CN106934980B - Method for safety monitoring and alarm method - Google Patents
Method for safety monitoring and alarm method Download PDFInfo
- Publication number
- CN106934980B CN106934980B CN201710324854.9A CN201710324854A CN106934980B CN 106934980 B CN106934980 B CN 106934980B CN 201710324854 A CN201710324854 A CN 201710324854A CN 106934980 B CN106934980 B CN 106934980B
- Authority
- CN
- China
- Prior art keywords
- photo
- processor
- environment
- target area
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001931 thermography Methods 0.000 claims abstract description 27
- 238000010586 diagram Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 11
- 230000000505 pernicious effect Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
- G08B21/14—Toxic gas alarms
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Alarm Systems (AREA)
Abstract
The present invention provides method for safety monitoring and alarm methods, are related to security monitoring field.Method for safety monitoring provided by the invention, it is by being provided with multiple video cameras, multiple thermal imaging systems, moving track, sensor group, multiple guiding indicators, walking robot, phonographic recorder and processor, and, with processor center in order to control, continuously across the judgement and verification of multiple steps, degree of danger value finally is determined, also according to the difference of degree of danger value, it is corresponding to be provided with three kinds of different type of alarms, to more accurate (have passed through multiple judgement), it is more targeted to complete being monitored in time to the fire behavior under indoor this enclosed environment for task.
Description
Technical field
The present invention relates to security monitoring fields, in particular to method for safety monitoring and alarm method.
Background technology
Video monitoring is the main monitoring system of social public security prevention and control.Video monitoring system by Workplace,
The important places such as entrance, garage, main thoroughfare, office install video camera, by monitor place the case where with video image shape
Formula is sent to administrative center in real time, and administrative staff show that equipment can check these places at any time by monitor, video wall etc.
The case where.
The monitoring carried out for indoor environment is generally also by completing based on video monitoring.But with indoor environment
The promotion of complexity, simple one video monitoring camera of use are monitored indoor environment, it is difficult to ensure monitoring
It is comprehensive, and then there is integritied monitoring and controling system, there is a large amount of monitor camera, and then pass through the division of labor in the monitoring system
Mode is completed to indoor whole overall monitor.
But it is found in use, such monitor mode still has certain limitation, monitoring not accurate enough.
Invention content
The purpose of the present invention is to provide method for safety monitoring, to improve the order of accuarcy of monitoring.
In a first aspect, an embodiment of the present invention provides method for safety monitoring, safety monitoring system, the safety prison are acted on
Control system includes：
Multiple video cameras, multiple thermal imaging systems, moving track, sensor group, multiple guiding indicators, running machine
People, phonographic recorder and processor；Processor respectively with multiple video cameras, multiple thermal imaging systems, sensor group, guiding indicator
It is electrically connected with walking robot；
The moving track is arranged on wall, and the moving track includes a plurality of horizontal slide rail and a plurality of vertical cunning
Rail, and any bar horizontal slide rail is connected from each vertical rails in different positions；The video camera and described
Thermal imaging system is arranged on moving track, any one video camera and any one thermal imaging system can be along the horizontal slide rails
It is mobile, and any one video camera and any one thermal imaging system can be moved to another vertical rails from a horizontal slide rail
On；Any one video camera and any one thermal imaging system can be moved along the vertical rails, and any one video camera
It can be moved in another horizontal slide rail from a vertical rails with any one thermal imaging system；
Sensor group include multiple temperature sensors, multiple wind transducers, multiple harmful gas sensors, decibel instrument and
Multiple pyroelectric infrared sensors；The multiple temperature sensor is arranged at the lower part on wall；The wind transducer and
The top on wall is arranged in the decibel instrument；The harmful gas sensor and the pyroelectric infrared sensor are arranged at
On ceiling；
The multiple guiding indicator is separately positioned on wall and ceiling；
The method includes：
Temperature sensor detects the ambient temperature value of target area in real time, and when ambient temperature value is more than predetermined temperature value
When, generate the first trigger signal；
Harmful gas sensor detects the gas station of target area in real time, and second is generated when detecting pernicious gas
Trigger signal；
Processor extracts the high temperature in thermal imaging photo when receiving the first trigger signal and/or the second trigger signal
The high temperature figure in region；
Processor is inquired in high temperature image data base whether there is test pattern similar with the high temperature figure；If
It is no, then target area is shot by the centralised video camera in target area, to obtain first environment photo；
The high temperature figure being previously stored in the high temperature image data base under human body different gestures；
Processor carries out foreground extraction according to the background image in background image data library, to first environment photo, obtains
First actual foreground image；
Processor searches whether there is standard foreground similar with the first actual foreground image in general pattern database
Image；
If criterion foreground image similar with the first actual foreground image is not present, processor judges that pernicious gas senses
Whether device within scheduled continuous a period of time detects pernicious gas, if so, the edge of driving not in the target area
Video camera is moved by moving track towards target area；And driving pyroelectric infrared sensor work；
After when edge, video camera is moved to target area, edge video camera shoots to obtain target area
Take second environment photo；
Edge video camera obtains shooting time and camera site by Big Dipper time dissemination system and BEI-DOU position system；
Edge camera is encrypted and is packaged to second environment photo, shooting time and camera site, is uploaded with being formed
Data packet；
Edge camera is sent to third-party server by independent sending module, by the upload data packet；
Pyroelectric infrared sensor is detected target area after work, if having detected, high temp objects pass through mesh
Region is marked, then generates the second trigger signal；
If processor receives the second trigger signal, guiding indicator work is driven, and start timing；
Processor drives pyroelectric infrared sensor to work again when the timing reaches first time；
Pyroelectric infrared sensor is detected target area after work, if having detected, high temp objects pass through mesh
Region is marked, then generates third trigger signal；
If processor receives third trigger signal, pass through the air speed value of wind transducer measurement target region；Pass through
The volume of decibel instrument measurement target region；It is recorded to target area by phonographic recorder, to obtain target audio and by regarding
Frequency camera shoots target area, to obtain third environment photo；
Processor carries out Application on Voiceprint Recognition to target audio, with the sound clip and voice data in the determination target audio
The audio similarity value of standard voice segment in library；The standard voice segment is the speech production sent out according to natural person
's；
Processor carries out foreground extraction to third environment photo, to determine the second actual foreground image；
Processor calculates the ratio of the image size of the second actual foreground image and the image size of third environment photo, obtains
To image accounting numerical value；
Processor calculates dangerous journey according to audio similarity value, image accounting numerical value, air speed value and the volume of target area
Angle value；
If degree of danger value is located at the first numberical range, processor is by third environment photo and shoots third environment photo
Time be uploaded to third-party server；
If degree of danger value is located at second value range, harmful gas of target area is detected by harmful gas sensor
Bulk concentration, and harmful gas concentration and target audio are sent to third-party server, and adjustment guides the output of indicator
Mode；
If degree of danger value is located at third value range, processor is by third environment photo and shoots third environment photo
Time be uploaded to third-party server, and driving walking robot is moved towards target area, also, walking robot exists
Playing alert tones during being moved towards target area；First numberical range, second value range and third value model
It encloses and is not overlapped numerically.
With reference to first aspect, an embodiment of the present invention provides the first possible embodiments of first aspect, wherein step
Rapid processor calculates degree of danger value packet according to audio similarity value, image accounting numerical value, air speed value and the volume of target area
It includes：
Processor calculates degree of danger value in the way of weighted calculation.
With reference to first aspect, an embodiment of the present invention provides second of possible embodiments of first aspect, wherein step
Suddenly include before the time of third environment photo and shooting third environment photo is uploaded to third-party server by processor：
Processor determines the clarity of each third environment photo respectively, and is more than the third of predetermined threshold by clarity
Environment photo carries out binary conversion treatment, with determination binary picture to be sent；
Binary picture to be sent is encrypted in processor, and by encrypted binary picture to be sent to third party's service
Device is sent.
With reference to first aspect, an embodiment of the present invention provides the third possible embodiments of first aspect, wherein step
Rapid processor carries out foreground extraction according to the background image in background image data library, to first environment photo, and it is real to obtain first
Border foreground image includes：
Processor determines the object time of shooting first environment photo；
Processor searches target background image corresponding with the object time in background image data library；The Background
Obtained background image of taking pictures is carried out to target area as being stored in database in advance in section in different times, and is stored
Image in background image data library updates once week about；
Processor carries out foreground extraction according to target background image to first environment photo, obtains the first actual foreground figure
Picture.
With reference to first aspect, an embodiment of the present invention provides the 4th kind of possible embodiments of first aspect, wherein also
Including：
Processor driving target area in video camera target area is continuously shot, with obtain multiple the 4th
Environment photo；
Processor is grouped multiple the 4th environment photos, obtains multigroup reference according to the sequencing of shooting time
Photo group；The arbitrary two groups shooting time sections with reference to corresponding to photo group are not overlapped, the shooting time with reference to corresponding to photo group
Section is complete with the last one according to the shooting time of same group of the 4th environment photo with reference to the first completion shooting in photo group
It is determined at the shooting time of the 4th environment photo of shooting；
Processor searches object reference photo group, and the similarity of image is more than scheduled threshold in the object reference photo group
Value；
Processor selection target refers to the highest 4th environment photo of clarity in photo group as background image.
With reference to first aspect, an embodiment of the present invention provides the 5th kind of possible embodiments of first aspect, wherein also
Including：
Processor generates the feature point diagram of each 4th environment photo respectively；
Processor calculates each according to the same group of feature point diagram with reference to corresponding to multiple 4th environment photos in photo group
With reference to the photo similarity of photo group；
Processor selects photo similarity highest with reference to photo group as object reference photo group.
With reference to first aspect, an embodiment of the present invention provides the 6th kind of possible embodiments of first aspect, wherein step
Rapid processor calculates each reference and shines according to the same group of feature point diagram with reference to corresponding to multiple 4th environment photos in photo group
The photo similarity of piece group includes：
Processor determines that same group refers in photo group, different 4th environment photo institutes in the way of Feature Points Matching
The distance between the characteristic point to match in corresponding feature point diagram；
Processor calculates same group with reference to photograph according to average weighted mode, according to the distance between characteristic point to match
In piece group, the benchmark similarity of the feature point diagram corresponding to the 4th environment photo of any two；
Processor each refers to the photo similarity of photo group according to benchmark similarity calculation.
With reference to first aspect, an embodiment of the present invention provides the 7th kind of possible embodiments of first aspect, wherein institute
It is 4K video cameras to state video camera.
With reference to first aspect, an embodiment of the present invention provides the 8th kind of possible embodiments of first aspect, wherein
The anti-skidding component of the walking robot lower part setting.
Second aspect, the embodiment of the present invention additionally provide alarm method, including the method for safety monitoring described in first aspect,
Further include：
Processor sends degree of danger value to client used by a user.
Method for safety monitoring provided in an embodiment of the present invention, by being provided with multiple video cameras, multiple thermal imagings
Instrument, moving track, sensor group, multiple guiding indicators, walking robot, phonographic recorder and processor, also, be with processor
Control centre finally determines degree of danger value continuously across the judgement and verification of multiple steps, also according to degree of danger value
Difference, it is corresponding to be provided with three kinds of different type of alarms, to more accurate (have passed through multiple judgement), more targetedly
Complete being monitored in time to the fire behavior under indoor this enclosed environment for task.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows the basic framework figure of safety monitoring system in the method for safety monitoring that the embodiment of the present invention is provided；
The flow chart of the first Optimization Steps of the method for safety monitoring provided Fig. 2 shows the embodiment of the present invention；
Fig. 3 shows the flow chart of second of Optimization Steps of the method for safety monitoring that the embodiment of the present invention is provided；
Fig. 4 shows the flow chart of the third Optimization Steps of the method for safety monitoring that the embodiment of the present invention is provided.
Specific implementation mode
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, the detailed description of the embodiment of the present invention to providing in the accompanying drawings is not intended to limit claimed invention below
Range, but it is merely representative of the selected embodiment of the present invention.Based on the embodiment of the present invention, those skilled in the art are not doing
The every other embodiment obtained under the premise of going out creative work, shall fall within the protection scope of the present invention.
As shown in Figs 1-4, present solution provides method for safety monitoring, act on safety monitoring system, the security monitoring
System includes：
Multiple video cameras 102, multiple thermal imaging systems 103, moving track, sensor group 104, multiple guiding indicators
105, walking robot 107, phonographic recorder 106 and processor 101；Processor 101 respectively with multiple video cameras 102, multiple
Thermal imaging system 103, sensor group 104, guiding indicator 105 and walking robot 107 are electrically connected；
The moving track is arranged on wall, and the moving track includes a plurality of horizontal slide rail and a plurality of vertical cunning
Rail, and any bar horizontal slide rail is connected from each vertical rails in different positions；The video camera 102 and institute
It states thermal imaging system 103 to be arranged on moving track, any one video camera 102 and any one thermal imaging system 103 can edges
The horizontal slide rail movement, and any one video camera 102 and any one thermal imaging system 103 can be moved from a horizontal slide rail
It moves to another vertical rails；Any one video camera 102 and any one thermal imaging system 103 can be along the vertical rails
It is mobile, and any one video camera 102 and any one thermal imaging system 103 can be moved to another cross from a vertical rails
To on sliding rail
Sensor group 104 includes multiple temperature sensors, multiple wind transducers, multiple harmful gas sensors, decibel
Instrument and multiple pyroelectric infrared sensors；The multiple temperature sensor is arranged at the lower part on wall；The wind direction sensing
The top on wall is arranged in device and the decibel instrument；The harmful gas sensor and the pyroelectric infrared sensor are all provided with
It sets on ceiling；
The multiple guiding indicator 105 is separately positioned on wall and ceiling；
The method includes：
Temperature sensor detects the ambient temperature value of target area in real time, and when ambient temperature value is more than predetermined temperature value
When, generate the first trigger signal；
Harmful gas sensor detects the gas station of target area in real time, and second is generated when detecting pernicious gas
Trigger signal；
Processor 101 is extracted when receiving the first trigger signal and/or the second trigger signal in thermal imaging photo
The high temperature figure of high-temperature area；
Processor 101 is inquired in high temperature image data base whether there is test pattern similar with the high temperature figure；
If it is not, then being shot to target area by the centralised video camera 102 in target area, to obtain first environment
Photo；The high temperature figure being previously stored in the high temperature image data base under human body different gestures；
Processor 101 carries out foreground extraction according to the background image in background image data library, to first environment photo, obtains
To the first actual foreground image；
Processor 101 is searched whether in general pattern database before there is standard similar with the first actual foreground image
Scape image；
If criterion foreground image similar with the first actual foreground image is not present, processor 101 judges pernicious gas
Whether sensor within scheduled continuous a period of time detects pernicious gas, if so, driving is not in the target area
Edge video camera 102 is moved by moving track towards target area；And driving pyroelectric infrared sensor work；
After edge video camera 102 is moved to target area, edge video camera 102 claps target area
It takes the photograph to obtain second environment photo；
Edge video camera 102 obtains shooting time and shooting position by Big Dipper time dissemination system and BEI-DOU position system
It sets；
Edge camera is encrypted and is packaged to second environment photo, shooting time and camera site, is uploaded with being formed
Data packet；
Edge camera is sent to third-party server by independent sending module, by the upload data packet；
Pyroelectric infrared sensor is detected target area after work, if having detected, high temp objects pass through mesh
Region is marked, then generates the second trigger signal；
If processor 101 receives the second trigger signal, guiding indicator 105 is driven to work, and start timing；
Processor 101 drives pyroelectric infrared sensor to work again when the timing reaches first time；
Pyroelectric infrared sensor is detected target area after work, if having detected, high temp objects pass through mesh
Region is marked, then generates third trigger signal；
If processor 101 receives third trigger signal, pass through the air speed value of wind transducer measurement target region；It is logical
Cross the volume of decibel instrument measurement target region；It is recorded to target area by phonographic recorder 106, to obtain target audio and lead to
It crosses video camera 102 to shoot target area, to obtain third environment photo；
Processor 101 carries out Application on Voiceprint Recognition to target audio, with the sound clip and sound in the determination target audio
The audio similarity value of standard voice segment in database；The standard voice segment is the voice sent out according to natural person
It generates；
Processor 101 carries out foreground extraction to third environment photo, to determine the second actual foreground image；
Processor 101 calculates the ratio of the image size of the second actual foreground image and the image size of third environment photo
Value, obtains image accounting numerical value；
Processor 101 calculates dangerous according to audio similarity value, image accounting numerical value, air speed value and the volume of target area
Degree value；
If degree of danger value is located at the first numberical range, processor 101 is by third environment photo and shoots third environment
The time of photo is uploaded to third-party server；
If degree of danger value is located at second value range, harmful gas of target area is detected by harmful gas sensor
Bulk concentration, and harmful gas concentration and target audio are sent to third-party server, and adjustment guides the defeated of indicator 105
Go out mode；
If degree of danger value is located at third value range, processor 101 is by third environment photo and shoots third environment
The time of photo is uploaded to third-party server, and driving walking robot 107 is moved towards target area, also, walks
Playing alert tones during being moved towards target area of robot 107；First numberical range, second value range and
It is not overlapped in third value range values.
Wherein, refer to can be for sensor that the prejudicial gas of human body is detected for harmful gas sensor.Have
Evil gas such as carbon monoxide etc., especially refers to the pernicious gas generated by burning.
Ceiling and wall surround the environment for foring relative closure.Ceiling is usually located at the top of wall.
In the present solution, the starting point of triggering is temperature sensor and harmful gas sensor mainly consider that fire behavior is occurring
When, the temperature value of usual environment can rise, but sometimes temperature sensor can not be arranged it is intensive enough, therefore, merely
Certain error is had by temperature sensor, is also used harmful gas sensor in turn, in this programme and is detected as supplement,
Then mainly when fire behavior is in non-expanded state (also imperfect combustion state), environment temperature be will not rise excessively, but
At this point, usually having produced pernicious gas, in turn, certain prevention work can be also played by the way that harmful gas sensor is arranged
With.
Thermal imaging photo can clearly react high temperature figure, and the high temperature of human body should be stored in high temperature image data base
Figure, and then test pattern similar with the high temperature figure whether there is by inquiry, to determine whether flase drop.
Edge video camera and centralised video camera belong to a part for video camera, distinguish the foundation of the two
Be video camera whether there is in target area.Due to needing to drive edge video camera in certain steps,
It should be each video camera configuration driven structure.
Pyroelectric infrared sensor is capable of detecting when the heat source of mobile status, therefore, if passing through if there is pedestrian, passes through
What the sensor can will be apparent that detects.Successively the purpose of driving pyroelectric infrared sensor work is to ensure that and will not go out twice
Existing flase drop.The effect that wind transducer is arranged, which is the movement speed of detection pedestrian, (if pedestrian's movement is too fast, can drive environment
Wind speed improve).
Under normal conditions, the first numberical range, second value range and third value range are increased with this, such as the first numerical value
It is 10-15, third value range is 15-25 that range, which is 5-10, second value range,.
Preferably, for the using flexible to user's bigger, and the accuracy calculated is improved, step processor is according to sound
Frequency similarity value, image accounting numerical value, air speed value and the volume of target area calculate degree of danger value：Processor is according to adding
The mode that power calculates calculates degree of danger value.
Used weights can voluntarily be concluded by user when specific weighted calculation.
Preferably, in order to guarantee data security, step processor is by third environment photo and shoots third environment photo
Time includes before being uploaded to third-party server：
S201, processor determine the clarity of each third environment photo respectively, and are more than predetermined threshold by clarity
Third environment photo carry out binary conversion treatment, with determination binary picture to be sent；
Binary picture to be sent is encrypted in S202, processor, and by encrypted binary picture to be sent to third
Square server is sent.
In turn, after binaryzation, the complexity of picture is reduced, the safety of data is also ensure that by encrypted mode.
Preferably, step processor is according to the background image in background image data library, before being carried out to first environment photo
Scape extracts, and obtaining the first actual foreground image includes：
S301, processor determine the object time of shooting first environment photo；
S302, processor search target background image corresponding with the object time in background image data library；It is described
It is stored in background image data library in advance section in different times and obtained background image of taking pictures is carried out to target area,
And it is stored in the image in background image data library and updates week about once；
S303, processor carries out foreground extraction according to target background image to first environment photo, before obtaining the first reality
Scape image.
Photo in background image data library be stored in advance in it is therein, it is typically advance by corresponding video camera
It has been shot that, certainly, shooting when needs to ensure that current environment is in a safe condition.Also, update is primary weekly, energy
Enough ensure it with enough reference values.
Preferably, scheme provided herein further includes the following process for determining background image：
S401, processor drives the video camera in target area to be continuously shot target area, more to obtain
Open the 4th environment photo；
S402, processor are grouped multiple the 4th environment photos, obtain multigroup according to the sequencing of shooting time
With reference to photo group；The arbitrary two groups shooting time sections with reference to corresponding to photo group are not overlapped, the shooting with reference to corresponding to photo group
Period is according to the shooting time of same group of the 4th environment photo with reference to the first completion shooting in photo group and last
What the shooting time of a the 4th environment photo for completing shooting determined；
S403, processor search object reference photo group, and the similarity of image is more than pre- in the object reference photo group
Fixed threshold value；
S404, processor selection target refer to the highest 4th environment photo of clarity in photo group as Background
Picture.
Wherein, the result after grouping such as can be as follows, the bat of the 4th environment picture A BC in the first reference photo group
It is 1 minute, 2 minutes and 3 minutes to take the photograph the time respectively；The shooting time point of the 4th environment photo DEF in second reference photo group
It is not 5 minutes, 6 minutes and 7 minutes.In turn, the shooting time section of the first reference photo group is exactly 1-3 minutes, and first with reference to photograph
The shooting time section of piece group is exactly 5-7 minutes.
Preferably, scheme provided herein further includes：
Processor generates the feature point diagram of each 4th environment photo respectively；
Processor calculates each according to the same group of feature point diagram with reference to corresponding to multiple 4th environment photos in photo group
With reference to the photo similarity of photo group；
Processor selects photo similarity highest with reference to photo group as object reference photo group.
Preferably, step processor is according to the same group of characteristic point with reference to corresponding to multiple 4th environment photos in photo group
Figure, calculating the photo similarity each with reference to photo group includes：
Processor determines that same group refers in photo group, different 4th environment photo institutes in the way of Feature Points Matching
The distance between the characteristic point to match in corresponding feature point diagram；
Processor calculates same group with reference to photograph according to average weighted mode, according to the distance between characteristic point to match
In piece group, the benchmark similarity of the feature point diagram corresponding to the 4th environment photo of any two；
Processor each refers to the photo similarity of photo group according to benchmark similarity calculation.
In turn, by the way of Feature Points Matching, first by the linked character point of two photos to (one in a photo
Characteristic point and a most like feature point group in another photo at characteristic point to) confirmed (wherein, feature point diagram
In marked out characteristic point, can with peripheral region generate significant difference point).
As shared 5 characteristic points in the 4th environment picture A, 5 characteristic points are shared in the 4th environment photo B, then first
It needs to match 5 characteristic points in AB this two photos, can only be pairing two-by-two (pairing form characteristic point to), and
Each characteristic point is used only once.Then, the distance between each two characteristic points of characteristic point centering are calculated separately, as spy
The characteristic point similarity of sign point pair, and then again phase of the photo relative to another photo is calculated according to characteristic point similarity
Like degree, finally add up the photo similarity formed with reference to photo.
Preferably, the video camera is 4K video cameras.
Preferably, in the anti-skidding component of walking robot lower part setting.
Present invention also provides alarm methods, including method for safety monitoring, further include：
Processor sends degree of danger value to client used by a user.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be expressed in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic disc or CD.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. method for safety monitoring, safety monitoring system is acted on, the safety monitoring system includes sensor group and processor,
It is characterized in that, the safety monitoring system further includes：
Multiple video cameras, multiple thermal imaging systems, moving track, multiple guiding indicators, walking robot and phonographic recorder；Place
Reason device is electrically connected with multiple video cameras, multiple thermal imaging systems, sensor group, guiding indicator and walking robot respectively；
The moving track is arranged on wall, and the moving track includes a plurality of horizontal slide rail and a plurality of vertical rails, and
Any bar horizontal slide rail is connected from each vertical rails in different positions；The video camera and the thermal imaging
Instrument is arranged on moving track, any one video camera and any one thermal imaging system can be moved along the horizontal slide rail,
And any one video camera and any one thermal imaging system can be moved to from a horizontal slide rail in another vertical rails；Appoint
One video camera and any one thermal imaging system can be moved along the vertical rails, and any one video camera and any
A thermal imaging system can be moved to from a vertical rails in another horizontal slide rail；
Sensor group includes multiple temperature sensors, multiple wind transducers, multiple harmful gas sensors, decibel instrument and multiple
Pyroelectric infrared sensor；The multiple temperature sensor is arranged at the lower part on wall；The wind transducer and described
The top on wall is arranged in decibel instrument；The harmful gas sensor and the pyroelectric infrared sensor are arranged at ceiling
On；
The multiple guiding indicator is separately positioned on wall and ceiling；
The method includes：
Temperature sensor detects the ambient temperature value of target area in real time, and when ambient temperature value is more than predetermined temperature value, raw
At the first trigger signal；
Harmful gas sensor detects the gas station of target area in real time, and the second triggering is generated when detecting pernicious gas
Signal；
Processor extracts the high-temperature area in thermal imaging photo when receiving the first trigger signal and/or the second trigger signal
High temperature figure；
Processor is inquired in high temperature image data base whether there is test pattern similar with the high temperature figure；If it is not, then
Target area is shot by the centralised video camera in target area, to obtain first environment photo；It is described
The high temperature figure being previously stored in high temperature image data base under human body different gestures；
Processor carries out foreground extraction according to the background image in background image data library, to first environment photo, obtains first
Actual foreground image；
Processor searches whether there is criterion foreground image similar with the first actual foreground image in general pattern database；
If criterion foreground image similar with the first actual foreground image is not present, processor judges that harmful gas sensor is
It is no to detect pernicious gas within scheduled continuous a period of time, if so, the edge video of driving not in the target area
Camera is moved by moving track towards target area；And driving pyroelectric infrared sensor work；
After when edge, video camera is moved to target area, edge video camera shoots target area to obtain
Two environment photos；
Edge video camera obtains shooting time and camera site by Big Dipper time dissemination system and BEI-DOU position system；
Edge camera is encrypted and is packaged to second environment photo, shooting time and camera site, to form upload data
Packet；
Edge camera is sent to third-party server by independent sending module, by the upload data packet；
Pyroelectric infrared sensor is detected target area after work, if having detected, high temp objects pass through target area
Domain then generates the second trigger signal；
If processor receives the second trigger signal, guiding indicator work is driven, and start timing；
Processor drives pyroelectric infrared sensor to work again when the timing reaches first time；
Pyroelectric infrared sensor is detected target area after work, if having detected, high temp objects pass through target area
Domain then generates third trigger signal；
If processor receives third trigger signal, pass through the air speed value of wind transducer measurement target region；Pass through decibel
The volume of instrument measurement target region；It is recorded to target area by phonographic recorder, to obtain target audio and be taken the photograph by video
As head shoots target area, to obtain third environment photo；
Processor carries out Application on Voiceprint Recognition to target audio, in the sound clip and audio database in the determination target audio
Standard voice segment audio similarity value；The standard voice segment is the speech production sent out according to natural person；
Processor carries out foreground extraction to third environment photo, to determine the second actual foreground image；
Processor calculates the ratio of the image size of the second actual foreground image and the image size of third environment photo, obtains figure
As accounting numerical value；
Processor calculates degree of danger value according to audio similarity value, image accounting numerical value, air speed value and the volume of target area；
If degree of danger value is located at the first numberical range, processor by third environment photo and shooting third environment photo when
Between be uploaded to third-party server；
If degree of danger value is located at second value range, the pernicious gas that target area is detected by harmful gas sensor is dense
Degree, and harmful gas concentration and target audio are sent to third-party server, and adjustment guides the way of output of indicator；
If degree of danger value is located at third value range, processor by third environment photo and shooting third environment photo when
Between be uploaded to third-party server, and driving walking robot is moved towards target area, also, walking robot is in direction
Playing alert tones during target area is moved；First numberical range, second value range and third value range number
It is not overlapped in value.
2. method for safety monitoring according to claim 1, which is characterized in that step processor according to audio similarity value,
Image accounting numerical value, air speed value and the volume of target area calculate degree of danger value：
Processor calculates degree of danger value in the way of weighted calculation.
3. method for safety monitoring according to claim 1, which is characterized in that step processor is by third environment photo and bat
Take the photograph third environment photo time be uploaded to third-party server before include：
Processor determines the clarity of each third environment photo respectively, and is more than the third environment of predetermined threshold by clarity
Photo carries out binary conversion treatment, with determination binary picture to be sent；
Binary picture to be sent is encrypted in processor, and encrypted binary picture to be sent is sent out to third-party server
It send.
4. method for safety monitoring according to claim 1, which is characterized in that step processor is according to background image data library
In background image, to first environment photo carry out foreground extraction, obtaining the first actual foreground image includes：
Processor determines the object time of shooting first environment photo；
Processor searches target background image corresponding with the object time in background image data library；The background image number
Obtained background image of taking pictures is carried out to target area according to being stored in library in advance in section in different times, and is stored in the back of the body
Image in scape image data base updates once week about；
Processor carries out foreground extraction according to target background image to first environment photo, obtains the first actual foreground image.
5. method for safety monitoring according to claim 4, which is characterized in that further include：
Video camera in processor driving target area is continuously shot target area, to obtain multiple the 4th environment
Photo；
Processor is grouped multiple the 4th environment photos according to the sequencing of shooting time, obtains multigroup with reference to photo
Group；The arbitrary two groups shooting time sections with reference to corresponding to photo group are not overlapped, and the shooting time section with reference to corresponding to photo group is
It is clapped according to the shooting time of same group of the 4th environment photo with reference to the first completion shooting in photo group and the last one completion
What the shooting time for the 4th environment photo taken the photograph determined；
Processor searches object reference photo group, and the similarity of image is more than scheduled threshold value in the object reference photo group；
Processor selection target refers to the highest 4th environment photo of clarity in photo group as background image.
6. method for safety monitoring according to claim 5, which is characterized in that further include：
Processor generates the feature point diagram of each 4th environment photo respectively；
Processor calculates each reference according to the same group of feature point diagram with reference to corresponding to multiple 4th environment photos in photo group
The photo similarity of photo group；
Processor selects photo similarity highest with reference to photo group as object reference photo group.
7. method for safety monitoring according to claim 6, which is characterized in that step processor refers to photo according to same group
Feature point diagram in group corresponding to multiple 4th environment photos, calculating the photo similarity each with reference to photo group includes：
Processor determines that same group refers in photo group, corresponding to different 4th environment photos in the way of Feature Points Matching
Feature point diagram in the distance between the characteristic point that matches；
Processor calculates same group according to average weighted mode, according to the distance between characteristic point to match and refers to photo group
In, the benchmark similarity of the feature point diagram corresponding to the 4th environment photo of any two；
Processor each refers to the photo similarity of photo group according to benchmark similarity calculation.
8. method for safety monitoring according to claim 1, which is characterized in that the video camera is 4K video cameras.
9. method for safety monitoring according to claim 1, which is characterized in that in the walking robot lower part, setting is anti-
Sliding component.
10. alarm method, which is characterized in that including such as claim 1-9 any one of them method for safety monitoring, further include：
Processor sends degree of danger value to client used by a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710324854.9A CN106934980B (en) | 2017-05-10 | 2017-05-10 | Method for safety monitoring and alarm method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710324854.9A CN106934980B (en) | 2017-05-10 | 2017-05-10 | Method for safety monitoring and alarm method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106934980A CN106934980A (en) | 2017-07-07 |
| CN106934980B true CN106934980B (en) | 2018-10-23 |
Family
ID=59429503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710324854.9A Active CN106934980B (en) | 2017-05-10 | 2017-05-10 | Method for safety monitoring and alarm method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106934980B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111201785B (en) * | 2017-10-18 | 2021-12-14 | 三菱电机株式会社 | Image sharing support device, image sharing system, and image sharing support method |
| CN109099893B (en) * | 2018-07-03 | 2021-04-27 | 中影数字巨幕（北京）有限公司 | Monitoring method, medium and computing device used in movie theatre |
| CN109583772A (en) * | 2018-12-04 | 2019-04-05 | 上海宝冶集团有限公司 | Method for managing and monitoring, device, system and the readable storage medium storing program for executing of construction site |
| CN109639967A (en) * | 2018-12-12 | 2019-04-16 | 深圳市沃特沃德股份有限公司 | Monitoring method, system and computer readable storage medium |
| CN109993949B (en) * | 2019-04-14 | 2021-06-29 | 杭州拓深科技有限公司 | Fire safety detection method based on multi-sensor fusion |
| CN111359132B (en) * | 2020-03-30 | 2021-07-30 | 重庆特斯联智慧科技股份有限公司 | Intelligent fire-fighting alarm method and system based on artificial intelligence |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3924252A1 (en) * | 1989-07-21 | 1991-02-07 | Preussag Ag Feuerschutz | Fire detection equipment for sensing source of heat - uses array of temperature sensors with microprocessor control to detect fires and store information |
| CN1044524C (en) * | 1993-11-05 | 1999-08-04 | 中国科学技术大学 | Fire alarm with image distinguish function |
| JPH11160158A (en) * | 1997-11-28 | 1999-06-18 | Hochiki Corp | Fire monitoring device |
| US7397369B2 (en) * | 2005-02-08 | 2008-07-08 | Ftc - Forward Threat Control Llc | Sensor and transmission control circuit in adaptive interface package |
| KR100990334B1 (en) * | 2008-04-30 | 2010-10-29 | (주)지오시스템 | Flame Detector and thereof Remote Controller, Method to Offer Mounting State of Flame Detector |
| CN203644161U (en) * | 2013-11-19 | 2014-06-11 | 西安奥赛福科技有限公司 | Fire alarm control system |
| CN204242355U (en) * | 2014-11-28 | 2015-04-01 | 陕西亚泰电器科技有限公司 | A kind of intelligent domestic alarm controller |
| CN106297157A (en) * | 2016-10-25 | 2017-01-04 | 上海腾盛智能安全科技股份有限公司 | A kind of comprehensive detection system collecting image detector |
| CN106448023B (en) * | 2016-12-01 | 2021-06-08 | 上海腾盛智能安全科技股份有限公司 | Fire smoke alarm with storage function |
-
2017
- 2017-05-10 CN CN201710324854.9A patent/CN106934980B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106934980A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106934980B (en) | Method for safety monitoring and alarm method | |
| US9047668B2 (en) | Location determination for an object using visual data | |
| TWI502558B (en) | Traffic Accident Monitoring and Tracking System | |
| US20210400240A1 (en) | Image processing apparatus, image processing method, and computer readable medium | |
| JPWO2007138811A1 (en) | Suspicious behavior detection apparatus and method, program, and recording medium | |
| KR20170018662A (en) | Location tracking system and method | |
| KR101679597B1 (en) | System for managing objects and method thereof | |
| JPWO2020022042A1 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, program | |
| WO2020202694A1 (en) | Surveillance system, surveillance device, surveillance method, and non-temporary computer readable medium | |
| CN106558317A (en) | Sound processing apparatus and sound processing method | |
| CN113192283B (en) | Wireless fire early warning system with multi-sensor information fusion | |
| CN106997447A (en) | Face identification system and face identification method | |
| JPWO2020166057A1 (en) | Fiber optic sensing system, behavior identification device, behavior identification method, and program | |
| TW201443835A (en) | Method of detecting emergency utilized in mobile device | |
| CN106209595A (en) | Information prompting method and device | |
| CN104913779A (en) | Emergency evacuation navigation method and apparatus thereof | |
| CN106969772B (en) | Guide dog method based on mobile phone platform | |
| KR101107120B1 (en) | Device for sound source tracing and object recognition and method for sound source tracing and object recognition | |
| CN108564751A (en) | The monitoring method of cable tunnel anti-intrusion, apparatus and system | |
| JPWO2020157917A1 (en) | Fiber optic sensing system, state detector, state detection method, and program | |
| CN114419481A (en) | Outdoor child unattended detection method and device based on community cerebellum monitoring | |
| US20230401941A1 (en) | Monitoring system, monitoring apparatus, monitoring method, and computer readable medium | |
| CN117557966A (en) | Campus abnormal behavior safety detection method and system based on monitoring image recognition | |
| WO2019187288A1 (en) | Information processing device, data generation method, and non-transient computer-readable medium whereon program has been stored | |
| US20200372779A1 (en) | Terminal device, risk prediction method, and recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |