CN109308555A - A kind of danger early warning method, apparatus, system and video capture device - Google Patents

A kind of danger early warning method, apparatus, system and video capture device Download PDF

Info

Publication number
CN109308555A
CN109308555A CN201710625542.1A CN201710625542A CN109308555A CN 109308555 A CN109308555 A CN 109308555A CN 201710625542 A CN201710625542 A CN 201710625542A CN 109308555 A CN109308555 A CN 109308555A
Authority
CN
China
Prior art keywords
data
sensor
abiotic
monitoring
monitoring data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710625542.1A
Other languages
Chinese (zh)
Inventor
练斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikvision Digital Technology Co Ltd
Original Assignee
Hangzhou Hikvision Digital Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Hikvision Digital Technology Co Ltd filed Critical Hangzhou Hikvision Digital Technology Co Ltd
Priority to CN201710625542.1A priority Critical patent/CN109308555A/en
Publication of CN109308555A publication Critical patent/CN109308555A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • 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

Abstract

The embodiment of the invention provides a kind of danger early warning method, apparatus, system and video capture device, the method is applied to video capture device, which comprises receives the monitoring data that each sensor is sent；Wherein, the identification information for acquiring the sensor of the monitoring data is carried in each monitoring data；According to the identification information of the sensor carried in each monitoring data, reference data corresponding to sensor of each monitoring data with the acquisition monitoring data locally saved is compared, the corresponding danger coefficient of all monitoring data is obtained；Wherein, reference data corresponding to each sensor locally saved is the normal historical data acquired according to the sensor, is obtained after being handled by Neural Network Self-learning algorithm the normal historical data；According to the danger coefficient, it is determined whether alarm.The embodiment of the present invention effectively can carry out danger early warning to monitoring scene.

Description

A kind of danger early warning method, apparatus, system and video capture device
Technical field
The present invention relates to technical field of video monitoring, more particularly to a kind of danger early warning method, apparatus, system and video Acquire equipment.
Background technique
With the continuous development of Video Supervision Technique, the construction such as safe city, intelligent residential district, intelligent transportation it is increasingly general Time, video surveillance applications are more and more extensive.
However, only acquiring monitor video in some monitoring scenes and being not met by practical application request, needed toward contact Hazard detection is carried out, also, is alarmed when dangerous.Such as, the scene being monitored in the behavior of some couples of people is (such as Home for destitute, medical centre etc.) in, when having potential dangerous, needs to carry out danger early warning in time, be otherwise likely to result in people The serious consequences such as member's injures and deaths；Alternatively, animal or environment are monitored scene (such as air quality monitoring, forest fire protection, Conservation of wildlife etc.) in, when environmental aspect is bad, it is also possible to influence the normal existence of animals and plants.
Therefore, while carrying out video monitoring, how to monitoring scene carry out danger early warning, become one it is urgently to be resolved The problem of.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of danger early warning method, apparatus, system and video capture device, with Danger early warning is carried out to monitoring scene.Specific technical solution is as follows:
In a first aspect, being applied to video capture device, the side the embodiment of the invention provides a kind of danger early warning method Method includes:
Receive the monitoring data that each sensor is sent；Wherein, the biography for acquiring the monitoring data is carried in each monitoring data The identification information of sensor；
According to the identification information of the sensor carried in each monitoring data, each monitoring data are adopted with what is locally saved Collect reference data corresponding to the sensor of the monitoring data to compare, obtains the corresponding dangerous system of all monitoring data Number；Wherein, reference data corresponding to each sensor locally saved is the normal historical data acquired according to the sensor, It is obtained after being handled by Neural Network Self-learning algorithm the normal historical data；
According to the danger coefficient, it is determined whether alarm.
Optionally, the identification information according to the sensor carried in each monitoring data, by each monitoring data with Reference data corresponding to the sensor of the acquisition monitoring data locally saved compares, and obtains all monitoring data pair The step of danger coefficient answered includes:
For each monitoring data, according to the identification information of the sensor carried in the monitoring data, by the monitoring data Reference data corresponding to sensor with the acquisition monitoring data locally saved compares, and it is corresponding to obtain the monitoring data The first danger coefficient；
According to corresponding first danger coefficient of each monitoring data and the corresponding weight of preset each monitoring data, calculate The corresponding danger coefficient of all monitoring data.
Optionally, the monitoring data include biological data and abiotic data；It is described to be taken according in each monitoring data The identification information of the sensor of band, will be corresponding to sensor of each monitoring data with the acquisition monitoring data locally saved The step of reference data compares, and obtains all monitoring data corresponding danger coefficient include:
According to the identification information of the sensor carried in each monitoring data, and each sensor identification letter locally saved The corresponding relationship of breath and data category identifies that each monitoring data are biological data or abiotic data；
According to the identification information of the sensor carried in each biological data, each biological data is adopted with what is locally saved Collect reference data corresponding to the sensor of the biological data to compare, obtains the comprehensive corresponding behavior of all biological datas Danger coefficient；
According to the identification information of the sensor carried in each abiotic data, by each abiotic data and local preservation The acquisition abiotic data sensor corresponding to reference data compare, obtain all abiotic aggregation of data pair The environmental hazard coefficient answered；
Using the behavior danger coefficient and/or the environmental hazard coefficient as the corresponding dangerous system of all monitoring data Number.
Optionally, the identification information according to the sensor carried in each biological data, by each biological data with Reference data corresponding to the sensor of the acquisition biological data locally saved compares, and it is comprehensive to obtain all biological datas The step of closing corresponding behavior danger coefficient include:
According to the identification information of the sensor carried in each biological data, each biological data is adopted with what is locally saved Collect reference data corresponding to the sensor of the biological data to compare, obtains the corresponding second dangerous system of the biological data Number, and according to corresponding second danger coefficient of each biological data and the corresponding weight of preset each biological data, it calculates all The comprehensive corresponding behavior danger coefficient of biological data；
The identification information according to the sensor carried in each abiotic data, by each abiotic data and local Reference data corresponding to the sensor of the acquisition of the preservation abiotic data compares, and it is comprehensive to obtain all abiotic data The step of closing corresponding environmental hazard coefficient include:
According to the identification information of the sensor carried in each abiotic data, by each abiotic data and local preservation The acquisition abiotic data sensor corresponding to reference data compare, obtain the corresponding third of the abiotic data Danger coefficient, and according to the corresponding third danger coefficient of each abiotic data and the corresponding power of preset each abiotic data Weight, calculates the corresponding environmental hazard coefficient of all abiotic aggregation of data.
Optionally, described to obtain corresponding second danger coefficient of each biological data and the corresponding third danger of each abiotic data After dangerous coefficient, the method also includes:
Identify that the second danger coefficient is greater than the biological data of the first preset threshold and third danger coefficient is greater than second in advance If the abiotic data of threshold value；
The biological data identified and abiotic data are uploaded to server.
Optionally, described to obtain the corresponding danger of all monitoring data when the monitoring data include biological data After coefficient, the method also includes:
Judge whether the danger coefficient is greater than third predetermined threshold value；
If so, the holder for controlling itself carries out tracing and monitoring to the target object for generating the biological data.
Optionally, described according to the danger coefficient, it is determined whether after being alarmed, the method also includes:
When determining without alarm, the monitoring data that each sensor is sent are corresponding as each sensor Normal historical data, and the corresponding reference data of each sensor locally saved is carried out more by Neural Network Self-learning algorithm Newly.
Second aspect, the embodiment of the invention provides a kind of risk early warning devices, are applied to video capture device, the dress It sets and includes:
Receiving module, the monitoring data sent for receiving each sensor；Wherein, acquisition is carried in each monitoring data should The identification information of the sensor of monitoring data；
Processing module, for the identification information according to the sensor carried in each monitoring data, by each monitoring data Reference data corresponding to sensor with the acquisition monitoring data locally saved compares, and obtains all monitoring data Corresponding danger coefficient；Wherein, reference data corresponding to each sensor locally saved is acquired according to the sensor Normal historical data obtains after being handled by Neural Network Self-learning algorithm the normal historical data；
Alarm module, for according to the danger coefficient, it is determined whether alarm.
Optionally, the processing module includes:
First processing submodule, for being directed to each monitoring data, according to the mark of the sensor carried in the monitoring data Know information, reference data corresponding to sensor of the monitoring data with the acquisition monitoring data locally saved is carried out pair Than obtaining corresponding first danger coefficient of the monitoring data；
Computational submodule, for according to corresponding first danger coefficient of each monitoring data and preset each monitoring data Corresponding weight calculates the corresponding danger coefficient of all monitoring data.
Optionally, the monitoring data include biological data and abiotic data；The processing module includes:
Submodule is identified, for the identification information according to the sensor carried in each monitoring data, and local preservation Each sensor identification information and data category corresponding relationship, identify each monitoring data be biological data or abiotic number According to；
Second processing submodule, for the identification information according to the sensor carried in each biological data, by each life Reference data corresponding to sensor of the object data with the acquisition biological data locally saved compares, and obtains all lifes The corresponding behavior danger coefficient of object aggregation of data；
Third handles submodule will be each for the identification information according to the sensor carried in each abiotic data Reference data corresponding to sensor of the abiotic data with the acquisition abiotic data locally saved compares, and obtains institute The corresponding environmental hazard coefficient of the abiotic aggregation of data having；
Submodule is determined, for using the behavior danger coefficient and/or the environmental hazard coefficient as all monitorings The corresponding danger coefficient of data.
Optionally, the second processing submodule, specifically for the mark according to the sensor carried in each biological data Know information, reference data corresponding to sensor of each biological data with the acquisition biological data locally saved is carried out pair Than obtaining corresponding second danger coefficient of the biological data, and according to corresponding second danger coefficient of each biological data, and pre- If the corresponding weight of each biological data, calculate the comprehensive corresponding behavior danger coefficient of all biological data；
The third handles submodule, specifically for being believed according to the mark of the sensor carried in each abiotic data Breath carries out reference data corresponding to sensor of each abiotic data with the acquisition abiotic data locally saved pair Than, obtain the corresponding third danger coefficient of the abiotic data, and according to the corresponding third danger coefficient of each abiotic data, with And the corresponding weight of preset each abiotic data, calculate the corresponding environmental hazard coefficient of all abiotic aggregation of data.
Optionally, described device further include:
Identification module, the second danger coefficient is greater than biological data and the third danger of the first preset threshold for identification Coefficient is greater than the abiotic data of the second preset threshold；
Uploading module, for the biological data identified and abiotic data to be uploaded to server.
Optionally, when the monitoring data include biological data, described device further include:
Judgment module, for judging whether the danger coefficient is greater than third predetermined threshold value；
Control module, for controlling the holder of the video capture device when the judgment module judging result, which is, is Tracing and monitoring is carried out to the target object for generating the biological data.
Optionally, described device further include:
Self-learning module, the prison for when the alarm module is determined without alarm, each sensor to be sent Measured data passes through Neural Network Self-learning algorithm to each sensor pair respectively as the corresponding normal historical data of each sensor The reference data answered is updated.
The third aspect, the embodiment of the invention provides a kind of danger early warning system, the system is included at least: at least one Sensor and video capture device；
Each sensor is sent to the video capture device for acquiring monitoring data, and by the monitoring data； Wherein, the identification information for acquiring the sensor of the monitoring data is carried in each monitoring data；
The video capture device, the monitoring data sent for receiving each sensor；It is taken according in each monitoring data The identification information of the sensor of band, will be corresponding to sensor of each monitoring data with the acquisition monitoring data locally saved Reference data compares, and obtains the corresponding danger coefficient of all monitoring data, and according to the danger coefficient, it is determined whether It alarms；Wherein, reference data corresponding to each sensor locally saved is normally going through according to sensor acquisition History data obtain after being handled by Neural Network Self-learning algorithm the normal historical data.
Optionally, the video capture device, is specifically used for:
For each monitoring data, according to the identification information of the sensor carried in the monitoring data, by the monitoring data Reference data corresponding to sensor with the acquisition monitoring data locally saved compares, and it is corresponding to obtain the monitoring data The first danger coefficient；
According to corresponding first danger coefficient of each monitoring data and the corresponding weight of preset each monitoring data, calculate The corresponding danger coefficient of all monitoring data.
Optionally, the monitoring data include biological data and abiotic data；The video capture device, it is specific to use In:
According to the identification information of the sensor carried in each monitoring data, and each sensor identification letter locally saved The corresponding relationship of breath and data category identifies that each monitoring data are biological data or abiotic data；
According to the identification information of the sensor carried in each biological data, each biological data is adopted with what is locally saved Collect reference data corresponding to the sensor of the biological data to compare, obtains the comprehensive corresponding behavior of all biological datas Danger coefficient；
According to the identification information of the sensor carried in each abiotic data, by each abiotic data and local preservation The acquisition abiotic data sensor corresponding to reference data compare, obtain all abiotic aggregation of data pair The environmental hazard coefficient answered；
Using the behavior danger coefficient and/or the environmental hazard coefficient as the corresponding dangerous system of all monitoring data Number.
Optionally, the video capture device, is specifically used for:
According to the identification information of the sensor carried in each biological data, each biological data is adopted with what is locally saved Collect reference data corresponding to the sensor of the biological data to compare, obtains the corresponding second dangerous system of the biological data Number, and according to corresponding second danger coefficient of each biological data and the corresponding weight of preset each biological data, it calculates all The comprehensive corresponding behavior danger coefficient of biological data；
According to the identification information of the sensor carried in each abiotic data, by each abiotic data and local preservation The acquisition abiotic data sensor corresponding to reference data compare, obtain the corresponding third of the abiotic data Danger coefficient, and according to the corresponding third danger coefficient of each abiotic data and the corresponding power of preset each abiotic data Weight, calculates the corresponding environmental hazard coefficient of all abiotic aggregation of data.
Optionally, the system also includes servers；
The video capture device is also used to identify that the second danger coefficient is greater than the biological data of the first preset threshold, with And third danger coefficient is greater than the abiotic data of the second preset threshold；It will be on the biological data that identified and abiotic data Reach the server；
The server, for receiving and saving the biological data and abiotic data that the video capture device uploads.
Optionally, when the monitoring data include biological data, the video capture device is also used to judge the danger Whether dangerous coefficient is greater than third predetermined threshold value；If so, controlling the holder of itself to the target object for generating the biological data Carry out tracing and monitoring.
Optionally, the video capture device is also used to send each sensor when determining without alarm Monitoring data pass through Neural Network Self-learning algorithm to local preservation respectively as the corresponding normal historical data of each sensor The corresponding reference data of each sensor be updated.
Fourth aspect, the embodiment of the invention provides a kind of video capture devices, including processor, communication interface, storage Device and communication bus, wherein the processor, the communication interface, the memory are completed mutual by the communication bus Between communication；
The memory, for storing computer program；
The processor when for executing the program stored on the memory, is realized as described in above-mentioned first aspect Method and step.
In the embodiment of the present invention, multiple sensors can be installed in monitoring scene, to acquire each monitoring data, also, The monitoring data that each sensor can also be acquired are sent to video capture device, and video capture device receives monitoring data Afterwards, each monitoring data and the reference data locally saved can be compared, so that it is determined that danger coefficient namely current scene In degree of danger, in turn, video capture device can determine the need for alarming according to danger coefficient, to realize The danger early warning of monitoring scene.Also, each reference data that video capture device locally saves is to pass through Neural Network Self-learning What algorithm obtained after handling the normal historical data that each sensor acquires, compared with original normal historical data, lead to Each monitoring number can more accurately be reflected by crossing the reference data obtained after self-learning algorithm handles normal historical data According to normal range (NR) improve the accurate of danger early warning to can more accurately carry out danger early warning according to the reference data Property.Certainly, it implements any of the products of the present invention or method must be not necessarily required to reach simultaneously above all advantages.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with It obtains other drawings based on these drawings.
Fig. 1 is a kind of danger early warning system architecture diagram of the embodiment of the present invention；
Fig. 2 is a kind of flow chart of danger early warning method of the embodiment of the present invention；
Fig. 3 is a kind of another flow chart of danger early warning method of the embodiment of the present invention；
Fig. 4 is a kind of another architecture diagram of danger early warning system of the embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of risk early warning device of the embodiment of the present invention；
Fig. 6 is a kind of structural schematic diagram of danger early warning system of the embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of video capture device of the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.
Below by way of specific embodiment, the present invention is described in detail.
In the embodiment of the present invention, in order to carry out danger early warning to monitoring scene, multiple biographies can be installed in monitoring scene Sensor.As shown in Figure 1, the danger early warning system of the embodiment of the present invention, may include video capture device 110, wireless sensor 120 and wired sensor 130.
Wherein, wireless sensor 120 and video capture device 110 establish connection by radio connection, as bluetooth, The modes such as WiFi；Wired sensor 130 and video capture device 110 establish connection by wired connection mode, to wirelessly pass The monitoring data that sensor 120 and wired sensor 130 can be acquired are sent to video capture device 110 and are handled.And And each wireless sensor 120 has its corresponding identification information, such as character, number number with wired sensor 130.
Wireless sensor 120 may include: temperature sensor, humidity sensor, pressure sensor, blood pressure sensor etc.. Temperature sensor can be used to monitoring objective object (people, animal, soil etc.) temperature information；Humidity sensor can be used to monitor Environment (air, soil etc.) humidity information；Pressure sensor can be used to monitor the information such as environment (air etc.) pressure；Blood pressure passes Sensor can be used to monitoring objective object (people, animal etc.) blood pressure information.
Wired sensor 130 may include: microwave remote sensor, laser sensor, infrared sensor etc..Microwave remote sensor can To be used to monitor the information such as biological heartbeat；Laser sensor can be used to the information such as monitoring distance；Infrared sensor can be used to The information such as monitoring temperature.
It should be noted that in the embodiment of the present invention, wireless sensor 120 and wired sensor 130 are not limited to above Listed type can also include other kinds of sensor, also, the quantity of all types of sensors can be one or more, It is not limited in the embodiment of the present invention.It also, can simultaneously include wireless pass in the danger early warning system of the embodiment of the present invention Sensor 120 and wired sensor 130 can also only include wireless sensor 120, or comprise only line sensor 130, the present invention Embodiment does not limit this, and can be specifically configured according to the difference of monitoring scene.
It is appreciated that the biological characteristics such as the temperature of human or animal, blood pressure, heartbeat are able to reflect its health status, e.g., work as people When physical condition is bad, temperature may be increased, blood pressure may increase, heartbeat may also can be accelerated；Ambient pressure, temperature Etc. the degree of danger that can reflect environment, such as when there is carbon monoxide leakage, air pressure would generally be increased, when a fire, Air pressure would generally increase, while temperature can also increase；Therefore, according to monitoring scene difference, corresponding sensor, Ke Yiyou are installed Effect ground carries out danger early warning to monitoring scene.
Referring to FIG. 2, it illustrates a kind of danger early warning method flow of the embodiment of the present invention, this method may include with Lower step:
S201 receives the monitoring data that each sensor is sent；Wherein, it is carried in each monitoring data and acquires the monitoring data Sensor identification information.
Method provided in an embodiment of the present invention can be applied to video capture device, for example, can be applied to as shown in Figure 1 Video capture device in system.
In embodiments of the present invention, the monitoring data that each sensor can be acquired are sent to video capture device, such as Temperature data, blood pressure data of blood pressure sensor acquisition of temperature sensor acquisition etc..Also, each sensor is set to video acquisition When preparation send monitoring data, the identification information of each sensor can be carried in each monitoring data.
Such as, when the personnel in any room are monitored in home for destitute, blood pressure sensor, temperature can be installed in the room Sensor, microwave remote sensor are spent, to monitor the blood pressure, body temperature and heartbeat of the personnel.Also, the identification information of blood pressure sensor can The identification information for thinking 01, temperature sensor can be able to be 03 for the identification information of 02, microwave remote sensor.
In this case, the video capture device in the room receive monitoring data that each sensor is sent can be with are as follows: 70,110mmHg, 01；36.8 degrees Celsius, 02；78 times, 03.
S202, according to the identification information of the sensor carried in each monitoring data, by each monitoring data and local guarantor Reference data corresponding to the sensor for the acquisition monitoring data deposited compares, and obtains the corresponding danger of all monitoring data Dangerous coefficient；Wherein, reference data corresponding to each sensor locally saved is the normal history acquired according to the sensor Data obtain after being handled by Neural Network Self-learning algorithm the normal historical data.
In embodiments of the present invention, in order to carry out danger early warning to monitoring scene, video capture device can be previously according to The normal historical data of each sensor acquisition, the normal historical data that each sensor is acquired by Neural Network Self-learning algorithm Corresponding reference data is obtained after being handled.
For example, being mounted with blood pressure sensor, temperature in the room when being monitored to the personnel in room any in home for destitute It, can be in a period of time (such as 12 hours, one day, two days) that the personnel are in a good state of health when sensor, microwave remote sensor It is interior, the monitoring data of the personnel are acquired by each sensor, and each sensor is acquired by Neural Network Self-learning algorithm Monitoring data are handled, and the corresponding reference data of each sensor namely the corresponding regime values range of each sensor are obtained.
Specifically, when video capture device carries out self study for the normal historical data of any sensor acquisition, it can be with The a large amount of normal historical data of sensor acquisition is analyzed, determines a numberical range, the as sensor is corresponding Reference data.Such as, the corresponding reference data of each sensor saved in video capture device can be with are as follows: less than 80, is less than 120mmHg, 01；36.2-37.2 degrees Celsius, 02；60-100 times, 03.
It, can basis after video capture device receives the monitoring data that each sensor is sent when carrying out danger early warning The identification information of the sensor carried in each monitoring data, by each monitoring data and the acquisition monitoring data that locally save Sensor corresponding to reference data compare, obtain the corresponding danger coefficient of all monitoring data.
Specifically, being directed to each monitoring data, video capture device can be according to the sensor carried in the monitoring data Identification information, reference data corresponding to sensor of the monitoring data with the acquisition monitoring data locally saved is carried out Comparison, obtains corresponding first danger coefficient of the monitoring data, in turn, can be according to the corresponding first dangerous system of each monitoring data Number and the corresponding weight of preset each monitoring data, calculate the corresponding danger coefficient of all monitoring data.
For example, when video capture device receives monitoring data that each sensor is sent can be with are as follows: 70,110mmHg, 01； 36.8 degrees Celsius, 02；78 times, 03, the reference data locally saved are as follows: less than 80, be less than 120mmHg, 01；36.2-37.2 takes the photograph Family name's degree, 02；60-100 times, when 03, video capture device can be looked into first against monitoring data 70,110mmHg, 01 locally Looking for identification information is the 01 corresponding reference data of sensor, and as less than 80, being less than 120mmHg can calculate in turn Corresponding first danger coefficient of the monitoring data, for example 12.5%.Likewise, video capture device can calculate monitoring data 36.8 degrees Celsius, 02 corresponding first danger coefficient is 10%, and monitoring data 78 times, 03 corresponding first danger coefficient is 10%.
The corresponding weight of preset each monitoring data for example can be with are as follows: 01-30%, 02-20%, 03-50%.It is obtaining respectively After corresponding first danger coefficient of monitoring data, the corresponding danger of all monitoring data can be calculated in video capture device Coefficient is 12.5%*30%+10%*20%+10%*50%=1.075%.
S203, according to the danger coefficient, it is determined whether alarm.
After danger coefficient is calculated, video capture device can determine whether to alarm according to the danger coefficient.Example Such as, video capture device may determine that whether the danger coefficient is greater than default danger threshold, such as 80%, 85%, 90%, if It is that determination is alarmed.
In the embodiment of the present invention, multiple sensors can be installed in monitoring scene, to acquire each monitoring data, also, The monitoring data that each sensor can also be acquired are sent to video capture device, and video capture device receives monitoring data Afterwards, each monitoring data and the reference data locally saved can be compared, so that it is determined that danger coefficient namely current scene In degree of danger, in turn, video capture device can determine the need for alarming according to danger coefficient, to realize The danger early warning of monitoring scene.Also, each reference data that video capture device locally saves is to pass through Neural Network Self-learning What algorithm obtained after handling the normal historical data that each sensor acquires, compared with original normal historical data, lead to Each monitoring number can more accurately be reflected by crossing the reference data obtained after self-learning algorithm handles normal historical data According to normal range (NR) improve the accurate of danger early warning to can more accurately carry out danger early warning according to the reference data Property.
It is appreciated that in some cases, it may be necessary to while personnel and environment are monitored.It such as, can in home for destitute To install the blood pressure sensor, temperature sensor, the microwave remote sensor that are monitored to personnel simultaneously, and environment is monitored Pressure sensor, temperature sensor etc., to ensure the safety of personnel.Wherein, the person related information of sensor acquisition can be with The context dependant information of referred to as biological data, sensor acquisition is properly termed as abiotic data.
As a kind of embodiment of the embodiment of the present invention, when monitoring data include biological data and abiotic data, In order to improve danger early warning effect, determine that danger source is caused by personnel itself or environment, as shown in figure 3, the present invention is implemented Video capture device calculates the step of all monitoring data corresponding danger coefficient and may include: in example
S301, according to the identification information of the sensor carried in each monitoring data, and each sensor locally saved The corresponding relationship of identification information and data category identifies that each monitoring data are biological data or abiotic data.
In embodiments of the present invention, after monitoring scene installs sensor, each sensor can be acquired to the class of data The corresponding relationship of the identification information of type and each sensor is stored in video capture device.Such as, when in the installation pair in home for destitute Blood pressure sensor 01 that personnel are monitored, temperature sensor 02, microwave remote sensor 03, and to the pressure that environment is monitored When sensor 04 and temperature sensor 05, the correspondence of each the sensor identification information and data category that are saved in video capture device Relationship can be as shown in the table:
Identification information Data category
01 Biological data
02 Biological data
03 Biological data
04 Abiotic data
05 Abiotic data
After video capture device receives the monitoring data that each sensor is sent, it can be taken according in each monitoring data The identification information of the sensor of band, and the corresponding relationship of each sensor identification information and data category locally saved, identification Each monitoring data are biological data or abiotic data.
Such as, when the monitoring data that video capture device receives are as follows: 70,110mmHg, 01；36.8 degrees Celsius, 02；78 times, 03；101.320Kpa, 04；28 degrees Celsius, when 05, can the corresponding relationship according to upper table, identify biological data packet It includes: 70,110mmHg, 01；36.8 degrees Celsius, 02；78 times, 03；Abiotic data include: 101.320Kpa, and 04；28 degrees Celsius, 05。
Alternatively, video capture device can also be according to the fluctuation situation etc. of each monitoring data itself, to determine each monitoring number According to being biological data or abiotic data.Such as, normal body temperature is 36.2-37.2 degrees Celsius, when video capture device receives When the monitoring data arrived are 37 degrees Celsius, which can be determined as biological data.
S302, according to the identification information of the sensor carried in each biological data, by each biological data and local guarantor Reference data corresponding to the sensor for the acquisition biological data deposited compares, and obtains that all biological datas are comprehensive to be corresponded to Behavior danger coefficient.
After identifying biological data and abiotic data, video capture device can be respectively for biological data and abiotic Data are handled, and the comprehensive corresponding behavior danger coefficient of all biological datas is calculated and all abiotic data are comprehensive Close corresponding environmental hazard coefficient.
Specifically, being directed to biological data, video capture device can be according to the sensor carried in each biological data Identification information carries out reference data corresponding to sensor of each biological data with the acquisition biological data locally saved Comparison, obtains corresponding second danger coefficient of the biological data, and according to corresponding second danger coefficient of each biological data, and The corresponding weight of preset each biological data calculates the comprehensive corresponding behavior danger coefficient of all biological datas.
Wherein, when being provided with the sensor of multiple same types in monitoring scene to acquire same type of biological data, Such as, multiple temperature sensors can be placed in human body different parts and carrys out temperature collection information, for the life of any sensor acquisition Object data, video capture device can carry out the biological data all normal historical datas corresponding with multiple sensors pair Than to determine corresponding second danger coefficient of the biological data.
Video capture device calculates the process of corresponding second danger coefficient of each biological data, and calculates in above-described embodiment The process of corresponding first danger coefficient of each monitoring data is similar, calculates the comprehensive corresponding behavior danger system of all biological datas The process that the corresponding danger coefficient of all monitoring data is calculated in several processes and above-described embodiment is similar, herein without superfluous It states.
S303, according to the identification information of the sensor carried in each abiotic data, by each abiotic data and this Reference data corresponding to the sensor of the acquisition of the ground preservation abiotic data compares, and obtains all abiotic data Comprehensive corresponding environmental hazard coefficient.
For abiotic data, video capture device can be according to the mark of the sensor carried in each abiotic data Information carries out reference data corresponding to sensor of each abiotic data with the acquisition abiotic data locally saved Comparison, obtains the corresponding third danger coefficient of the abiotic data, and according to the corresponding third danger coefficient of each abiotic data, And the corresponding weight of preset each abiotic data, calculate the corresponding environmental hazard coefficient of all abiotic aggregation of data.
Video capture device calculates the process of the corresponding third danger coefficient of each abiotic data, falls into a trap with above-described embodiment The process for calculating corresponding first danger coefficient of each monitoring data is similar, calculates the corresponding environment danger of all abiotic aggregation of data The process that the corresponding danger coefficient of all monitoring data is calculated in the process of dangerous coefficient and above-described embodiment is similar, herein not into Row repeats.
It should be noted that the sequence of above-mentioned steps S302 and S303 are not limited to aforesaid way, that is to say, that Ke Yixian Step S302 is executed, then executes step S303；Step S303 can also be first carried out, then executes step S302, the embodiment of the present invention To this without limiting.
S304, the behavior danger coefficient and/or the environmental hazard coefficient is corresponding as all monitoring data Danger coefficient.
Video capture device obtains the corresponding behavior danger coefficient of all biological datas and all abiotic data pair It, can be using behavior danger coefficient and/or environmental hazard coefficient as all monitoring data pair after the environmental hazard coefficient answered The danger coefficient answered.That is, can individually using behavior danger coefficient as the corresponding danger coefficient of all monitoring data, It can also be individually using environmental hazard coefficient as the corresponding danger coefficient of all monitoring data, alternatively, behavior can also be endangered Dangerous coefficient and environmental hazard coefficient, specifically can be according to monitoring fields collectively as all corresponding danger coefficients of monitoring data The difference of scape carries out corresponding setting.
In the present embodiment, video capture device can be respectively processed for biological data and abiotic data, in turn It may determine that the class of risk is that personnel itself are dangerous or environmental hazard, so as to further increase the safety of personnel Property.
As a kind of embodiment of the embodiment of the present invention, when video capture device obtains each biological data corresponding second After danger coefficient and the corresponding third danger coefficient of each abiotic data, it is pre- can also to identify that the second danger coefficient is greater than first If the biological data and third danger coefficient of threshold value are greater than the abiotic data of the second preset threshold, and it is possible to by being known Not Chu biological data and abiotic data be uploaded to server.
When dangerous, leading to dangerous reason may be some or several factors, can also pass through wherein one Kind or a variety of monitoring data judge dangerous reason.In the embodiment of the present invention, the biggish data of danger coefficient are uploaded to service Device has so that staff can be according to the data saved in server, and finding out leads to dangerous reason when occurring dangerous It is targetedly handled, improves Risk Management efficiency.
As a kind of embodiment of the embodiment of the present invention, as shown in figure 4, the danger early warning system of the embodiment of the present invention In, it may include holder 111 in video capture device.In this case, when in the monitoring data that video capture device receives Including biological data, and after obtaining the corresponding danger coefficient of all monitoring data, video capture device can also judge this Whether danger coefficient is greater than third predetermined threshold value；If so, showing may have target object dangerous.
In this case, video capture device can control itself holder to generate the target object of the biological data into Line trace monitoring obtains its real-time status, until video monitoring video is sentenced again persistently to carry out track up to target object Until disconnected elimination dangerous out.In turn, during subsequent Risk Management, target object can be known according to the video taken Truth e.g. whether fall down behavior etc., so as to be corresponded to it according to the truth of target object The processing such as rescue.
As a kind of embodiment of the embodiment of the present invention, when the danger coefficient that video capture device is calculated according to it When determining without alarm, show that the monitoring data being currently received are normal data.It in this case, can will be each The monitoring data that sensor is sent are calculated respectively as the corresponding normal historical data of each sensor, and by Neural Network Self-learning Method is updated the corresponding reference data of each sensor locally saved.
The corresponding reference data of each sensor locally saved is updated by normal monitoring data, it can be continuous Ground is corrected the corresponding reference data of each sensor, keeps each reference data more acurrate, thus subsequent further according to reference data When carrying out danger early warning, the accuracy of danger early warning can be further increased.
Correspondingly, being applied to video capture device, such as Fig. 5 the embodiment of the invention also provides a kind of risk early warning device Shown, described device includes:
Receiving module 510, the monitoring data sent for receiving each sensor；Wherein, it carries and adopts in each monitoring data Collect the identification information of the sensor of the monitoring data；
Processing module 520, for the identification information according to the sensor carried in each monitoring data, by each monitoring number It is compared according to reference data corresponding to the sensor of the acquisition monitoring data locally saved, obtains all monitoring numbers According to corresponding danger coefficient；Wherein, reference data corresponding to each sensor locally saved is acquired according to the sensor Normal historical data, obtained after being handled by Neural Network Self-learning algorithm the normal historical data；
Alarm module 530, for according to the danger coefficient, it is determined whether alarm.
In the embodiment of the present invention, multiple sensors can be installed in monitoring scene, to acquire each monitoring data, also, The monitoring data that each sensor can also be acquired are sent to video capture device, and video capture device receives monitoring data Afterwards, each monitoring data and the reference data locally saved can be compared, so that it is determined that danger coefficient namely current scene In degree of danger, in turn, video capture device can determine the need for alarming according to danger coefficient, to realize The danger early warning of monitoring scene.Also, each reference data that video capture device locally saves is to pass through Neural Network Self-learning What algorithm obtained after handling the normal historical data that each sensor acquires, compared with original normal historical data, lead to Each monitoring number can more accurately be reflected by crossing the reference data obtained after self-learning algorithm handles normal historical data According to normal range (NR) improve the accurate of danger early warning to can more accurately carry out danger early warning according to the reference data Property.
As a kind of embodiment of the embodiment of the present invention, the processing module 520 includes:
First processing submodule (not shown), for being directed to each monitoring data, for each monitoring data, according to The identification information of the sensor carried in the monitoring data, by the biography of the monitoring data and the acquisition monitoring data locally saved Reference data corresponding to sensor compares, and obtains corresponding first danger coefficient of the monitoring data；
Computational submodule (not shown) is used for according to corresponding first danger coefficient of each monitoring data, and default The corresponding weight of each monitoring data, calculate the corresponding danger coefficient of all monitoring data.
As a kind of embodiment of the embodiment of the present invention, the monitoring data include biological data and abiotic data； The processing module 520 includes:
Identify submodule (not shown), for the identification information according to the sensor carried in each monitoring data, And the corresponding relationship of each the sensor identification information and data category locally saved, identify that each monitoring data are biological data Or abiotic data；
Second processing submodule (not shown), for being believed according to the mark of the sensor carried in each biological data Breath compares reference data corresponding to sensor of each biological data with the acquisition biological data locally saved, Obtain the comprehensive corresponding behavior danger coefficient of all biological datas；
Third handles submodule (not shown), for the mark according to the sensor carried in each abiotic data Information carries out reference data corresponding to sensor of each abiotic data with the acquisition abiotic data locally saved Comparison, obtains the corresponding environmental hazard coefficient of all abiotic aggregation of data；
Submodule (not shown) is determined, for making the behavior danger coefficient and/or the environmental hazard coefficient For all corresponding danger coefficients of monitoring data.
As a kind of embodiment of the embodiment of the present invention, the second processing submodule is specifically used for according to each life The identification information of the sensor carried in object data, by the sensing of each biological data and the acquisition biological data locally saved Reference data corresponding to device compares, and obtains corresponding second danger coefficient of the biological data, and according to each biological data Corresponding second danger coefficient and the corresponding weight of preset each biological data calculate the comprehensive correspondence of all biological datas Behavior danger coefficient；
The third handles submodule, specifically for being believed according to the mark of the sensor carried in each abiotic data Breath carries out reference data corresponding to sensor of each abiotic data with the acquisition abiotic data locally saved pair Than, obtain the corresponding third danger coefficient of the abiotic data, and according to the corresponding third danger coefficient of each abiotic data, with And the corresponding weight of preset each abiotic data, calculate the corresponding environmental hazard coefficient of all abiotic aggregation of data.
As a kind of embodiment of the embodiment of the present invention, described device further include:
Identification module (not shown), the second danger coefficient is greater than the biological data of the first preset threshold for identification, And third danger coefficient is greater than the abiotic data of the second preset threshold；
Uploading module (not shown), for the biological data identified and abiotic data to be uploaded to service Device.
As a kind of embodiment of the embodiment of the present invention, when the monitoring data include biological data, described device Further include:
Judgment module (not shown), for judging whether the danger coefficient is greater than third predetermined threshold value；
Control module (not shown), for controlling the video and adopting when the judgment module judging result, which is, is The holder for collecting equipment carries out tracing and monitoring to the target object for generating the biological data.
As a kind of embodiment of the embodiment of the present invention, described device further include:
Self-learning module (not shown) is used for when the alarm module is determined without alarm, by each biography The monitoring data that sensor is sent pass through Neural Network Self-learning algorithm respectively as the corresponding normal historical data of each sensor The corresponding reference data of each sensor locally saved is updated.
Correspondingly, the embodiment of the invention also provides a kind of danger early warning systems, as shown in fig. 6, the system comprises: extremely A few sensor 610 and video capture device 620；
The monitoring data for acquiring monitoring data, and are sent to the video acquisition and set by each sensor 610 Standby 620；Wherein, the identification information for acquiring the sensor of the monitoring data is carried in each monitoring data；
The video capture device 620, the monitoring data sent for receiving each sensor 610；According to each monitoring number According to the identification information of the sensor of middle carrying, by the sensor institute of each monitoring data and the acquisition monitoring data locally saved Corresponding reference data compares, and obtains the corresponding danger coefficient of all monitoring data, and according to the danger coefficient, really It is fixed whether to alarm；Wherein, reference data corresponding to each sensor locally saved is acquired according to the sensor Normal historical data obtains after being handled by Neural Network Self-learning algorithm the normal historical data.
In the embodiment of the present invention, multiple sensors can be installed in monitoring scene, to acquire each monitoring data, also, The monitoring data that each sensor can also be acquired are sent to video capture device, and video capture device receives monitoring data Afterwards, each monitoring data and the reference data locally saved can be compared, so that it is determined that danger coefficient namely current scene In degree of danger, in turn, video capture device can determine the need for alarming according to danger coefficient, to realize The danger early warning of monitoring scene.Also, each reference data that video capture device locally saves is to pass through Neural Network Self-learning What algorithm obtained after handling the normal historical data that each sensor acquires, compared with original normal historical data, lead to Each monitoring number can more accurately be reflected by crossing the reference data obtained after self-learning algorithm handles normal historical data According to normal range (NR) improve the accurate of danger early warning to can more accurately carry out danger early warning according to the reference data Property.
As a kind of embodiment of the embodiment of the present invention, the video capture device 620 is specifically used for:
For each monitoring data, according to the identification information of the sensor carried in the monitoring data, by the monitoring data Reference data corresponding to sensor with the acquisition monitoring data locally saved compares, and it is corresponding to obtain the monitoring data The first danger coefficient；
According to corresponding first danger coefficient of each monitoring data and the corresponding weight of preset each monitoring data, calculate The corresponding danger coefficient of all monitoring data.
As a kind of embodiment of the embodiment of the present invention, the monitoring data include biological data and abiotic data； The video capture device 620, is specifically used for:
According to the identification information of the sensor carried in each monitoring data, and each sensor identification letter locally saved The corresponding relationship of breath and data category identifies that each monitoring data are biological data or abiotic data；
According to the identification information of the sensor carried in each biological data, each biological data is adopted with what is locally saved Collect reference data corresponding to the sensor of the biological data to compare, obtains the comprehensive corresponding behavior of all biological datas Danger coefficient；
According to the identification information of the sensor carried in each abiotic data, by each abiotic data and local preservation The acquisition abiotic data sensor corresponding to reference data compare, obtain all abiotic aggregation of data pair The environmental hazard coefficient answered；
Using the behavior danger coefficient and/or the environmental hazard coefficient as the corresponding dangerous system of all monitoring data Number.
As a kind of embodiment of the embodiment of the present invention, the video capture device 620 is specifically used for:
According to the identification information of the sensor carried in each biological data, each biological data is adopted with what is locally saved Collect reference data corresponding to the sensor of the biological data to compare, obtains the corresponding second dangerous system of the biological data Number, and according to corresponding second danger coefficient of each biological data and the corresponding weight of preset each biological data, it calculates all The comprehensive corresponding behavior danger coefficient of biological data；
According to the identification information of the sensor carried in each abiotic data, by each abiotic data and local preservation The acquisition abiotic data sensor corresponding to reference data compare, obtain the corresponding third of the abiotic data Danger coefficient, and according to the corresponding third danger coefficient of each abiotic data and the corresponding power of preset each abiotic data Weight, calculates the corresponding environmental hazard coefficient of all abiotic aggregation of data.
As a kind of embodiment of the embodiment of the present invention, the system also includes: server；
The video capture device 620 is also used to identify that the second danger coefficient is greater than the biological data of the first preset threshold, And third danger coefficient is greater than the abiotic data of the second preset threshold；By the biological data identified and abiotic data It is uploaded to the server；
The server, for receiving and saving the biological data and abiotic data that the video capture device uploads.
As a kind of embodiment of the embodiment of the present invention, when the monitoring data include biological data, the video Equipment 620 is acquired, is also used to judge whether the danger coefficient is greater than third predetermined threshold value；If so, controlling the holder of itself Tracing and monitoring is carried out to the target object for generating the biological data.
As a kind of embodiment of the embodiment of the present invention, the video capture device 620, be also used to when determine without When alarm, the monitoring data that each sensor is sent pass through as the corresponding normal historical data of each sensor Neural Network Self-learning algorithm is updated the corresponding reference data of each sensor locally saved.
Correspondingly, the embodiment of the invention also provides a kind of video capture device, as shown in fig. 7, comprises processor 710, Communication interface 720, memory 730 and communication bus 740, wherein the processor 710, described is deposited at the communication interface 720 Reservoir 730 completes mutual communication by the communication bus 740；
The memory 730, for storing computer program；
The processor 710 performs the steps of when for executing the program stored on the memory 730
Receive the monitoring data that each sensor is sent；Wherein, the biography for acquiring the monitoring data is carried in each monitoring data The identification information of sensor；
According to the identification information of the sensor carried in each monitoring data, each monitoring data are adopted with what is locally saved Collect reference data corresponding to the sensor of the monitoring data to compare, obtains the corresponding dangerous system of all monitoring data Number；Wherein, reference data corresponding to each sensor locally saved is the normal historical data acquired according to the sensor, It is obtained after being handled by Neural Network Self-learning algorithm the normal historical data；
According to the danger coefficient, it is determined whether alarm.
In the embodiment of the present invention, multiple sensors can be installed in monitoring scene, to acquire each monitoring data, also, The monitoring data that each sensor can also be acquired are sent to video capture device, and video capture device receives monitoring data Afterwards, each monitoring data and the reference data locally saved can be compared, so that it is determined that danger coefficient namely current scene In degree of danger, in turn, video capture device can determine the need for alarming according to danger coefficient, to realize The danger early warning of monitoring scene.Also, each reference data that video capture device locally saves is to pass through Neural Network Self-learning What algorithm obtained after handling the normal historical data that each sensor acquires, compared with original normal historical data, lead to Each monitoring number can more accurately be reflected by crossing the reference data obtained after self-learning algorithm handles normal historical data According to normal range (NR) improve the accurate of danger early warning to can more accurately carry out danger early warning according to the reference data Property.
The communication bus 740 that above-mentioned computer equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component Interconnect, abbreviation PCI) bus or expanding the industrial standard structure (Extended Industry Standard Architecture, abbreviation EISA) bus etc..The communication bus 740 can be divided into address bus, data/address bus, Control bus etc..Only to be indicated with a line in figure convenient for indicating, it is not intended that an only bus or a type of total Line.
Communication interface 720 is for the communication between above-mentioned computer equipment and other equipment.
Memory 730 may include random access memory (Random Access Memory, abbreviation RAM), can also be with Including nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.Optionally, memory 730 can also be that at least one is located remotely from the storage device of aforementioned processor.
Above-mentioned processor 710 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit (Ne twork Processor, abbreviation NP) etc.；It can also be digital signal processor (Digital Signal Processing, abbreviation DSP), specific integrated circuit (Applica tion Specific Integrated Circuit, abbreviation ASIC), field programmable gate array (Field-Programmable Gate Array, Abbreviation FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.
Correspondingly, the embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable storage Dielectric memory contains computer program, and one kind as described in above-described embodiment is realized when the computer program is executed by processor Danger early warning method.
In the embodiment of the present invention, multiple sensors can be installed in monitoring scene, to acquire each monitoring data, also, The monitoring data that each sensor can also be acquired are sent to video capture device, and video capture device receives monitoring data Afterwards, each monitoring data and the reference data locally saved can be compared, so that it is determined that danger coefficient namely current scene In degree of danger, in turn, video capture device can determine the need for alarming according to danger coefficient, to realize The danger early warning of monitoring scene.Also, each reference data that video capture device locally saves is to pass through Neural Network Self-learning What algorithm obtained after handling the normal historical data that each sensor acquires, compared with original normal historical data, lead to Each monitoring number can more accurately be reflected by crossing the reference data obtained after self-learning algorithm handles normal historical data According to normal range (NR) improve the accurate of danger early warning to can more accurately carry out danger early warning according to the reference data Property.
For device/system/video capture device/storage medium embodiment, since it is substantially similar to method reality Example is applied, so being described relatively simple, the relevent part can refer to the partial explaination of embodiments of method.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method Part explanation.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention It is interior.

Claims (22)

1. a kind of danger early warning method, which is characterized in that be applied to video capture device, which comprises
Receive the monitoring data that each sensor is sent；Wherein, the sensor for acquiring the monitoring data is carried in each monitoring data Identification information；
It, should with the acquisition locally saved by each monitoring data according to the identification information of the sensor carried in each monitoring data Reference data corresponding to the sensor of monitoring data compares, and obtains the corresponding danger coefficient of all monitoring data；Its In, reference data corresponding to each sensor for locally saving is the normal historical data acquired according to the sensor, is passed through What Neural Network Self-learning algorithm obtained after handling the normal historical data；
According to the danger coefficient, it is determined whether alarm.
2. the method according to claim 1, wherein described according to the sensor carried in each monitoring data Identification information carries out reference data corresponding to sensor of each monitoring data with the acquisition monitoring data locally saved Comparison, the step of obtaining all monitoring data corresponding danger coefficient include:
For each monitoring data, according to the identification information of the sensor carried in the monitoring data, by the monitoring data and this Reference data corresponding to the sensor for the acquisition monitoring data that ground saves compares, and obtains the monitoring data corresponding the One danger coefficient；
According to corresponding first danger coefficient of each monitoring data and the corresponding weight of preset each monitoring data, calculate all The corresponding danger coefficient of monitoring data.
3. the method according to claim 1, wherein the monitoring data include biological data and abiotic number According to；The identification information according to the sensor carried in each monitoring data adopts each monitoring data with what is locally saved Collect reference data corresponding to the sensor of the monitoring data to compare, obtains the corresponding danger coefficient of all monitoring data The step of include:
According to the identification information of the sensor carried in each monitoring data, and each sensor identification information for locally saving and The corresponding relationship of data category identifies that each monitoring data are biological data or abiotic data；
It, should with the acquisition locally saved by each biological data according to the identification information of the sensor carried in each biological data Reference data corresponding to the sensor of biological data compares, and it is dangerous to obtain the comprehensive corresponding behavior of all biological datas Coefficient；
According to the identification information of the sensor carried in each abiotic data, each abiotic data are adopted with what is locally saved Collect reference data corresponding to the sensor of the abiotic data to compare, it is corresponding to obtain all abiotic aggregation of data Environmental hazard coefficient；
Using the behavior danger coefficient and/or the environmental hazard coefficient as the corresponding danger coefficient of all monitoring data.
4. according to the method described in claim 3, it is characterized in that, described according to the sensor carried in each biological data Identification information carries out reference data corresponding to sensor of each biological data with the acquisition biological data locally saved Comparison, obtaining the step of all biological datas integrate corresponding behavior danger coefficient includes:
It, should with the acquisition locally saved by each biological data according to the identification information of the sensor carried in each biological data Reference data corresponding to the sensor of biological data compares, and obtains corresponding second danger coefficient of the biological data, and According to corresponding second danger coefficient of each biological data and the corresponding weight of preset each biological data, all lifes are calculated The corresponding behavior danger coefficient of object aggregation of data；
The identification information according to the sensor carried in each abiotic data, by each abiotic data and local preservation The acquisition abiotic data sensor corresponding to reference data compare, obtain all abiotic aggregation of data pair The step of environmental hazard coefficient answered includes:
According to the identification information of the sensor carried in each abiotic data, each abiotic data are adopted with what is locally saved Collect reference data corresponding to the sensor of the abiotic data to compare, it is dangerous to obtain the corresponding third of the abiotic data Coefficient, and according to the corresponding third danger coefficient of each abiotic data and the corresponding weight of preset each abiotic data, meter The corresponding environmental hazard coefficient of all abiotic aggregation of data.
5. according to the method described in claim 4, it is characterized in that, described obtain corresponding second danger coefficient of each biological data After third danger coefficient corresponding with each abiotic data, the method also includes:
Identify that the second danger coefficient is greater than the biological data of the first preset threshold and third danger coefficient is greater than the second default threshold The abiotic data of value；
The biological data identified and abiotic data are uploaded to server.
6. method according to claim 1-5, which is characterized in that when the monitoring data include biological data When, it is described obtain the corresponding danger coefficient of all monitoring data after, the method also includes:
Judge whether the danger coefficient is greater than third predetermined threshold value；
If so, the holder for controlling itself carries out tracing and monitoring to the target object for generating the biological data.
7. method according to claim 1-5, which is characterized in that described according to the danger coefficient, determination is It is no alarmed after, the method also includes:
It is corresponding normal using the monitoring data that each sensor is sent as each sensor when determining without alarm Historical data, and the corresponding reference data of each sensor locally saved is updated by Neural Network Self-learning algorithm.
8. a kind of risk early warning device, which is characterized in that be applied to video capture device, described device includes:
Receiving module, the monitoring data sent for receiving each sensor；Wherein, it is carried in each monitoring data and acquires the monitoring The identification information of the sensor of data；
Processing module, for the identification information according to the sensor carried in each monitoring data, by each monitoring data and this Reference data corresponding to the sensor of the acquisition of the ground preservation monitoring data compares, and it is corresponding to obtain all monitoring data Danger coefficient；Wherein, reference data corresponding to each sensor locally saved is according to the normal of sensor acquisition Historical data obtains after being handled by Neural Network Self-learning algorithm the normal historical data；
Alarm module, for according to the danger coefficient, it is determined whether alarm.
9. device according to claim 8, which is characterized in that the processing module includes:
First processing submodule is believed for being directed to each monitoring data according to the mark of the sensor carried in the monitoring data Reference data corresponding to sensor of the monitoring data with the acquisition monitoring data locally saved is compared, is obtained by breath To corresponding first danger coefficient of the monitoring data；
Computational submodule, for corresponding according to corresponding first danger coefficient of each monitoring data and preset each monitoring data Weight, calculate the corresponding danger coefficient of all monitoring data.
10. device according to claim 8, which is characterized in that the monitoring data include biological data and abiotic number According to；The processing module includes:
It identifies submodule, for the identification information according to the sensor carried in each monitoring data, and locally saves each The corresponding relationship of sensor identification information and data category identifies that each monitoring data are biological data or abiotic data；
Second processing submodule, for the identification information according to the sensor carried in each biological data, by each biological number It is compared according to reference data corresponding to the sensor of the acquisition biological data locally saved, obtains all biological numbers According to the corresponding behavior danger coefficient of synthesis；
Third handles submodule, for the identification information according to the sensor carried in each abiotic data, by each non-life Reference data corresponding to sensor of the object data with the acquisition abiotic data locally saved compares, and obtains all The corresponding environmental hazard coefficient of abiotic aggregation of data；
Submodule is determined, for using the behavior danger coefficient and/or the environmental hazard coefficient as all monitoring data Corresponding danger coefficient.
11. device according to claim 10, which is characterized in that the second processing submodule is specifically used for according to every The identification information of the sensor carried in a biological data, by each biological data and the acquisition biological data that locally saves Reference data corresponding to sensor compares, and obtains corresponding second danger coefficient of the biological data, and according to each biology It is comprehensive to calculate all biological datas for corresponding second danger coefficient of data and the corresponding weight of preset each biological data Corresponding behavior danger coefficient；
The third handles submodule, will specifically for the identification information according to the sensor carried in each abiotic data Reference data corresponding to sensor of each abiotic data with the acquisition abiotic data locally saved compares, and obtains To the corresponding third danger coefficient of the abiotic data, and according to the corresponding third danger coefficient of each abiotic data, and it is pre- If the corresponding weight of each abiotic data, calculate the corresponding environmental hazard coefficient of all abiotic aggregation of data.
12. device according to claim 11, which is characterized in that described device further include:
Identification module, the second danger coefficient is greater than the biological data and third danger coefficient of the first preset threshold for identification Greater than the abiotic data of the second preset threshold；
Uploading module, for the biological data identified and abiotic data to be uploaded to server.
13. according to the described in any item devices of claim 8-12, which is characterized in that when the monitoring data include biological data When, described device further include:
Judgment module, for judging whether the danger coefficient is greater than third predetermined threshold value；
Control module, for controlling the holder of the video capture device to production when the judgment module judging result, which is, is The target object of the raw biological data carries out tracing and monitoring.
14. according to the described in any item devices of claim 8-12, which is characterized in that described device further include:
Self-learning module, the monitoring number for when the alarm module is determined without alarm, each sensor to be sent According to respectively as the corresponding normal historical data of each sensor, and by Neural Network Self-learning algorithm to each biography locally saved The corresponding reference data of sensor is updated.
15. a kind of danger early warning system, which is characterized in that the system includes at least: at least a sensor and video are adopted Collect equipment；
Each sensor is sent to the video capture device for acquiring monitoring data, and by the monitoring data；Its In, the identification information for acquiring the sensor of the monitoring data is carried in each monitoring data；
The video capture device, the monitoring data sent for receiving each sensor；According to what is carried in each monitoring data The identification information of sensor, by reference corresponding to sensor of each monitoring data with the acquisition monitoring data locally saved Data compare, and obtain the corresponding danger coefficient of all monitoring data, and according to the danger coefficient, it is determined whether carry out Alarm；Wherein, reference data corresponding to each sensor locally saved is the normal history number acquired according to the sensor According to being obtained after being handled by Neural Network Self-learning algorithm the normal historical data.
16. system according to claim 15, which is characterized in that the video capture device is specifically used for:
For each monitoring data, according to the identification information of the sensor carried in the monitoring data, by the monitoring data and this Reference data corresponding to the sensor for the acquisition monitoring data that ground saves compares, and obtains the monitoring data corresponding the One danger coefficient；
According to corresponding first danger coefficient of each monitoring data and the corresponding weight of preset each monitoring data, calculate all The corresponding danger coefficient of monitoring data.
17. system according to claim 15, which is characterized in that the monitoring data include biological data and abiotic number According to；The video capture device, is specifically used for:
According to the identification information of the sensor carried in each monitoring data, and each sensor identification information for locally saving and The corresponding relationship of data category identifies that each monitoring data are biological data or abiotic data；
It, should with the acquisition locally saved by each biological data according to the identification information of the sensor carried in each biological data Reference data corresponding to the sensor of biological data compares, and it is dangerous to obtain the comprehensive corresponding behavior of all biological datas Coefficient；
According to the identification information of the sensor carried in each abiotic data, each abiotic data are adopted with what is locally saved Collect reference data corresponding to the sensor of the abiotic data to compare, it is corresponding to obtain all abiotic aggregation of data Environmental hazard coefficient；
Using the behavior danger coefficient and/or the environmental hazard coefficient as the corresponding danger coefficient of all monitoring data.
18. system according to claim 17, which is characterized in that the video capture device is specifically used for:
It, should with the acquisition locally saved by each biological data according to the identification information of the sensor carried in each biological data Reference data corresponding to the sensor of biological data compares, and obtains corresponding second danger coefficient of the biological data, and According to corresponding second danger coefficient of each biological data and the corresponding weight of preset each biological data, all lifes are calculated The corresponding behavior danger coefficient of object aggregation of data；
According to the identification information of the sensor carried in each abiotic data, each abiotic data are adopted with what is locally saved Collect reference data corresponding to the sensor of the abiotic data to compare, it is dangerous to obtain the corresponding third of the abiotic data Coefficient, and according to the corresponding third danger coefficient of each abiotic data and the corresponding weight of preset each abiotic data, meter The corresponding environmental hazard coefficient of all abiotic aggregation of data.
19. system according to claim 18, which is characterized in that the system also includes: server；
The video capture device is also used to identify that the second danger coefficient is greater than the biological data of the first preset threshold, Yi Ji Three danger coefficients are greater than the abiotic data of the second preset threshold；The biological data identified and abiotic data are uploaded to The server；
The server, for receiving and saving the biological data and abiotic data that the video capture device uploads.
20. the described in any item systems of 5-19 according to claim 1, which is characterized in that when the monitoring data include biological number According to when, the video capture device is also used to judge whether the danger coefficient is greater than third predetermined threshold value；If so, control The holder of itself carries out tracing and monitoring to the target object for generating the biological data.
21. the described in any item systems of 5-19 according to claim 1, which is characterized in that the video capture device is also used to work as When determining without alarm, using the monitoring data that each sensor is sent as the corresponding normal history number of each sensor According to, and the corresponding reference data of each sensor locally saved is updated by Neural Network Self-learning algorithm.
22. a kind of video capture device, which is characterized in that including processor, communication interface, memory and communication bus, wherein The processor, the communication interface, the memory complete mutual communication by the communication bus；
The memory, for storing computer program；
The processor when for executing the program stored on the memory, realizes side as claimed in claim 1 to 7 Method step.
CN201710625542.1A 2017-07-27 2017-07-27 A kind of danger early warning method, apparatus, system and video capture device Pending CN109308555A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710625542.1A CN109308555A (en) 2017-07-27 2017-07-27 A kind of danger early warning method, apparatus, system and video capture device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710625542.1A CN109308555A (en) 2017-07-27 2017-07-27 A kind of danger early warning method, apparatus, system and video capture device

Publications (1)

Publication Number Publication Date
CN109308555A true CN109308555A (en) 2019-02-05

Family

ID=65202223

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710625542.1A Pending CN109308555A (en) 2017-07-27 2017-07-27 A kind of danger early warning method, apparatus, system and video capture device

Country Status (1)

Country Link
CN (1) CN109308555A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109816179A (en) * 2019-03-05 2019-05-28 重庆工商大学融智学院 ECOLOGICAL ENVIRONMENTAL MONITORING method for early warning and system based on big data
CN111275911A (en) * 2020-01-16 2020-06-12 珠海格力电器股份有限公司 Danger prompting method, equipment and computer readable storage medium
CN112116246A (en) * 2020-09-18 2020-12-22 青岛海信网络科技股份有限公司 Risk processing method and device
CN112950836A (en) * 2019-12-10 2021-06-11 联骐技研有限公司 Access control system with fire-fighting warning function and fire-fighting warning method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103070676A (en) * 2013-02-04 2013-05-01 广州视声电子科技有限公司 Method and system for acquiring safety state of monitored object
CN103389719A (en) * 2013-08-02 2013-11-13 临沂市拓普网络股份有限公司 Intelligent home monitoring system and method based on cloud computing
CN104408874A (en) * 2014-11-28 2015-03-11 广东欧珀移动通信有限公司 Security pre-alarm method and device
CN104657792A (en) * 2015-03-06 2015-05-27 中电海康集团有限公司 Early warning method based on rule engine and intelligent prediction
CN106652330A (en) * 2016-11-16 2017-05-10 深圳市元征科技股份有限公司 Human body health and environmental monitoring equipment-based monitoring method and related equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103070676A (en) * 2013-02-04 2013-05-01 广州视声电子科技有限公司 Method and system for acquiring safety state of monitored object
CN103389719A (en) * 2013-08-02 2013-11-13 临沂市拓普网络股份有限公司 Intelligent home monitoring system and method based on cloud computing
CN104408874A (en) * 2014-11-28 2015-03-11 广东欧珀移动通信有限公司 Security pre-alarm method and device
CN104657792A (en) * 2015-03-06 2015-05-27 中电海康集团有限公司 Early warning method based on rule engine and intelligent prediction
CN106652330A (en) * 2016-11-16 2017-05-10 深圳市元征科技股份有限公司 Human body health and environmental monitoring equipment-based monitoring method and related equipment

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109816179A (en) * 2019-03-05 2019-05-28 重庆工商大学融智学院 ECOLOGICAL ENVIRONMENTAL MONITORING method for early warning and system based on big data
CN112950836A (en) * 2019-12-10 2021-06-11 联骐技研有限公司 Access control system with fire-fighting warning function and fire-fighting warning method
CN111275911A (en) * 2020-01-16 2020-06-12 珠海格力电器股份有限公司 Danger prompting method, equipment and computer readable storage medium
CN111275911B (en) * 2020-01-16 2021-02-26 珠海格力电器股份有限公司 Danger prompting method, equipment and computer readable storage medium
CN112116246A (en) * 2020-09-18 2020-12-22 青岛海信网络科技股份有限公司 Risk processing method and device
CN112116246B (en) * 2020-09-18 2022-12-09 青岛海信网络科技股份有限公司 Risk processing method and device

Similar Documents

Publication Publication Date Title
US11665024B2 (en) Method and apparatus for environmental sensing
CN109308555A (en) A kind of danger early warning method, apparatus, system and video capture device
US11197641B2 (en) Communication device, abnormality notification system, and abnormality notification method
US11185235B2 (en) Information processing method, information processing device, and recording medium
KR20160085033A (en) Learning type emergency detection system with multi-sensor and that method
EP3196854A1 (en) Indoor activity detection based on tag tracking
US9886013B2 (en) Wireless network of low power sensing and actuating motes
CN108153186A (en) A kind of air quality monitoring system
CN105575080A (en) Method for carrying out wireless monitoring on barn
CN113568812A (en) State detection method and device for intelligent robot
CN109166269A (en) Fire early warning device and system based on wireless communication
More et al. A test-bed for habitat monitoring system using Wi-Fi in Wireless Sensor Networks
CN107895453A (en) Building safety warning system and method
CN111896052A (en) Implementation method for monitoring safety of aerial work and wearing device for monitoring safety of aerial work
CN104539628A (en) ZigBee-based equipment monitoring system and monitoring method thereof
CN112212980B (en) Human body temperature detection method capable of resisting external environment temperature interference
GB2603185A (en) An electrical socket system and method
Annese et al. On-line shelf-life prediction in perishable goods chain through the integration of WSN technology with a 1st order kinetic model
CN108170060A (en) Danger source and environment monitoring warning system and method
Bocicor et al. Cyber-physical system for assisted living and home monitoring
CN205373756U (en) Temperature and humidity sensor
SE542317C2 (en) Fall detection system and method
KR20130128664A (en) Data management system
Khudhur et al. Application of self-managing system in greenhouse with wireless sensor network
US20230111264A1 (en) Identification of air quality of indoor spaces

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20190205

RJ01 Rejection of invention patent application after publication