CN108986379B - Flame detector with infrared photographing function and control method thereof - Google Patents
Flame detector with infrared photographing function and control method thereof Download PDFInfo
- Publication number
- CN108986379B CN108986379B CN201810928780.4A CN201810928780A CN108986379B CN 108986379 B CN108986379 B CN 108986379B CN 201810928780 A CN201810928780 A CN 201810928780A CN 108986379 B CN108986379 B CN 108986379B
- Authority
- CN
- China
- Prior art keywords
- resistor
- control unit
- infrared
- picture
- adp509x
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000001931 thermography Methods 0.000 claims abstract description 44
- 238000004891 communication Methods 0.000 claims abstract description 22
- 239000003990 capacitor Substances 0.000 claims description 32
- 230000005669 field effect Effects 0.000 claims description 22
- 241000282414 Homo sapiens Species 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 3
- 238000005530 etching Methods 0.000 claims 1
- 238000009826 distribution Methods 0.000 description 13
- 238000012790 confirmation Methods 0.000 description 11
- 230000007613 environmental effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000005286 illumination Methods 0.000 description 8
- 230000008030 elimination Effects 0.000 description 6
- 238000003379 elimination reaction Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 101100489713 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) GND1 gene Proteins 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- HEMJJKBWTPKOJG-UHFFFAOYSA-N Gemfibrozil Chemical compound CC1=CC=C(C)C(OCCCC(C)(C)C(O)=O)=C1 HEMJJKBWTPKOJG-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
-
- 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
Abstract
The invention discloses a flame detector with an infrared camera and a control method thereof, wherein the flame detector comprises an MCU (microprogrammed control unit) main control unit, the MCU main control unit is also connected with an image recognition unit, and the image recognition unit is connected with a visible light image sensor and an infrared image sensor array; the infrared image sensor array is used for capturing an infrared thermal imaging picture of the fire scene and the temperature value of each pixel in the picture; the MCU main control unit acquires a visible light picture of the image recognition unit and combines an infrared thermal imaging picture to carry out fire recognition; the MCU main control unit is also connected with an NB-IoT wireless communication unit to send fire information. The invention can improve the identification accuracy of flame and improve the acquisition efficiency and the utilization efficiency of the power supply of the equipment.
Description
Technical Field
The invention relates to the technical field of forest fire monitoring, in particular to a flame detector with an infrared camera and a control method thereof.
Background
The traditional forest fire prevention means mainly comprises the steps of forest maintainers patrolling and camera monitoring. The forest guard cannot monitor all fireproof areas in real time through patrol, and the uncontrollable factors of fire prevention depend on manpower are too many; the camera monitoring power consumption is large, wired power supply is needed, the installation position is limited, and the early fire monitoring of surface fire and forest fire is difficult, so that the development direction of pursuing the fire detection time point to be earlier and earlier in the industry cannot be met.
At present, the related domestic multi-sensing combined dual-waveband photographing type mixed flame detector and the detection method thereof have few applied patents and have certain limitations. The existing ultraviolet infrared flame detectors on the market cannot realize visualization and evidence collection; the embedded image acquisition is mainly applied to a field hunting camera, does not apply to forest fire prevention, and cannot solve the problems of accuracy and reliability of field long-term forest fire real-time detection and evidence obtaining. The existing equipment device for monitoring the early fire condition under the forest and capturing and obtaining evidence by combining a flame sensor and an image recognition technology can realize low-power-consumption self-powered all-weather monitoring and makes great progress in the aspects of fire detection and on-site evidence obtaining. In fact, the flame detector with infrared shooting in the field is limited by energy consumption and transmission bandwidth, pixels of a visible light sensor have to be reduced, and a field image has to be compressed and then transmitted back, so that the final flame confirmation is carried out by only depending on the image, and high-brightness light spots such as field illumination, lamplight and the like cannot be clearly excluded. In an actual application scene, the situation that the flame on the spot cannot be judged also exists, manual patrol confirmation is also caused to forest protection personnel, the labor cost is increased, and the best fire emergency disposal time is possibly delayed.
With the development of information technology and sensing technology, the problems of forest fire prevention and evidence collection difficulty can be effectively solved only by using low-power-consumption flame identification sensing technology and embedded image acquisition identification technology and low-power-consumption wireless transmission technology.
the image acquisition system is only a visible light picture sensor and cannot acquire infrared thermal imaging pictures, so that final flame confirmation is carried out only by depending on the visible light pictures, and high-brightness light spots such as field illumination, lamplight and the like cannot be clearly excluded. In an actual application scene, the situation that the flame on site cannot be judged exists, and false alarm is easily caused by the interference of ambient light.
As can be seen from fig. 2 of the reference document 1, the solar cell panel directly supplies power to the rechargeable battery, and the power acquisition module is absent, so that the solar energy acquisition effect is poor, the rechargeable battery charging effect is poor, the rechargeable battery and the super capacitor supply power to each module through the plurality of voltage conversion chips, more electric energy is wasted, and the power utilization effect is poor; low energy consumption is very important for flame detectors placed in the field.
Reference 2: application No. 201710847837.3 discloses a photographing type hybrid flame detector and a detection method thereof; the patent does not disclose the above distinguishing technical features and lacks technical means for solving the above related technical problems.
Disclosure of Invention
In view of at least one of the defects in the prior art, an object of the present invention is to provide a flame detector with infrared photography and a control method thereof, which collect a visible light picture in combination with an infrared thermal imaging picture to confirm a fire, and improve the recognition accuracy of flames.
In order to achieve the purpose, the invention adopts the following technical scheme: the utility model provides a take flame detector of infrared shooting which the key lies in: the system comprises an MCU main control unit, wherein the MCU main control unit is also connected with an image recognition unit, and the image recognition unit is connected with a visible light image sensor and an infrared image sensor array; the infrared image sensor array is used for capturing an infrared thermal imaging picture of the fire scene and the temperature value of each pixel in the picture;
the MCU main control unit acquires a visible light picture of the image recognition unit and combines an infrared thermal imaging picture to carry out fire recognition;
the MCU main control unit is also connected with an NB-IoT wireless communication unit to send fire information.
Through the structural arrangement, the visible light image is collected through the visible light image sensor and the infrared image sensor array, the infrared thermal imaging image is combined with the visible light image to confirm the flame signal, and the identification accuracy of flame is improved.
Because the identification is easily influenced by the field illumination only by the visible light picture, the invention acquires the visible light picture and combines the infrared thermal imaging picture for processing, calculates the correlation coefficient of the visible light picture and confirms the fire.
And finally, sending the signals to a supervisor through an NB-IoT wireless communication unit, namely a narrowband Internet of things module.
The flame detector with the infrared photographing function can be used for final identification of flame signals in a fire scene, namely infrared signal identification or ultraviolet signal identification of the flame signals can be added before image identification, and accuracy is improved.
The control method of the flame detector with the infrared photographing is used for the flame detector with the infrared photographing and is characterized by comprising the following steps of,
step C1, the MCU master control unit starts an image recognition unit to collect visible light picture data VisablePic [ m ];
step C2, the MCU main control unit converts the visible light picture data VisablePic [ m ] into a Gray image VisablePicy [ m ], performs convolution with a convolution kernel, and calculates the peak value of the convolved Gray image VisablePicy _ Conv [ m ] to obtain the picture data VisablePic _ Gray _ Peek after calculating the peak value, and performs binarization to obtain a binarization result picture VisablePic _ Bool;
step C3, the MCU main control unit performs morphological corrosion, filtering, expansion and reduction on the binarization result picture VisablePC _ Bool to obtain a filtering binarization picture VisablePC _ Bool _ Reduce;
step C4, the MCU main control unit filters the filtered binary picture VisablePico _ Bool _ Reduce to obtain a suspected flame characteristic picture VisablePico _ Final;
step C5, the MCU main control unit collects the infrared thermal imaging picture IrPic and the temperature value of each pixel of the infrared thermal imaging picture; carrying out binarization processing on the infrared thermal imaging picture IrPic to obtain a binarized infrared thermal imaging picture IrPic _ Bool;
step C6, the MCU main control unit calculates the picture correlation coefficient Count _ Fire of the suspected flame characteristic picture VisablePinal and the binary infrared thermal imaging picture IrPic _ Bool;
step C7, the MCU main control unit judges that the picture correlation coefficient Count _ Fire is higher than the experience threshold value, and finally identifies the picture correlation coefficient Count _ Fire as a flame early warning signal, and the step C8 is entered; otherwise, returning to the step C1;
in addition to returning to step C1, if infrared signal recognition or ultraviolet signal recognition of flame signals is set before the image recognition of the present invention, it is also possible to return to the infrared signal recognition process or ultraviolet signal recognition process of flame signals;
and step C8, the MCU main control unit uploads the fire warning signal, the visible light picture data VisablePic [ m ] and the infrared thermal imaging picture IrPic through the NB-IoT communication module.
The invention has the remarkable effects that the invention provides the flame detector with the infrared photographing function and the control method thereof, the visible light picture is collected and the infrared thermal imaging picture is combined to confirm the fire, and the identification accuracy of the flame is improved.
Drawings
FIG. 1 is a block diagram of the present invention; FIG. 2 is a circuit diagram of an integrated infrared flame sensor;
FIG. 3 is a circuit diagram of an MCU master control unit; FIG. 4 is a circuit diagram of an ultraviolet acquisition circuit;
FIG. 5 is a circuit diagram of an image recognition unit; FIG. 6 is a circuit diagram of a visible light picture sensor;
FIG. 7 is a circuit diagram of an infrared image sensor array; FIG. 8 is a circuit diagram of a light energy collecting unit;
FIG. 9 is a circuit diagram of a power management unit; FIG. 10 is a flow chart of a method of the present invention.
Fig. 11 is a flowchart of a control method of the cloud platform.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
As shown in fig. 1-11, a flame detector with infrared photographing comprises an MCU main control unit 1, wherein the MCU main control unit 1 is connected with an integrated infrared flame sensor 2, and the integrated infrared flame sensor 2 is integrated with a first flame infrared sensing unit, a second flame infrared sensing unit, a human body infrared sensing unit and a background infrared reference sensing unit; the MCU main control unit 1 is also connected with an ultraviolet flame sensor 4 through an ultraviolet acquisition circuit 3;
as shown in fig. 2, S1, S3, S2 and S4 respectively represent the first flame infrared sensing unit, the second flame infrared sensing unit, the human body infrared sensing unit and the background infrared reference sensing unit; since the sensor ePY122X belongs to the existing mature module, the internal structure thereof is not described in detail, and the integrated infrared flame sensor 2 is also connected with the MCU main control unit 1 through the interrupt connection end INT; requesting an interrupt signal to the MCU main control unit 1; the wavelength of S2 was 5 μm, the wavelength of S4 was 3.91 μm, the wavelength of S1 was 4.64 μm, and the wavelength of S3 was 4.48 μm. The MCU main control unit 1 is also connected with an environmental parameter sensing unit 5, and the environmental parameter sensing unit 5 is used for collecting atmospheric temperature, humidity, illuminance and ultraviolet intensity signals;
the MCU main control unit 1 is also connected with an image recognition unit 6, and the image recognition unit 6 is connected with a visible light image sensor 61 and an infrared image sensor array 62; the visible light image sensor 61 is used for capturing a visible light picture of a fire scene, and the infrared image sensor array 62 is used for capturing an infrared thermal imaging picture of the fire scene and temperature values of all pixels in the picture;
the method comprises the following steps that an MCU (microprogrammed control Unit) main control unit 1 acquires an infrared flame signal of an integrated infrared flame sensor 2, primary flame infrared identification is carried out by combining a illuminance signal of an environment parameter sensing unit 5, a signal of an ultraviolet flame sensor 4 is acquired by the MCU main control unit 1, flame signal confirmation is carried out by combining an ultraviolet intensity signal of the environment parameter sensing unit 5, and a visible light picture of an image identification unit 6 is acquired by the MCU main control unit 1, and final fire identification is carried out by combining an infrared thermal imaging picture;
the MCU main control unit 1 is also connected with an NB-IoT wireless communication unit 7 to transmit fire information.
Through foretell structure setting, adopt integrated infrared flame sensor 2, gather multiple infrared signal and carry out primary discernment, carry out the secondary through the flame ultraviolet signal that ultraviolet flame sensor 4 gathered and confirm, gather the visible light picture through visible light image sensor 61 and infrared image sensor array 62 at last and combine infrared thermal imaging picture to carry out final confirmation, improve the identification accuracy degree of flame.
The first flame infrared sensing unit and the second flame infrared sensing unit are respectively used for collecting flame infrared signals with two different wavelengths, the human body infrared sensing unit is used for collecting human body infrared interference signals, namely interference infrared signals sent by human beings or animals, and the background infrared reference sensing unit is used for collecting infrared wavelength signals sent by a background environment; signals acquired by the first flame infrared sensing unit and the second flame infrared sensing unit are subjected to Fourier transform, if the signals are judged to have flame signal characteristics, correlation coefficients of the human body infrared sensing unit and the background infrared reference sensing unit are respectively obtained, and if the correlation coefficients are consistent with the flame characteristics, the signals are primarily identified as flame signals.
The ultraviolet flame sensor 4 is used for collecting an ultraviolet signal of flame and carrying out secondary confirmation by combining the ultraviolet signal of the environment parameter sensing unit 5.
Because the identification is easily influenced by the field illumination only by the visible light picture, the invention acquires the visible light picture and combines the infrared thermal imaging picture for processing, calculates the correlation coefficient and finally confirms.
And finally, sending the signals to a supervisor through an NB-IoT wireless communication unit 7, namely a narrowband Internet of things module.
The light energy collection device further comprises a light energy collection unit 8, after the light energy collection unit 8 converts light energy into electric energy, the electric energy directly supplies power to the MCU main control unit 1, and the light energy collection unit 8 supplies power to the integrated infrared flame sensor 2, the ultraviolet acquisition circuit 3, the environmental parameter sensing unit 5, the image recognition unit 6, the visible light image sensor 61, the infrared image sensor array 62 and the NB-IoT wireless communication unit 7 through the power management unit 81. The MCU main control unit 1 controls the power management unit 81 to supply power.
Through the structure, the solar energy is collected by the light energy collecting unit 8 to supply power to the flame detector with the infrared photographing function, and a power line does not need to be built in a forest area. The MCU main control unit 1 manages power supply through the power management unit 81, improves the collection rate and the utilization rate of a power supply, and can obviously reduce the energy consumption of the flame detector.
The MCU main control unit 1 is an MSP430 singlechip;
the light energy collecting unit 8 comprises solar cell panels S1 and ADP509X collecting modules, the MCU main control unit 1 is provided with a power supply collecting end group, and the MSP430 single chip microcomputer is connected with the ADP509X collecting module through the power supply collecting end group;
a power supply end of the solar panel S1 is connected with one end of a resistor R1, the other end of the resistor R1 is grounded through a capacitor C1, and the other end of the resistor R1 is connected with a VIN end of an ADP509X collection module; the VIN end of the ADP509X collection module is connected with the SW end of the ADP509X collection module through an inductor L1; the ground end of the solar panel S1 is grounded;
the ground end of the ADP509X power module is grounded;
one end of the resistor R1 is further connected to the source of the field effect transistor M1, the drain of the field effect transistor M1 is connected to the other end of the resistor R1, one end of the resistor R1 is further connected to one end of the resistor R2, the other end of the resistor R2 is connected to the gate of the field effect transistor M1, the drain of the field effect transistor M1 is further connected to one end of the resistor R4, the other end of the resistor R4 is grounded through the resistor R5, the other end of the resistor R4 is connected to the non-inverting input terminal of the integrated operational amplifier U1, the non-inverting input terminal of the integrated operational amplifier U1 is further connected to one end of the resistor R3, the other end of the resistor R3 is connected to the gate of the field effect transistor M1, the other end of the resistor R3 is further connected to the output terminal of the integrated operational amplifier U1, the inverting input terminal of the integrated operational amplifier U1 is connected to the REG-OUT terminal of the collection module 6, the inverting input terminal of the integrated operational amplifier U6 is grounded through the REG-OUT terminal of the collection module;
the VIN end of the ADP509X collection module is also connected with one end of a resistor R8, and the other end of the resistor R8 is connected with the MPPT end of the ADP509X collection module; the other end of the resistor R8 is grounded through a resistor R9, the VID end of the ADP509X collection module is grounded through a resistor R10, the CBP end of the ADP509X collection module is grounded through a capacitor C2, and the MINOP end of the ADP509X collection module is grounded through a capacitor C3;
the BACK-UP end of the ADP509X collection module is connected with the anode of the super capacitor, and the cathode of the super capacitor is grounded; the BAT end of the ADP509X collection module is connected with the positive electrode of the rechargeable battery, and the negative electrode of the rechargeable battery is grounded;
the REG-OUT end of the ADP509X power module is also connected with one end of a resistor R11, the other end of the resistor R11 is connected with the REG-FB end of the ADP509X power module, and the other end of the resistor R11 is also grounded through a resistor R21;
the REF end of the ADP509X power module is connected with one end of a resistor R12, the other end of the resistor R12 is connected with the SETSD end of the ADP509X power module, and the other end of the resistor R12 is grounded through a resistor R13;
the REF end of the ADP509X power module is further connected with one end of a resistor R14, the other end of the resistor R14 is connected with the SETPG end of the ADP509X power module, the other end of the resistor R14 is further connected with one end of a resistor R15, the other end of the resistor R15 is connected with the SETHYST end of the ADP509X power module, and the other end of the resistor R15 is further grounded through a resistor R16;
the REF end of the ADP509X power module is also connected with one end of a resistor R17, the other end of the resistor R17 is connected with the SETBK end of the ADP509X power module, and the other end of the resistor R17 is also grounded through a resistor R18;
the REF end of the ADP509X power module is also connected with one end of a resistor R19, the other end of the resistor R19 is connected with the TERM end of the ADP509X power module, and the other end of the resistor R19 is also grounded through a resistor R20;
an SYS end of the ADP509X power supply module is connected with a power supply end of the MCU main control unit 1 to supply power to the MCU main control unit;
the ADP509X collection module is adopted to collect the electric energy of the solar cell panel S1 to charge the rechargeable battery, so that the charging efficiency can be improved, the service life of the rechargeable battery is prolonged, the ADP509X collection module has low power consumption, the field effect tube M1 is switched on when the current is large, the field effect tube M1 is switched off when the current is small, and trickle charging can be realized when the current is low due to the control effect of the field effect tube M1. The ADP509X power module is directly connected with the MCU main control unit 1 to supply power to the MCU main control unit.
The ADP509X collection module is connected with a super capacitor, and can supply power to the flame detector when the rechargeable battery is low in charge.
The power management unit 81 adopts an RC5T619 management module, the MCU main control unit 1 is provided with a power management end group, and the MCU main control unit 1 is connected with the RC5T619 management module through the power management end group; the anode of the rechargeable battery is connected with the anode of a diode D3 through a resistor R35, the cathode of a diode D3 is grounded through a capacitor C31, the cathode of the diode D3 is also connected with a VINP1 end of an RC5T619 management module, and a VINP1 end of the RC5T619 management module is also connected with a VINP2 end, a VINP3 end, a VINL1 end, a VINL2 end and a VINL3 end of the RC5T619 management module in parallel; the ground end AGND of the RC5T619 management module is grounded;
the positive electrode of the rechargeable battery is further connected with one end of a resistor R31, the other end of the resistor R31 is grounded through a resistor R32, the other end of the resistor R31 is further connected with the inverting input end of an integrated operational amplifier U3, the non-inverting input end of the integrated operational amplifier U3 is connected with the positive electrode of a super capacitor through a resistor R33, the non-inverting input end of the integrated operational amplifier U3 is further grounded through a resistor R34, the positive electrode of the super capacitor is further connected with the source electrode of a field-effect tube M3, the drain electrode of the field-effect tube M3 is connected with the VINP1 end of an RC5T619 management module, the output end of the integrated operational amplifier U3 is connected with the grid electrode of a field-effect tube M3, and the source electrode of the field-effect tube M36;
the RC5T619 management module is further connected with a first output power supply circuit, the RC5T619 management module supplies power to the ultraviolet acquisition circuit 3 through the first output power supply circuit, the first output power supply circuit comprises an inductor L31, one end of the inductor L31 is connected with the LX1 end of the RC5T619 management module, the other end of the inductor L31 is connected with one end of a resistor R37, the other end of the resistor R37 is connected with the FB1 end of the RC5T619 management module, and the other end of the resistor R37 is further connected with the GND1 end of the RC5T619 management module through the R38; the other end of the inductor L31 is also connected with the GND1 end of the RC5T619 management module through a capacitor C32, the capacitor C32 is connected with a capacitor C33 in parallel, and the other end of the inductor L31 is connected with the ultraviolet acquisition circuit 3 to supply power to the ultraviolet acquisition circuit;
the RC5T619 management module is also connected with a second output power supply circuit, the RC5T619 management module supplies power to the NB-IoT wireless communication unit 7 through the second output power supply circuit, and the second output power supply circuit and the first output power supply circuit are the same in structure;
the RC5T619 management module is also connected with a third output power supply circuit, the RC5T619 management module supplies power to the visible light image sensor 61 and the infrared image sensor array 62 through the third output power supply circuit, and the third output power supply circuit and the first output power supply circuit are identical in structure;
the LDOVOUT1 end of the RC5T619 management module is connected with the integrated infrared flame sensor 2 to supply power to the integrated infrared flame sensor; the LDOVOUT2 end of the RC5T619 management module is connected with the environmental parameter sensing unit 5 to supply power for the environmental parameter sensing unit; the terminal LDOVOUT3 of the RC5T619 management module is connected with the image recognition unit 6 to supply power to the image recognition unit.
The power management unit 81 adopts an RC5T619 management module, and the MCU main control unit 1 controls the RC5T619 management module to supply power to the integrated infrared flame sensor 2, the ultraviolet acquisition circuit 3, the environmental parameter sensing unit 5, the image recognition unit 6, the visible light image sensor 61, the infrared image sensor array 62 and the NB-IoT wireless communication unit 7 through the power management end group. The RC5T619 management module is convenient to control and low in power consumption.
By the control action of the integrated operational amplifier U3 and the field effect transistor M3, when the electricity quantity of the rechargeable battery is low, the super capacitor is adopted for supplying power.
The environment parameter sensing unit 5 comprises a temperature and humidity sensor 51 and an atmospheric illumination ultraviolet sensor 52, the temperature and humidity sensor 51 adopts an SI702X sensor, and the atmospheric illumination ultraviolet sensor 52 adopts an SI113X sensor. Both the sensors belong to mature modules, and the internal circuits of the sensors are omitted.
Through the structure setting, the temperature and humidity signals can be conveniently collected through the SI702X sensor, and the illuminance and ultraviolet intensity signals of the environment can be collected through the SI113X sensor.
The ultraviolet acquisition circuit 3 comprises an ultraviolet sensor circuit and an interference elimination circuit 31, and the ultraviolet sensor circuit is connected with the MCU main control unit 1 through the interference elimination circuit 31.
The ultraviolet sensor circuit is provided with a TPS65552A module, a Vcc end of the TPS65552A module is connected with a VBAT end of the TPS65552A module in parallel and then is connected with the power management unit 81, the Vcc end of the TPS65552A module is grounded through a capacitor C61, a PGND end of the TPS65552A module is grounded, and a CHG end of the TPS65552A module is connected with the Vcc end of the TPS65552A module through a resistor R64; the I-PEAK end of the TPS65552A module is connected with the Vcc end of the TPS65552A module through an upper voltage-dividing resistor R61, and the I-PEAK end of the TPS65552A module is grounded through a lower voltage-dividing resistor R62; the F-ON end of the TPS65552A module is connected with the Vcc end of the TPS65552A module through a resistor R63;
the XIFULL end of the TPS65552A module is grounded through a resistor R66, a resistor R67 and an adjustable resistor RSEL in sequence;
the SW end of the TPS65552A module is connected with one end of an input coil of a transformer TR1, the other end of the input coil of the transformer TR1 is connected with one end of a resistor R65, and the other end of the resistor R65 is grounded through a capacitor C62; one end of an output coil of the transformer TR1 is connected with the anode of a diode D61, the cathode of a diode D61 is connected with the anode of an electrolytic capacitor C63, and the cathode of the electrolytic capacitor C63 is connected with the other end of the output coil of the transformer TR1 in parallel and then grounded; the anode of the electrolytic capacitor C63 is also connected with one end of the ultraviolet flame sensor 4, and the other end of the ultraviolet flame sensor 4 is grounded through a resistor R70;
the anode of the electrolytic capacitor C63 is also connected with one end of a resistor R68, the other end of the resistor R68 is connected with one end of an input coil of a transformer TR2 through a capacitor C64, the other end of the input coil of the transformer TR2 is connected with one end of an output coil of a transformer TR2, and the other end of the output coil of the transformer TR2 is connected with the other end of the ultraviolet flame sensor 4;
the other end of the resistor R68 is also connected with a collector of a switch tube T61, an emitter of the switch tube T61 is grounded, a base of the switch tube T61 is connected with a G-IGBT end of a TPS65552A module, the other end of the ultraviolet flame sensor 4 is also connected with an anode of a diode D62, a cathode of a diode D62 is connected with the collector of the switch tube T61, the other end of the ultraviolet flame sensor 4 is also connected with one end of a capacitor C65, and the other end of the capacitor C65 is connected with a cathode of a diode D62 through a resistor R69;
the other end of the ultraviolet flame sensor 4 is also connected with a non-inverting input end of the integrated operational amplifier U8, the non-inverting input end of the integrated operational amplifier U8 is also grounded through a capacitor C66, the inverting input end of the integrated operational amplifier U8 is connected with the power management unit 81 through a resistor R71, the inverting input end of the integrated operational amplifier U8 is also grounded through a resistor R72, and the output end of the integrated operational amplifier U8 is connected with the interference elimination circuit 31;
the interference elimination circuit 31 comprises a CD4017 counter, the output end of the integrated operational amplifier U8 is connected with the CLOCK end of the CD4017 counter, the Q2 end of the CD4017 counter is connected with the base electrode of a switch tube T64, the collector electrode of the switch tube T64 is connected with the first ultraviolet acquisition end of the MCU main control unit 1, and the emitter electrode of the switch tube T64 is grounded;
the Q5 end of the CD4017 counter is connected with the base electrode of a switch tube T63, the collector electrode of the switch tube T63 is connected with the second ultraviolet acquisition end of the MCU main control unit 1, and the emitter electrode of the switch tube T63 is grounded; the Q5 terminal of the CD4017 counter is also connected to the CLOCK-IN terminal of the CD4017 counter.
The pulses generated by the ultraviolet flame sensor 4 were counted by a CD4017 counter.
Therefore, pulse signals generated by some low-frequency ultraviolet rays in the environment can be filtered according to the selection of the sensitivity, namely the number of pulses generated by the ultraviolet flame sensor 4.
The specific implementation mode is as follows: the singlechip collects the pulse output by the CD4017, actually, the ultraviolet flame sensor 4 sends three or six pulse flame signals, and the singlechip receives one pulse flame signal, so that the interference of an environmental light source can be effectively eliminated.
The control method of the flame detector with the infrared photographing function is characterized by comprising the following steps of,
step A1, the MCU main control unit 1 controls the integrated infrared flame sensor 2 to be electrified;
step A2, the MCU main control unit 1 enters a sleep state;
step A3, the MCU main control unit 1 acquires an interrupt signal of the integrated infrared flame sensor 2 for awakening;
a4, the MCU main control unit 1 acquires data Ch _ fire1[ i ] of a first flame infrared sensing unit of the integrated infrared flame sensor 2, data Ch _ fire2[ i ] of a second flame infrared sensing unit, data Ch _ interference [ i ] of a human body infrared sensing unit and data Ch _ background [ i ] of a background infrared reference sensing unit; i is the number of the collected signals, and i is 1-128;
step A5, the MCU main control unit 1 acquires illuminance information Light [ n ] through the environment parameter sensing unit 5, wherein n is the number of the acquired illuminance information, and n is 1-3;
step A6, the MCU main control unit 1 respectively performs Fourier transform on data Ch _ fire1[ i ] of the first flame infrared sensing unit and data Ch _ fire2[ i ] of the second flame infrared sensing unit to respectively obtain Fourier transform results FFt _ fire1 and FFt _ fire2, and respectively performs statistics on the Fourier transform results FFt _ fire1 and FFt _ fire2 by using a frequency domain distribution statistical function to respectively obtain statistical results Sta _ fire1 and Sta _ fire 2;
step A7, the MCU master control unit 1 judges whether the statistical results Sta _ fire1 and Sta _ fire2 have the basic frequency characteristics of the flame, if not, the step A2 is returned; if yes, go to step A8;
step A8, MCU master control unit 1 through Light illumination information Light [ n]Determining the threshold value y of the correlation coefficient of the infrared channel3；
Step A9, MCU Master Unit 1 obtains Ch _ fire1[ i]And Ch _ interference [ i ]]Correlation coefficient of (1) ("rho")1，Ch_fire1[i]And Ch _ background [ i ]]Correlation coefficient of (1) ("rho")2，Ch_fire2[i]And Ch _ interference [ i ]]Correlation coefficient of (1) ("rho")3，Ch_fire2[i]And Ch _ background [ i ]]Correlation coefficient of (1) ("rho")4；
Step A10, MCU main control unit 1 judges if correlation coefficient rho1Correlation coefficient rho2Correlation coefficient rho3Correlation coefficient rho4Is all less than the threshold value y of the infrared correlation coefficient3(ii) a The primary flame identification result is a flame signal, the primary flame identification result is uploaded through the NB-IoT wireless communication unit 7 or further flame ultraviolet identification is adopted, otherwise, the step a2 is returned.
The flame ultraviolet identification method comprises the following steps:
step B1, the MCU main control unit 1 obtains the ultraviolet intensity UV of the environment through the environment parameter sensing unit 5;
step B2, the MCU main control unit 1 determines an identification Threshold value UV _ Threshold of the flame ultraviolet sensor 4 according to the ultraviolet intensity UV;
step B3, the MCU main control unit 1 starts the flame ultraviolet sensor 4 to obtain the ultraviolet pulse frequency UV _ Count;
and step B4, the MCU main control unit 1 judges that the secondary flame confirmation result is a flame signal if the ultraviolet pulse frequency UV _ Count is higher than the identification Threshold UV _ Threshold, uploads the secondary flame confirmation result through the NB-IoT wireless communication unit 7 or further adopts image identification, and otherwise returns to the step A2.
The image recognition comprises the following steps:
step C1, the MCU main control unit 1 starts the image recognition unit 6 to collect visible light picture data VisablePic [ m ];
step C2, the MCU main control unit 1 converts the visible light picture data VisablePic [ m ] into a Gray map VisablePicy [ m ], performs convolution with a convolution kernel to obtain a convolved Gray map VisablePicv [ m ], finds a peak value of the convolved Gray map VisablePic _ Gray _ Conv [ m ], obtains picture data VisablePic _ Gray _ Peek after finding the peak value, and performs binarization to obtain a binarization result picture VisablePic _ Bool;
step C3, the MCU main control unit 1 performs morphological corrosion, filtering, expansion and reduction on the binarization result picture VisablePico _ Bool to obtain a filtering binarization picture VisablePico _ Bool _ Reduce;
step C4, the MCU main control unit 1 filters the filtered binary picture VisablePico _ Bool _ Reduce to obtain a suspected flame characteristic picture VisablePico _ Final;
step C5, the MCU main control unit 1 collects the infrared thermal imaging picture IrPic and the temperature value of each pixel of the infrared thermal imaging picture; carrying out binarization processing on the infrared thermal imaging picture IrPic to obtain a binarized infrared thermal imaging picture IrPic _ Bool;
step C6, the MCU main control unit 1 calculates the picture correlation coefficient Count _ Fire of the suspected flame characteristic picture VisablePinal and the binarized infrared thermal imaging picture IrPic _ Bool;
step C7, the MCU main control unit 1 judges that the picture correlation coefficient Count _ Fire is higher than the experience threshold value, and finally identifies the picture correlation coefficient Count _ Fire as a flame early warning signal, and the step C8 is entered; otherwise, returning to the step A2;
if there is no preceding stage infrared recognition or ultraviolet recognition, the step may return to step C1;
step C8, the MCU main control unit 1 uploads the fire warning information, the visible light picture data VisablePic [ m ] and the infrared thermal imaging picture IrPic to the cloud platform 9 through the NB-IoT communication module 7;
the fire early warning information comprises the serial number, the position and the like of the flame detector.
As shown in fig. 11, the control method of the cloud platform 9 includes the following steps:
step D1: the cloud platform 9 receives fire early warning information of the NB-IoT communication module 7;
step D2: the cloud platform 9 judges whether the fire warning information is received successfully or not, if so, the successful receiving information is issued to the NB-IoT communication module 7, and the step D3 is performed; otherwise, requesting NB-IoT communication module 7 to retransmit, returning to step D1;
step D3: the cloud platform 9 analyzes the fire early warning information;
step D4: the cloud platform 9 calls a short message gateway interface 91 to send a short message fire warning to the user terminal;
step D5: the cloud platform 9 positions and displays the early warning position on the GIS map;
step D6: the cloud platform 9 receives visible light picture data VisablePic [ m ] and an infrared thermal imaging picture IrPic sent by the NB-IoT communication module 7;
step D7: the cloud platform 9 determines whether the visible light picture data visablepac [ m ] and the infrared thermal imaging picture IrPic are successfully received, and if not, requests the NB-IoT communication module 7 to retransmit, and returns to step D6; if the message is successful, sending a receiving success message to the NB-IoT communication module 7, and entering step D8;
step D8: the cloud platform 9 analyzes the visible light picture data VisablePic [ m ] and the infrared thermal imaging picture IrPic;
step D9: the cloud platform 9 performs image synthesis operation on the visible light picture data VisablePic [ m ] and the infrared thermal imaging picture IrPic to obtain a synthesis operation image;
step D10: the cloud platform 9 pushes the synthetic operation image to the user terminal through the image pushing interface 92;
step D11: the cloud platform 9 uploads the synthetic operation image to a GIS map;
step D12: the cloud platform 9 waits for a warning command.
The short message gateway interface 91 and the image pushing interface 92 both belong to API interfaces, and are connected with a short message platform to push information and images to the user terminal.
Through the arrangement of the control method, the MCU main control unit 1 adopts the integrated infrared flame sensor 2 to collect various infrared signals for primary identification, secondary confirmation is carried out through flame ultraviolet signals collected by the ultraviolet flame sensor 4, and finally, visible light pictures are collected by the visible light image sensor 61 and the infrared image sensor array 62 to be combined with infrared thermal imaging pictures for final confirmation, so that the identification accuracy of flame is improved.
The first flame infrared sensing unit and the second flame infrared sensing unit are respectively used for collecting flame infrared signals with two different wavelengths, the human body infrared sensing unit is used for collecting human body infrared interference signals, namely interference infrared signals sent by human beings or animals, and the background infrared reference sensing unit is used for collecting infrared wavelength signals sent by a background environment; signals acquired by the first flame infrared sensing unit and the second flame infrared sensing unit are subjected to Fourier transform, if the signals are judged to have flame signal characteristics, correlation coefficients of the human body infrared sensing unit and the background infrared reference sensing unit are respectively obtained, and if the correlation coefficients are consistent with the flame characteristics, the signals are primarily identified as flame signals.
The ultraviolet flame sensor 4 is used for collecting an ultraviolet signal of flame and carrying out secondary confirmation by combining the ultraviolet signal of the environment parameter sensing unit 5.
Because the identification is easily influenced by the field illumination only by the visible light picture, the invention acquires the visible light picture and combines the infrared thermal imaging picture for processing, calculates the correlation coefficient and finally confirms.
The MCU main control unit 1 collects infrared data through the integrated infrared flame sensor 2, collects environmental data through the environmental parameter sensing unit 5 and identifies flame signals by adopting a cross-comparison algorithm:
the first flame infrared sensing unit, the second flame infrared sensing unit, the human body infrared sensing unit and the background infrared reference sensing unit respectively collect data and are used for reflecting waveform data of the infrared units in the period. The four infrared unit data are defined as follows, and respectively represent an array comprising 128 numerical values:
ch _ fire1[ i ] represents data collected by the first flame infrared sensing unit; ch _ fire2[ i ] represents data collected by the second flame infrared sensing unit; ch _ interference [ i ] represents data collected by the human body infrared sensing unit; ch _ background [ i ] represents data collected by the background infrared reference sensing unit; i is 1 to 128. When four infrared unit data are collected, illuminance data, namely illuminance information, are collected through the environmental parameter sensing unit 5, and an array containing n numerical values is obtained: light [ n ], n is 1-3.
Using Fourier transform function y1＝FFt(x1)(1)
The function is a common Fourier transform function, Ch _ fire1[ i]，Ch_fire2[i]As variable x1Inputting a Fourier transform function;
fourier-transformed result data FFt _ fire1 and FFt _ fire2 of two flame paths Ch _ fire1[ i ] and Ch _ fire2[ i ] are obtained. The Fourier transformed result data shows the distribution of the waveform of the infrared unit at different frequencies during data collection. FFt _ fire1 and FFt _ fire2 are frequency distributions of Ch _ fire1[ i ] and Ch _ fire2[ i ] at 0-20 Hz.
Using frequency domain distribution statistical functions
In the formula, the data FFt _ fire1 after Fourier transformation of the first flame infrared sensing unit and the data FFt _ fire2 after Fourier transformation of the second flame infrared sensing unit are input and respectively substituted for operation; sum () in the above formula is a summation function;
function counts input array x2In formula (2), the numerator calculates the sum of the distribution at 3-5 Hz, the denominator calculates the sum of the distribution of all frequencies, and then the ratio y of the former to the latter is returned2，y2The return value range of (1) to (0.0);
let FFt _ fire1 and FFt _ fire2 be x2Substitution of statistical functions of frequency domain distributionThe results of the function execution of FFt _ fire1 and FFt _ fire2 are found, resulting in the frequency domain distributions Sta _ fire1 and Sta _ fire 2. If the values of the two are less than the empirical parameter 0.5, the infrared trigger is judged to be interfered, and the recognition algorithm is stopped. If one of the parameters is greater than the empirical parameter of 0.5, the fundamental frequency characteristic of the flame is obtained.
Acquiring an infrared correlation coefficient threshold value by using an infrared correlation coefficient threshold value acquisition function;
in the formula, the illuminance data Light [ n ] collected by the environment parameter sensing unit (5) is input]Light [ n ]]As variable x3Substituting into a formula to carry out operation;
tanh () available y in the above formula (3)6It is shown that,
e is a natural base number;
the Average () function in the above formula (3) returns the Average value of the input array;
the Peak () function in the above formula returns the Peak-to-Peak value of the input array;
the formula is obtained by fitting actual experimental data;
mixing Light [ n ]]The final result y is obtained through the conversion of the formula3Namely, the infrared correlation coefficient threshold value is obtained. Light [ n ]]The range of each value of the array is (0-3000), the range of the result after Average () is (0-3000), the range of the result after Peak () is (0-3000), so the range of the result after Peak () is (0-3000)
The result range of (1) is (0-4). The function curve of Tanh () function is shown in the following figure, and the returned result value range is (0.0-1.0). In summary, the numerical range is (0.3-0.7).
The cross-correlation coefficient is used to obtain the function:
in the above formula (6), a (i) is any one of two sets of flame path data, and b (i) is any one of interference or background path data;
n in the formula is the length of an array, and the fixed value in the scheme is 128; 1-128 parts of i;
returning the Average value of the input array in the Average () in the formula;
using the above equation (6), the correlation coefficient between Ch _ fire1 and Ch _ interference is obtained as ρ1Let us denote the correlation coefficient between Ch _ fire1 and Ch _ background, which is expressed by ρ2The correlation coefficient between Ch _ fire2 and Ch _ interference is represented by ρ3Let us denote the correlation coefficient between Ch _ fire1 and Ch _ background, which is expressed by ρ4And (4) showing.
Correlation coefficient ρ1、ρ2、ρ3、ρ4All are smaller than the infrared correlation coefficient threshold; the primary recognition result is a flame; the algorithm identifies successfully.
The ultraviolet pulse number and environment ultraviolet intensity weighting algorithm comprises the following steps:
the MCU main control unit (1) collects the current environment ultraviolet intensity UV through the environment parameter sensing unit 5;
obtaining the pulse number UV _ Count output by the ultraviolet flame sensor 4 within 3 seconds through the ultraviolet acquisition circuit 3; UV _ Count is the ultraviolet pulse frequency;
UV _ Threshold is obtained using equation (7):
in the above formula (7), x7The value of the current environment ultraviolet intensity UV is (0-3000);
int () in the above formula is a rounding function, which is the value of the integer part of the parameter in parentheses;
using the above formula, the ultraviolet intensity UV is input to obtain the result y7Namely UV _ Threshold, which is the identification Threshold of the flame ultraviolet sensor 4. And if the UV _ Count is greater than the UV _ Threshold, the secondary identification result is a flame signal, and the flame condition is met.
Visible light picture flame feature extraction algorithm: the MCU main control unit 1 acquires a visible light picture every 200ms through the visible light image sensor 61 to obtain visible light picture data; the visible picture data is denoted VisablePic [ m ]; m is the number of the visible light picture data, and m is 1-5;
VisablePic [ m ] is a color picture; converting the Gray scale image into a Gray scale image VisablePic [ m ] by using a psychological formula;
psychological formula: gray ═ 0.3 xr +0.59 xg +0.11 xb; (8)
in the formula (8), R, G, B represents the channel values corresponding to the three colors of red, green and blue;
the same object is present in VisablePic _ Gray m]The 5 pictures in the image may have different positions, and the absolute positions in the pictures may have drift. Therefore, the Gray map VisablePaic _ Gray [ m ]]And convolution kernel
Convolution is carried out, drift is reduced, and a convolved Gray scale image VisablePhoto _ Gray _ Conv [ m ] is obtained]；
For a certain pixel point in VisablePic _ Gray _ Conv [ m ], the value obtained by subtracting the minimum value from the maximum value in 5 pictures is the peak-to-peak value corresponding to the pixel point. Solving the peak value of each point in VisablePic _ Gray _ Conv [ m ] to obtain picture data VisablePic _ Gray _ Peek after the peak value is solved;
obtaining a segmentation threshold value of VisablePic _ Gray _ Peek by using a maximum entropy threshold value method, and then binarizing the segmentation threshold value to obtain a binarization result picture VisablePic _ Bool;
maximum entropy threshold method: the pixel point value range in the picture is 0-255, and the probability distribution of the pixel points in the range of 0-255 is counted. For example, if the pixel point with the value of 125 appears 10 times in the picture, and there are 100 pixel points in total, the distribution on 125 is 10%;
definition of entropy in digital images:
H＝-Σp(g)×log(p(g)) (9)
the entropy is H in equation (9). p (g) represents the distribution over g, which is the value of the pixel. p (g) is the number of pixels with the value g; if the probability distribution of the pixel point with the value of 125 is 10%, p (125) ═ 10% ═ 0.1; log (p (g)) represents the log corresponding to the distribution, and is usually taken as the base 2.
An optimal partitioning point X is found, such that the entropy sum H1 of 0-X and the entropy sum H2 of X-255 have the maximum value of H1+ H2. Then the point X is the maximum threshold segmentation point.
By structural elements
Performing morphological corrosion on the VisablePico _ Bool for filtering, then performing morphological expansion and image restoration to obtain a filtering binary image VisablePico _ Bool _ Reduce;
checking a white area in the VisablePaic _ Bool _ Reducel image, checking the color distribution of the area in the VisablePac [ m ] of the original picture, filtering out areas which do not meet the flame color, and obtaining a Final suspected flame characteristic picture VisablePac _ Final;
the region with the pixel point value of 1 in visablepaic _ Final is the flame feature.
A flame characteristic and infrared thermal imaging picture superposition flame characteristic algorithm of the suspected flame characteristic picture:
obtaining an infrared thermal imaging picture IrPic through an infrared image sensor array (62), wherein each pixel in the IrPic stores a temperature value; the temperature is 300 degrees as the threshold value of the segmented image, and IrPic binarization processing is converted into a binarization infrared thermal imaging picture IrPic _ Bool;
performing AND operation on each corresponding pixel point of the VisablePinal and the IrPic _ Bool to obtain a FirePic picture; and operation (in symbol & expression): 1&1 ═ 1, 0&0 ═ 0, 1&0 ═ 0
Counting the total number of pixel points with the pixel value of 1 in the FirePic to obtain Count _ Fire; namely the picture correlation coefficient of the suspected flame characteristic picture and the binary infrared thermal imaging picture. A Count _ Fire greater than an empirical threshold identifies a flame. The empirical threshold may be 10% of the total number of pixels in a picture.
After receiving the fire alarm text information, the cloud platform 9 pushes a fire early warning notification to the user at the first time, calls the short message gateway interface 91, sends early warning information to the user terminal, positions the fire position area information on the GIS map according to the reported information, and executes early warning of the cloud platform 9. After the cloud platform 9 receives the image data, data analysis is performed according to a specific protocol, superposition operation of visible light images and infrared thermal imaging is performed, operation operations of marking flame shapes, flame sizes, flame zone temperatures, firing positions and the like on the visible light images are completed, the image pushing interface 92 is called, picture information is pushed to the client terminal, and meanwhile the position of the alarm detector is displayed in a GIS map of the cloud platform 9.
Finally, it is noted that: the above-mentioned embodiments are only examples of the present invention, and it is a matter of course that those skilled in the art can make modifications and variations to the present invention, and it is considered that the present invention is protected by the modifications and variations if they are within the scope of the claims of the present invention and their equivalents.
Claims (4)
1. The utility model provides a take flame detector of infrared shooting which characterized in that: the device comprises an MCU (microprogrammed control unit) (1), wherein the MCU (1) is also connected with an image recognition unit (6), and the image recognition unit (6) is connected with a visible light image sensor (61) and an infrared image sensor array (62); the visible light image sensor (61) is used for capturing a visible light picture of a fire scene, and the infrared image sensor array (62) is used for capturing an infrared thermal imaging picture of the fire scene and a temperature value of each pixel in the picture;
the MCU main control unit (1) is connected with an integrated infrared flame sensor (2), and the integrated infrared flame sensor (2) is integrated with a first flame infrared sensing unit, a second flame infrared sensing unit, a human body infrared sensing unit and a background infrared reference sensing unit; the MCU main control unit (1) is also connected with an ultraviolet flame sensor (4) through an ultraviolet acquisition circuit (3);
the MCU main control unit (1) acquires a visible light picture of the image recognition unit (6) and combines an infrared thermal imaging picture to carry out fire recognition;
the MCU main control unit (1) is also connected with an NB-IoT wireless communication unit (7) to send fire information;
the MCU master control unit is characterized by further comprising a light energy collecting unit (8), wherein the light energy collecting unit (8) directly supplies power to the MCU master control unit (1) after converting light energy into electric energy, and the light energy collecting unit (8) also supplies power to the image recognition unit (6), the visible light image sensor (61), the infrared image sensor array (62) and the NB-IoT wireless communication unit (7) through a power management unit (81); the MCU main control unit (1) controls the power supply of the power supply management unit (81);
the MCU main control unit (1) is an MSP430 singlechip;
the light energy collecting unit (8) comprises solar cell panels S1 and an ADP509X collecting module, the MCU main control unit (1) is provided with a power supply collecting end group, and the MSP430 single chip microcomputer is connected with the ADP509X collecting module through the power supply collecting end group;
a power supply end of the solar panel S1 is connected with one end of a resistor R1, the other end of the resistor R1 is grounded through a capacitor C1, and the other end of the resistor R1 is connected with a VIN end of an ADP509X collection module; the VIN end of the ADP509X collection module is connected with the SW end of the ADP509X collection module through an inductor L1; the ground end of the solar panel S1 is grounded;
the ground end of the ADP509X power module is grounded;
one end of the resistor R1 is further connected to the source of the field effect transistor M1, the drain of the field effect transistor M1 is connected to the other end of the resistor R1, one end of the resistor R1 is further connected to one end of the resistor R2, the other end of the resistor R2 is connected to the gate of the field effect transistor M1, the drain of the field effect transistor M1 is further connected to one end of the resistor R4, the other end of the resistor R4 is grounded through the resistor R5, the other end of the resistor R4 is connected to the non-inverting input terminal of the integrated operational amplifier U1, the non-inverting input terminal of the integrated operational amplifier U1 is further connected to one end of the resistor R3, the other end of the resistor R3 is connected to the gate of the field effect transistor M1, the other end of the resistor R3 is further connected to the output terminal of the integrated operational amplifier U1, the inverting input terminal of the integrated operational amplifier U1 is connected to the REG-OUT terminal of the collection module 6, the inverting input terminal of the integrated operational amplifier U6 is grounded through the REG-OUT terminal of the collection module;
the VIN end of the ADP509X collection module is also connected with one end of a resistor R8, and the other end of the resistor R8 is connected with the MPPT end of the ADP509X collection module; the other end of the resistor R8 is grounded through a resistor R9, the VID end of the ADP509X collection module is grounded through a resistor R10, the CBP end of the ADP509X collection module is grounded through a capacitor C2, and the MINOP end of the ADP509X collection module is grounded through a capacitor C3;
the BACK-UP end of the ADP509X collection module is connected with the anode of the super capacitor, and the cathode of the super capacitor is grounded; the BAT end of the ADP509X collection module is connected with the positive electrode of the rechargeable battery, and the negative electrode of the rechargeable battery is grounded;
the REG-OUT end of the ADP509X power module is also connected with one end of a resistor R11, the other end of the resistor R11 is connected with the REG-FB end of the ADP509X power module, and the other end of the resistor R11 is also grounded through a resistor R21;
the REF end of the ADP509X power module is connected with one end of a resistor R12, the other end of the resistor R12 is connected with the SETSD end of the ADP509X power module, and the other end of the resistor R12 is grounded through a resistor R13;
the REF end of the ADP509X power module is further connected with one end of a resistor R14, the other end of the resistor R14 is connected with the SETPG end of the ADP509X power module, the other end of the resistor R14 is further connected with one end of a resistor R15, the other end of the resistor R15 is connected with the SETHYST end of the ADP509X power module, and the other end of the resistor R15 is further grounded through a resistor R16;
the REF end of the ADP509X power module is also connected with one end of a resistor R17, the other end of the resistor R17 is connected with the SETBK end of the ADP509X power module, and the other end of the resistor R17 is also grounded through a resistor R18;
the REF end of the ADP509X power module is also connected with one end of a resistor R19, the other end of the resistor R19 is connected with the TERM end of the ADP509X power module, and the other end of the resistor R19 is also grounded through a resistor R20;
the SYS end of the ADP509X power supply module is connected with the power supply end of the MCU main control unit (1) to supply power to the MCU main control unit;
the power management unit (81) adopts an RC5T619 management module, the MCU main control unit (1) is provided with a power management end group, and the MCU main control unit (1) is connected with the RC5T619 management module through the power management end group; the anode of the rechargeable battery is connected with the anode of a diode D3 through a resistor R35, the cathode of a diode D3 is grounded through a capacitor C31, the cathode of the diode D3 is also connected with a VINP1 end of an RC5T619 management module, and a VINP1 end of the RC5T619 management module is also connected with a VINP2 end, a VINP3 end, a VINL1 end, a VINL2 end and a VINL3 end of the RC5T619 management module in parallel; the ground end AGND of the RC5T619 management module is grounded;
the positive electrode of the rechargeable battery is further connected with one end of a resistor R31, the other end of the resistor R31 is grounded through a resistor R32, the other end of the resistor R31 is further connected with the inverting input end of an integrated operational amplifier U3, the non-inverting input end of the integrated operational amplifier U3 is connected with the positive electrode of a super capacitor through a resistor R33, the non-inverting input end of the integrated operational amplifier U3 is further grounded through a resistor R34, the positive electrode of the super capacitor is further connected with the source electrode of a field-effect tube M3, the drain electrode of the field-effect tube M3 is connected with the VINP1 end of an RC5T619 management module, the output end of the integrated operational amplifier U3 is connected with the grid electrode of a field-effect tube M3, and the source electrode of the field-effect tube M36;
the RC5T619 management module is also connected with a second output power supply circuit, and the RC5T619 management module supplies power to the NB-IoT wireless communication unit (7) through the second output power supply circuit;
the RC5T619 management module is also connected with a third output power supply circuit, and the RC5T619 management module supplies power to the visible light image sensor (61) and the infrared image sensor array (62) through the third output power supply circuit;
the LDOVOUT3 terminal of the RC5T619 management module is connected with the image recognition unit (6) to supply power for the image recognition unit.
2. A control method of a flame detector with infrared photography, which is used for the flame detector with infrared photography as claimed in claim 1, is characterized by comprising the following steps,
step C1, the MCU main control unit (1) starts the image recognition unit (6) to collect visible light picture data VisablePic [ m ];
step C2, the MCU main control unit (1) converts the visible light picture data VisablePic [ m ] into a Gray image VisablePicy [ m ], performs convolution with a convolution kernel, and obtains a peak value of the convolved Gray image VisablePic _ Gray _ Conv [ m ], obtains the picture data VisablePic _ Gray _ Peek after obtaining the peak value, and performs binarization to obtain a binarization result picture VisablePic _ Bool;
the MCU main control unit (1) converts a Gray scale map VisablePicy m]And convolution kernel
Performing convolution;
obtaining a segmentation threshold value of VisablePic _ Gray _ Peek by using a maximum entropy threshold value method, and then binarizing the segmentation threshold value to obtain a binarization result picture VisablePic _ Bool;
step C3, the MCU master control unit (1) performs morphological corrosion, filtering, expansion and reduction on the binarization result picture VisablePal to obtain a filtering binary picture VisablePal _ Bool _ Reduce;
step C4, the MCU master control unit (1) filters the filtered binary picture VisablePico _ Bool _ Reduce to obtain a suspected flame characteristic picture VisablePico _ Final;
step C5, the MCU main control unit (1) collects an infrared thermal imaging picture IrPic and temperature values of each pixel of the infrared thermal imaging picture; carrying out binarization processing on the infrared thermal imaging picture IrPic to obtain a binarized infrared thermal imaging picture IrPic _ Bool;
step C6, the MCU main control unit (1) calculates the picture correlation coefficient Count _ Fire of the suspected flame characteristic picture VisablePinal and the binarized infrared thermal imaging picture IrPic _ Bool;
step C7, the MCU main control unit (1) judges that the picture correlation coefficient Count _ Fire is higher than the experience threshold value, and finally identifies the picture correlation coefficient Count _ Fire as a flame early warning signal, and the step C8 is entered; otherwise, returning to the step C1;
and step C8, uploading the fire early warning signal, the visible light picture data VisablePic [ m ] and the infrared thermal imaging picture IrPic through the NB-IoT communication module (7) by the MCU main control unit (1).
3. The method for controlling a flame detector with infrared photography according to claim 2, wherein in step C2; the MCU main control unit (1) converts the visible light picture data VisablePic [ m ] into a Gray scale picture VisablePic _ Gray [ m ] by using a psychological formula.
4. The method for controlling a flame detector with infrared photography according to claim 2, wherein in step C3; the MCU master control unit (1) uses the structural elements of the binarization result picture VisablePal
Morphological etching is carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810928780.4A CN108986379B (en) | 2018-08-15 | 2018-08-15 | Flame detector with infrared photographing function and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810928780.4A CN108986379B (en) | 2018-08-15 | 2018-08-15 | Flame detector with infrared photographing function and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108986379A CN108986379A (en) | 2018-12-11 |
| CN108986379B true CN108986379B (en) | 2020-09-08 |
Family
ID=64553615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810928780.4A Active CN108986379B (en) | 2018-08-15 | 2018-08-15 | Flame detector with infrared photographing function and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108986379B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112837495B (en) * | 2019-11-25 | 2023-07-04 | 宏力实业股份有限公司 | Flame detection method |
| CN111739249B (en) * | 2020-06-20 | 2023-08-11 | 深泽县联宇电子科技有限公司 | Fire monitoring method, device and system |
| CN112217979B (en) * | 2020-10-13 | 2022-01-25 | 重庆英卡电子有限公司 | Self-adaptive low-power-consumption wild animal snapshot device and method based on Internet of things |
| CN114022451A (en) * | 2021-11-05 | 2022-02-08 | 华能国际电力股份有限公司上海石洞口第二电厂 | Intelligent flame detection method based on image segmentation recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5237308A (en) * | 1991-02-18 | 1993-08-17 | Fujitsu Limited | Supervisory system using visible ray or infrared ray |
| JP3252742B2 (en) * | 1997-02-27 | 2002-02-04 | 三菱電機株式会社 | Fire detection system |
| EP2264677B1 (en) * | 2009-06-17 | 2012-05-30 | Teletron Euroricerche S.r.l. | Method for fire prevention and/or detection, and monitoring system and computer product thereof |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3269453B2 (en) * | 1998-04-08 | 2002-03-25 | 三菱電機株式会社 | Fire detection system |
| CN102044126A (en) * | 2009-10-22 | 2011-05-04 | 叶建华 | Optical fiber flame detector |
| CN201540627U (en) * | 2009-10-27 | 2010-08-04 | 西安盛赛尔电子有限公司 | Multi-parameter infrared flame detector |
| CN201867924U (en) * | 2010-11-15 | 2011-06-15 | 上海翼捷工业安防技术有限公司 | Three-wavelength infrared flame detector |
| CN102624071B (en) * | 2012-03-26 | 2013-11-27 | 重庆英卡电子有限公司 | Power supply device used for forest fire prevention detector |
| CN202865254U (en) * | 2012-08-20 | 2013-04-10 | 湖南镭目科技有限公司 | Converter flame temperature detection system |
| CN202758458U (en) * | 2012-08-27 | 2013-02-27 | 英森电气系统(上海)有限公司 | Bi wave band infra red flame detector |
| KR20120138715A (en) * | 2012-09-10 | 2012-12-26 | 김은종 | Multi-functional fire detector |
| CN105512667B (en) * | 2014-09-22 | 2019-01-15 | 中国石油化工股份有限公司 | Infrared and visible light video image fusion recognition fire method |
| CN106097630B (en) * | 2016-08-22 | 2018-01-30 | 重庆英卡电子有限公司 | A kind of flame identification method of double infrared channel flame detectors |
| CN106408836A (en) * | 2016-10-21 | 2017-02-15 | 上海斐讯数据通信技术有限公司 | Forest fire alarm terminal and system |
| CN107170173A (en) * | 2017-05-27 | 2017-09-15 | 重庆英卡电子有限公司 | Infrared and ultraviolet flame detector control system and its control method |
| CN107590941B (en) * | 2017-09-19 | 2019-08-20 | 重庆英卡电子有限公司 | Photo taking type mixed flame detector and its detection method |
| CN108010254A (en) * | 2017-11-28 | 2018-05-08 | 无锡职业技术学院 | One kind is based on four wave band infrared flame detectors and its flame identification algorithm |
| CN108010085B (en) * | 2017-11-30 | 2019-12-31 | 西南科技大学 | Target identification method based on binocular visible light camera and thermal infrared camera |
| CN207440954U (en) * | 2017-12-06 | 2018-06-01 | 中钛互联（北京）科技有限公司 | A kind of risk of forest fire management system based on NB-IOT |
-
2018
- 2018-08-15 CN CN201810928780.4A patent/CN108986379B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5237308A (en) * | 1991-02-18 | 1993-08-17 | Fujitsu Limited | Supervisory system using visible ray or infrared ray |
| JP3252742B2 (en) * | 1997-02-27 | 2002-02-04 | 三菱電機株式会社 | Fire detection system |
| EP2264677B1 (en) * | 2009-06-17 | 2012-05-30 | Teletron Euroricerche S.r.l. | Method for fire prevention and/or detection, and monitoring system and computer product thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108986379A (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108986379B (en) | Flame detector with infrared photographing function and control method thereof | |
| CN109060148B (en) | Flame detector and its control method | |
| CN104079874B (en) | A kind of security protection integral system and method based on technology of Internet of things | |
| CN107370955A (en) | Can be automatically switched web camera, implementation method and the monitoring system of diurnal pattern | |
| CN106372576A (en) | Deep learning-based intelligent indoor intrusion detection method and system | |
| CN104966375A (en) | Security monitoring system and monitoring method | |
| CN107592502B (en) | Wireless sensor network image monitoring system powered by solar energy | |
| CN108806165B (en) | Photographing type flame detection system and control method thereof | |
| CN105866118B (en) | A kind of animal excrements composition detection system and method | |
| CN108961647B (en) | Photographing type flame detector and control method thereof | |
| CN104185348B (en) | Intelligent substation is maked an inspection tour to illuminate and is far controlled linkage | |
| CN103916640A (en) | Intelligent home and shop monitoring system | |
| CN107526319A (en) | A kind of building safety defense monitoring system | |
| CN110174133A (en) | A kind of nature lightning discharge process monitoring system | |
| CN111950491A (en) | Personnel density monitoring method and device and computer readable storage medium | |
| CN109600758B (en) | RSS-based people flow monitoring method | |
| CN101931789A (en) | High-resolution human figure automatic recording and comparing system and method in key region | |
| CN110031041A (en) | A kind of nature lightning discharge sound, light, electricity, the more physical processes of magnetic monitor systems | |
| CN109257575A (en) | A kind of density of rodents monitoring method and monitoring system | |
| CN106292609A (en) | A kind of home security long distance control system based on Zigbee | |
| CN106205027A (en) | A kind of domestic safety prevention system based on GSM | |
| CN209488862U (en) | A kind of artificial intelligence energy conservation lamp control system based on computer vision | |
| CN107895365B (en) | Image matching method and monitoring system for power transmission channel external damage protection | |
| Khedkar | Wireless Intruder Detection System for Remote Locations | |
| CN112966552B (en) | Routine inspection method and system based on intelligent identification |
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 |