Data obtain the audio data of other monitoring devices acquisition, as the second audio data；
When the picture frame of the third video data includes the image with the images match of the risk identification by the third
Video data and the second audio data are as the tracking information.
9. such as alarm method described in any item of the claim 1 to 8, which is characterized in that the acquisitions monitor video data with
Before the step of monitoring audio data further include:
History monitoring data is obtained, the history monitoring data includes history video data and its corresponding history audio data；
The monitoring data in the history monitoring data comprising effective monitoring information is extracted, as data sample；
Determine that the data sample in the data sample comprising alert information determines the data sample as positive sample training set
The data sample for not including alert information in this, as negative sample training set；
By positive sample training set described in machine learning and the negative sample training set, the default alert identification model is obtained.
10. a kind of monitoring system, which is characterized in that the monitoring system includes:
Monitoring device, including video acquisition device and audio frequency acquisition device；
Warning device including memory, processor and is stored in the report that can be run on the memory and on the processor
Alert program, the processor are connect with the video acquisition device and the audio frequency acquisition device respectively, the alert program quilt
The step of processor realizes alarm method as claimed in any one of claims 1-9 wherein when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811578222.6A CN109598885B (en) | 2018-12-21 | 2018-12-21 | Monitoring system and alarm method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811578222.6A CN109598885B (en) | 2018-12-21 | 2018-12-21 | Monitoring system and alarm method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109598885A true CN109598885A (en) | 2019-04-09 |
| CN109598885B CN109598885B (en) | 2021-06-11 |
Family
ID=65963107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811578222.6A Active CN109598885B (en) | 2018-12-21 | 2018-12-21 | Monitoring system and alarm method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598885B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060437A (en) * | 2019-04-19 | 2019-07-26 | 广东中安金狮科创有限公司 | Regional Management System |
| CN110148283A (en) * | 2019-05-16 | 2019-08-20 | 安徽天帆智能科技有限责任公司 | It is a kind of to fall water monitoring system in real time based on convolutional neural networks |
| CN110223474A (en) * | 2019-07-04 | 2019-09-10 | 无锡睿勤科技有限公司 | A kind of intelligent monitoring and alarming method, system and storage medium |
| CN110390262A (en) * | 2019-06-14 | 2019-10-29 | 平安科技（深圳）有限公司 | Video analysis method, apparatus, server and storage medium |
| CN110428587A (en) * | 2019-07-19 | 2019-11-08 | 国网安徽省电力有限公司建设分公司 | A kind of engineering site early warning interlock method and system |
| CN110516529A (en) * | 2019-07-09 | 2019-11-29 | 杭州电子科技大学 | It is a kind of that detection method and system are fed based on deep learning image procossing |
| CN110532888A (en) * | 2019-08-01 | 2019-12-03 | 悉地国际设计顾问（深圳）有限公司 | A kind of monitoring method, apparatus and system |
| CN110696717A (en) * | 2019-09-05 | 2020-01-17 | 成都亿盟恒信科技有限公司 | Vehicle-mounted system based on split type active safety and intelligent processing |
| CN110909707A (en) * | 2019-12-02 | 2020-03-24 | 天津大海云科技有限公司 | Video inspection system and method based on generating type countermeasure network |
| CN111145538A (en) * | 2019-12-06 | 2020-05-12 | 齐鲁交通信息集团有限公司 | Stereo perception system suitable for audio and video acquisition, recognition and monitoring on highway |
| CN111179546A (en) * | 2019-12-26 | 2020-05-19 | 数海信息技术有限公司 | Self-adaptive distributed audio alarm method and system |
| CN111556620A (en) * | 2020-04-01 | 2020-08-18 | 上海申铁信息工程有限公司 | Method and device for linkage of railway station platform protection system and illumination control system |
| CN111770317A (en) * | 2020-07-22 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Video monitoring method, device, equipment and medium for intelligent community |
| CN111784947A (en) * | 2020-07-10 | 2020-10-16 | 上海茂声智能科技有限公司 | Active early warning method, system and equipment based on image and voiceprint |
| CN111862524A (en) * | 2020-07-10 | 2020-10-30 | 广州博冠智能科技有限公司 | Monitoring alarm method and device based on intelligent home system |
| CN112383756A (en) * | 2020-11-13 | 2021-02-19 | 珠海大横琴科技发展有限公司 | Video monitoring alarm processing method and device |
| CN113569604A (en) * | 2020-12-10 | 2021-10-29 | 特斯联科技集团有限公司 | City dangerous case processing method, device, electronic equipment and medium |
| CN117077988A (en) * | 2023-10-16 | 2023-11-17 | 广东广宇科技发展有限公司 | Police condition monitoring data processing method and system |
| CN117830911A (en) * | 2024-03-06 | 2024-04-05 | 一脉通(深圳)智能科技有限公司 | Intelligent identification method and device for intelligent camera, electronic equipment and medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010043269A1 (en) * | 1997-10-29 | 2001-11-22 | Trevor Holloway | Monitoring system |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| CN101799876A (en) * | 2010-04-20 | 2010-08-11 | 王巍 | Video/audio intelligent analysis management control system |
| CN102724482A (en) * | 2012-06-18 | 2012-10-10 | 西安电子科技大学 | Intelligent visual sensor network moving target relay tracking system based on GPS (global positioning system) and GIS (geographic information system) |
| CN102724773A (en) * | 2012-05-25 | 2012-10-10 | 西安电子科技大学 | Wireless intelligent monitoring device and method based on machine to machine (M2M) communication |
| CN104008371A (en) * | 2014-05-22 | 2014-08-27 | 南京邮电大学 | Regional suspicious target tracking and recognizing method based on multiple cameras |
| CN104125433A (en) * | 2014-07-30 | 2014-10-29 | 西安冉科信息技术有限公司 | Moving object video surveillance method based on multi-PTZ (pan-tilt-zoom)-camera linkage structure |
| CN105453149A (en) * | 2013-04-19 | 2016-03-30 | M·雷加马尼 | Crime evidence provider cum help seeker |
| CN105488044A (en) * | 2014-09-16 | 2016-04-13 | 华为技术有限公司 | Data processing method and device |
| US20160150338A1 (en) * | 2013-06-05 | 2016-05-26 | Samsung Electronics Co., Ltd. | Sound event detecting apparatus and operation method thereof |
| US20160241818A1 (en) * | 2015-02-18 | 2016-08-18 | Honeywell International Inc. | Automatic alerts for video surveillance systems |
| CN105957168A (en) * | 2016-04-19 | 2016-09-21 | 唐山新质点科技有限公司 | Determination method and apparatus for direction of movement track |
| US9514371B1 (en) * | 2014-04-10 | 2016-12-06 | Smartvue Corporation | Systems and methods for automated cloud-based analytics and 3-dimensional (3D) display for surveillance systems |
| KR101733305B1 (en) * | 2015-10-23 | 2017-05-08 | (주) 케이엠미디어 | Smart alarm broadcasting apparatus |
| CN106815958A (en) * | 2017-02-24 | 2017-06-09 | 上海华崟信息技术有限公司 | Warning system, alarm analysis/display device, alarm analysis/display methods |
| CN107223332A (en) * | 2015-03-19 | 2017-09-29 | 英特尔公司 | Audio-visual scene analysis based on acoustics camera |
| CN107679455A (en) * | 2017-08-29 | 2018-02-09 | 平安科技（深圳）有限公司 | Target tracker, method and computer-readable recording medium |
| CN107945442A (en) * | 2017-10-30 | 2018-04-20 | 深圳辉锐天眼科技有限公司 | Alarm management method |
| CN107977638A (en) * | 2017-12-11 | 2018-05-01 | 智美达（江苏）数字技术有限公司 | Video monitoring alarm method, device, computer equipment and storage medium |
-
2018
- 2018-12-21 CN CN201811578222.6A patent/CN109598885B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010043269A1 (en) * | 1997-10-29 | 2001-11-22 | Trevor Holloway | Monitoring system |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| CN101799876A (en) * | 2010-04-20 | 2010-08-11 | 王巍 | Video/audio intelligent analysis management control system |
| CN102724773A (en) * | 2012-05-25 | 2012-10-10 | 西安电子科技大学 | Wireless intelligent monitoring device and method based on machine to machine (M2M) communication |
| CN102724482A (en) * | 2012-06-18 | 2012-10-10 | 西安电子科技大学 | Intelligent visual sensor network moving target relay tracking system based on GPS (global positioning system) and GIS (geographic information system) |
| CN105453149A (en) * | 2013-04-19 | 2016-03-30 | M·雷加马尼 | Crime evidence provider cum help seeker |
| US20160150338A1 (en) * | 2013-06-05 | 2016-05-26 | Samsung Electronics Co., Ltd. | Sound event detecting apparatus and operation method thereof |
| US9514371B1 (en) * | 2014-04-10 | 2016-12-06 | Smartvue Corporation | Systems and methods for automated cloud-based analytics and 3-dimensional (3D) display for surveillance systems |
| CN104008371A (en) * | 2014-05-22 | 2014-08-27 | 南京邮电大学 | Regional suspicious target tracking and recognizing method based on multiple cameras |
| CN104125433A (en) * | 2014-07-30 | 2014-10-29 | 西安冉科信息技术有限公司 | Moving object video surveillance method based on multi-PTZ (pan-tilt-zoom)-camera linkage structure |
| CN105488044A (en) * | 2014-09-16 | 2016-04-13 | 华为技术有限公司 | Data processing method and device |
| US20160241818A1 (en) * | 2015-02-18 | 2016-08-18 | Honeywell International Inc. | Automatic alerts for video surveillance systems |
| CN107223332A (en) * | 2015-03-19 | 2017-09-29 | 英特尔公司 | Audio-visual scene analysis based on acoustics camera |
| KR101733305B1 (en) * | 2015-10-23 | 2017-05-08 | (주) 케이엠미디어 | Smart alarm broadcasting apparatus |
| CN105957168A (en) * | 2016-04-19 | 2016-09-21 | 唐山新质点科技有限公司 | Determination method and apparatus for direction of movement track |
| CN106815958A (en) * | 2017-02-24 | 2017-06-09 | 上海华崟信息技术有限公司 | Warning system, alarm analysis/display device, alarm analysis/display methods |
| CN107679455A (en) * | 2017-08-29 | 2018-02-09 | 平安科技（深圳）有限公司 | Target tracker, method and computer-readable recording medium |
| CN107945442A (en) * | 2017-10-30 | 2018-04-20 | 深圳辉锐天眼科技有限公司 | Alarm management method |
| CN107977638A (en) * | 2017-12-11 | 2018-05-01 | 智美达（江苏）数字技术有限公司 | Video monitoring alarm method, device, computer equipment and storage medium |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060437A (en) * | 2019-04-19 | 2019-07-26 | 广东中安金狮科创有限公司 | Regional Management System |
| CN110148283A (en) * | 2019-05-16 | 2019-08-20 | 安徽天帆智能科技有限责任公司 | It is a kind of to fall water monitoring system in real time based on convolutional neural networks |
| CN110390262A (en) * | 2019-06-14 | 2019-10-29 | 平安科技（深圳）有限公司 | Video analysis method, apparatus, server and storage medium |
| CN110390262B (en) * | 2019-06-14 | 2023-06-30 | 平安科技（深圳）有限公司 | Video analysis method, device, server and storage medium |
| WO2020248386A1 (en) * | 2019-06-14 | 2020-12-17 | 平安科技（深圳）有限公司 | Video analysis method and apparatus, computer device and storage medium |
| CN110223474A (en) * | 2019-07-04 | 2019-09-10 | 无锡睿勤科技有限公司 | A kind of intelligent monitoring and alarming method, system and storage medium |
| CN110516529A (en) * | 2019-07-09 | 2019-11-29 | 杭州电子科技大学 | It is a kind of that detection method and system are fed based on deep learning image procossing |
| CN110428587A (en) * | 2019-07-19 | 2019-11-08 | 国网安徽省电力有限公司建设分公司 | A kind of engineering site early warning interlock method and system |
| CN110532888A (en) * | 2019-08-01 | 2019-12-03 | 悉地国际设计顾问（深圳）有限公司 | A kind of monitoring method, apparatus and system |
| CN110696717A (en) * | 2019-09-05 | 2020-01-17 | 成都亿盟恒信科技有限公司 | Vehicle-mounted system based on split type active safety and intelligent processing |
| CN110909707A (en) * | 2019-12-02 | 2020-03-24 | 天津大海云科技有限公司 | Video inspection system and method based on generating type countermeasure network |
| CN111145538A (en) * | 2019-12-06 | 2020-05-12 | 齐鲁交通信息集团有限公司 | Stereo perception system suitable for audio and video acquisition, recognition and monitoring on highway |
| CN111179546A (en) * | 2019-12-26 | 2020-05-19 | 数海信息技术有限公司 | Self-adaptive distributed audio alarm method and system |
| CN111179546B (en) * | 2019-12-26 | 2021-12-28 | 数海信息技术有限公司 | Self-adaptive distributed audio alarm method and system |
| CN111556620A (en) * | 2020-04-01 | 2020-08-18 | 上海申铁信息工程有限公司 | Method and device for linkage of railway station platform protection system and illumination control system |
| CN111784947A (en) * | 2020-07-10 | 2020-10-16 | 上海茂声智能科技有限公司 | Active early warning method, system and equipment based on image and voiceprint |
| CN111862524A (en) * | 2020-07-10 | 2020-10-30 | 广州博冠智能科技有限公司 | Monitoring alarm method and device based on intelligent home system |
| CN111770317A (en) * | 2020-07-22 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Video monitoring method, device, equipment and medium for intelligent community |
| CN111770317B (en) * | 2020-07-22 | 2023-02-03 | 平安国际智慧城市科技股份有限公司 | Video monitoring method, device, equipment and medium for intelligent community |
| CN112383756B (en) * | 2020-11-13 | 2021-08-17 | 珠海大横琴科技发展有限公司 | Video monitoring alarm processing method and device |
| CN112383756A (en) * | 2020-11-13 | 2021-02-19 | 珠海大横琴科技发展有限公司 | Video monitoring alarm processing method and device |
| CN113569604A (en) * | 2020-12-10 | 2021-10-29 | 特斯联科技集团有限公司 | City dangerous case processing method, device, electronic equipment and medium |
| CN117077988A (en) * | 2023-10-16 | 2023-11-17 | 广东广宇科技发展有限公司 | Police condition monitoring data processing method and system |
| CN117830911A (en) * | 2024-03-06 | 2024-04-05 | 一脉通(深圳)智能科技有限公司 | Intelligent identification method and device for intelligent camera, electronic equipment and medium |
| CN117830911B (en) * | 2024-03-06 | 2024-05-28 | 一脉通(深圳)智能科技有限公司 | Intelligent identification method and device for intelligent camera, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109598885B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598885A (en) | Monitoring system and its alarm method | |
| US11394933B2 (en) | System and method for gate monitoring during departure or arrival of an autonomous vehicle | |
| CN106530633B (en) | The safety protection method disposed and system in a kind of intelligence thing | |
| CN111552216A (en) | Construction site intelligent supervision system based on 5G | |
| US10752213B2 (en) | Detecting an event and automatically obtaining video data | |
| US11354576B1 (en) | Devices and methods using machine learning for surveillance and granting of privileges | |
| KR102531272B1 (en) | Control device using artificial intelligence learning images and vibrations and intrusion alert systme including the same | |
| CN109191829A (en) | Road safety monitoring method and system, computer readable storage medium | |
| CN108319892A (en) | A kind of vehicle safety method for early warning and system based on genetic algorithm | |
| US11532221B1 (en) | System and method for vehicle security monitoring | |
| CN110211334A (en) | Campus Security alarming method for power and device based on big data neural network | |
| CN109949540A (en) | A kind of artificial intelligence early warning system | |
| CN113505709A (en) | Method and system for monitoring dangerous behaviors of human body in real time | |
| CN111027463A (en) | Wall turning detection method based on video analysis | |
| CN114821785B (en) | Potential sudden criminal identification method based on hypothesis evaluation and Bayesian learning | |
| CN113593256B (en) | Unmanned aerial vehicle intelligent driving-away control method and system based on city management and cloud platform | |
| JP2023079291A (en) | Image processing device, image processing method, and program | |
| Dibazar et al. | Intelligent recognition of acoustic and vibration threats for security breach detection close proximity danger identification and perimeter protection | |
| CN113065500A (en) | Abnormal behavior control system for special actions | |
| CN117746218B (en) | Security management method and device for smart campus | |
| KR20160086536A (en) | Warning method and system using prompt situation information data | |
| US11915481B1 (en) | Capturing and analyzing security events and activities and generating corresponding natural language descriptions | |
| CN114694344B (en) | Campus violence monitoring method and device and electronic equipment | |
| CN117749994A (en) | Campus security intelligent monitoring system and method based on Internet of things | |
| US11423760B2 (en) | Device for detecting drowning individuals or individuals in a situation presenting a risk of drowning |
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 |