CN113160513A - Flame detection device based on multisensor - Google Patents
Flame detection device based on multisensor Download PDFInfo
- Publication number
- CN113160513A CN113160513A CN202110419871.7A CN202110419871A CN113160513A CN 113160513 A CN113160513 A CN 113160513A CN 202110419871 A CN202110419871 A CN 202110419871A CN 113160513 A CN113160513 A CN 113160513A
- Authority
- CN
- China
- Prior art keywords
- flame
- infrared
- thermal imaging
- flame detection
- target area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 116
- 238000001931 thermography Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 46
- 230000005855 radiation Effects 0.000 claims abstract description 25
- 230000008859 change Effects 0.000 claims description 40
- 239000013598 vector Substances 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 9
- 230000009977 dual effect Effects 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 239000000779 smoke Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000002238 attenuated effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000002360 explosive Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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 detection device based on multiple sensors, and belongs to the field of flame detection. In the device, a multiband infrared detection device detects infrared radiation data of different wavebands in a target area through a plurality of infrared sensors and sends the infrared radiation data to a first signal processing device in real time so as to judge whether flames exist in the target area and output a corresponding first flame detection signal; the infrared thermal imaging image acquisition device acquires an infrared thermal imaging image of a target area, and sends the infrared thermal imaging image to the second signal processing device in real time so as to analyze whether an area which accords with flame characteristics exists in the infrared thermal imaging image and output a corresponding second flame detection signal; the alarm output device can output a final flame detection signal after fusing the two judgment signals according to a preset alarm mode. The invention combines multiband flame detection and infrared thermal imaging image type flame detection, and really realizes the advantage complementation of two modes.
Description
Technical Field
The invention belongs to the field of flame detection, and particularly relates to a flame detection device based on multiple sensors.
Background
In recent years, fire disasters occur in industrial places such as oil and gas fields, gas stations, petrochemical plants, combustible warehouses, coal mines and the like, and great loss is caused to life and property safety of the nation and people. In these flammable and explosive places, once a fire breaks out, the fire spreads rapidly, and if the fire is not alarmed and extinguished in time, very serious consequences can be caused.
The traditional smoke-sensitive, temperature-sensitive and light-sensitive flame detectors respectively identify flames by using the characteristics of smoke, temperature and light of the flames, and have the advantages of simple manufacturing process and low price, so the traditional smoke-sensitive, temperature-sensitive and light-sensitive flame detectors are well applied to places such as hotels, trains, residential houses and the like, but the detection modes mostly adopt a concentration detection method and do not detect the characteristics of the flames, so the traditional smoke-sensitive, temperature-sensitive and light-sensitive flame detectors have the advantages of long response time, narrow detection range, high requirement on the surrounding environment, poor interference resistance and incapability of predicting certain conditions such as smokeless flames and the like. With the continuous development of machine vision technology, the flame detection technology utilizing the artificial neural network and the image recognition method makes certain progress, and has higher interference immunity capability and detection precision, but the basic theory research of early fire image detection is not sufficient, and the algorithm is complex, needs a very large training sample, and has low convergence rate and efficiency.
The flame detection technology based on the infrared pyroelectric principle utilizes an infrared pyroelectric sensor as a sensitive element to receive infrared information of flame combustion radiation and convert the infrared information into a voltage signal. In the early stage, a single-point infrared detector is internationally used for detecting flame in places which are inflammable and explosive, have large-range and large space and need rapid alarm. Because only infrared information of a single wave band is collected, a real flame signal is difficult to distinguish from false fire signals such as a high-temperature heat source, an artificial light source and the like, so that the false alarm rate is high, and in addition, the infrared ray is rapidly attenuated along with the increase of the distance in the air, so that the detection range is very limited. In recent years, multi-band infrared (MIR) flame detectors are successively and successfully developed and used for identifying flames in the countries such as the United states, Japan, Germany, Switzerland and the like, reference bands are introduced to eliminate false fire signals, so that the anti-interference capability is greatly improved, and a correlation analysis method among the bands is adopted to replace an energy threshold analysis method of a single-band detection technology, so that the problem of infrared attenuation along with distance is well solved. However, the infrared pyroelectric flame detectors in single band or multiband cannot solve the problem of detecting moving flame, such as the occurrence of fire due to local friction or failure of moving vehicles in a tunnel. It is therefore desirable to provide a method and apparatus that enables accurate detection of moving flames.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a flame detection device based on multiple sensors.
The invention adopts the following specific technical scheme:
a flame detection device based on multiple sensors comprises a multiband infrared detection device, an infrared thermal imaging image acquisition device, a first signal processing device, a second signal processing device and an alarm output device;
the multiband infrared detection device is used for detecting infrared radiation data of different wavebands in a target area through a plurality of infrared sensors, transmitting the infrared radiation data to the first signal processing device in real time, judging whether flame exists in the target area through the first signal processing device, and outputting a corresponding first flame detection signal;
the infrared thermal imaging image acquisition device is used for acquiring an infrared thermal imaging image of a target area, transmitting the infrared thermal imaging image to the second signal processing device in real time, analyzing whether an area which accords with flame characteristics exists in the infrared thermal imaging image or not by the second signal processing device, and outputting a corresponding second flame detection signal;
and the alarm output device is used for acquiring the first judgment signal and the second judgment signal, fusing the first judgment signal and the second judgment signal according to a preset alarm mode and outputting a final flame detection signal.
Preferably, the multiband infrared detection device is a tri-band infrared detection device.
Further, three detection wave bands of the three-band infrared detection device are respectively 3.8um, 4.3um and 5.2umRespectively used for identifying infrared radiation and CO of heat source2Radiation and background infrared radiation.
Preferably, a sensor capable of collecting 8-14 um continuous wave band infrared radiation is arranged in the infrared thermal imaging image collecting device.
Preferably, in the second signal processing device, first, whether a high temperature region corresponding to a flame temperature range exists in the infrared thermal imaging image of the target region is analyzed, if so, whether shape change, temperature change and shaking condition of the high temperature region correspond to flame characteristics is further analyzed, and if so, the flame in the target region is judged to exist.
Preferably, the specific method for determining whether or not the region corresponding to the flame characteristic exists in the second signal processing device is as follows:
s1, aiming at the infrared thermal imaging image of each frame of target area acquired in real time, identifying whether a high-temperature area higher than a flame temperature threshold exists or not, if so, extracting the high-temperature area and calculating the area size, the temperature average value, the HOG and the flicker intensity of the high-temperature area; the flicker intensity is the average value of the pixel values in the high-temperature area;
s2, if the high-temperature region exists in the infrared thermal imaging images of continuous multi-frame target regions in one period, performing feature extraction on all image frames in the high-temperature region in the current period to obtain an area change rate feature, a temperature change rate feature, an HOG feature and a flicker intensity change rate feature;
the area change rate characteristic is the mean value of the absolute change of the area of the adjacent image frames in the current period;
the temperature change rate is characterized by being the average value of the absolute change of the temperature average value of the adjacent image frames in the current period;
the HOG characteristic is the mean value of the HOG absolute variation of adjacent image frames in the current period;
the flicker intensity change rate is characterized by being the average value of the flicker intensity absolute change of the adjacent image frames in the current period;
and S3, forming the four features extracted in S2 into feature vectors, outputting a judgment result whether the current feature vectors accord with the flame features or not in a classifier which is trained in advance, judging whether flames exist in a target area and outputting an alarm signal if the current feature vectors accord with the flame features.
Further, the classifier is an SVM classifier.
Preferably, the first signal processing means and the second signal processing means are integrated in the same signal processing means.
Preferably, the preset alarm mode in the alarm output device comprises one or more of a multiband alarm mode, a thermal imaging alarm mode, an arbitrary alarm mode and a dual alarm mode;
in the multiband alarm mode, if the first flame detection signal judges that flame exists in a target area, the flame exists in the target area finally;
in the thermal imaging alarm mode, if the second flame detection signal judges that flame exists in the target area, the flame exists in the target area is finally judged;
in any alarm mode, if the first flame detection signal or the second flame detection signal judges that flame exists in the target area, the flame exists in the target area is finally judged;
in the dual alarm mode, if the first flame detection signal and the second flame detection signal both judge that flame exists in the target area, the flame exists in the target area is finally judged.
10. The multi-sensor based flame detection device of claim 1, wherein the alarm output device is in the form of one or more of sound, light, electricity, text, and image.
Compared with the prior art, the invention has the following beneficial effects:
1) the invention combines multiband flame detection and infrared thermal imaging image type flame detection, can find flame at earlier stage, and has high alarm speed and low false alarm rate.
2) The invention combines multiband flame detection and infrared thermal imaging image type flame detection, can detect moving flame, solves the problem that the traditional flame detector cannot detect the moving flame, and expands the application neighborhood of the flame detector.
3) The invention can set diversified alarm modes, can be configured according to different application scenes, and really realizes the complementation of the advantages of two types of detected flames.
Drawings
FIG. 1 is a schematic diagram of a multi-sensor based flame detection device according to an embodiment;
FIG. 2 is a schematic diagram of one embodiment of a method for determining whether an area corresponding to a flame signature exists;
FIG. 3 is a schematic view of another multi-sensor based flame detection device according to an embodiment.
Detailed Description
The invention will be further elucidated and described with reference to the drawings and the detailed description. The technical features of the embodiments of the present invention can be combined correspondingly without mutual conflict.
In a preferred embodiment of the present invention, as shown in fig. 1, a multi-sensor based flame detection device is provided, which can be divided into a multi-band infrared detection device, an infrared thermal imaging image acquisition device, a first signal processing device, a second signal processing device and an alarm output device according to functional division. The detailed connection mode and the function implementation of each part are explained in detail below.
The first detection induction part is a multiband infrared detection device and is used for detecting infrared radiation data of different wavebands in a target area through a plurality of infrared sensors and sending the infrared radiation data to the first signal processing device in real time. The multiband infrared detection device, namely the multiband infrared detector, belongs to the prior art, and the specific structure and form thereof are not described in detail. The multiband infrared detection device is provided with a plurality of sensors with different wave bands, and the purpose of eliminating interference can be achieved by comprehensively analyzing and comparing infrared radiation signals generated by the sensors.
In the prior art, the multiband infrared flame detection technology mainly adopts three bands, so the invention recommends a three-band infrared detection device which adopts three pyroelectric infrared sensors with different central wavelength narrowband filters to respectively detect different band information. In the invention, three detection wave bands of the three-wave-band infrared detection device are preferably set to be 3.8um, 4.3um and 5.2um, the pass band widths of the three-wave-band infrared detection device can be set to be +/-200 nm, and the three wave bands can be respectively used for identifying infrared radiation and CO of a heat source2Radiation and background infrared radiation. Different infrared radiation sources have unique spectral characteristics in the three bands, and the real flame signal and the false flame signal can be distinguished by comparing the mathematical relationship between the radiation intensities of the three bands.
The three-band infrared flame detection technology can well solve the problem that detection signals are attenuated along with the distance, even if the radiation signal intensities of the three bands are attenuated along with the increase of the distance, the mathematical relation between the radiation intensities of the three bands does not change along with the attenuation of the signals, and flame information submerged by noise due to the attenuation can be detected by adopting the mathematical correlation analysis technology, so that the detection distance and the detection sensitivity are improved to a great extent, and the false alarm rate is low. Of course, the present invention is not limited to the three-band infrared detection device, and other multi-band infrared detection devices may be adopted as long as the corresponding functions can be realized.
The multi-band infrared detection device is mainly used for detecting to obtain signals, the signals are processed by the first signal processing device, whether flames exist in a target area or not can be judged through a built-in flame judgment algorithm, and corresponding first flame detection signals are output. At present, technologies such as three-band infrared flame detection and the like have ready flame judgment algorithms, and the present invention is not limited to this and is not described in detail again, as long as the function can be realized. When the multiband detection signal is analyzed, the mathematical relation among the radiation intensities of all the wave bands is mainly analyzed, if the mathematical relation accords with the preset flame radiation characteristics, the flame exists in the current view field, and a flame alarm signal of the multiband detection device is output.
The multiband infrared detection device and the first signal processing device can be independent modules respectively, and can also adopt integrated equipment. When the integrated equipment is adopted, a finished product of a commercial multiband infrared flame detector can be adopted for replacement.
In addition, the second detection sensing part of the invention is an infrared thermal imaging image acquisition device, which is used for acquiring an infrared thermal imaging image of the target area and sending the infrared thermal imaging image to the second signal processing device in real time. Similarly, the infrared thermal imaging image acquisition device also belongs to the prior art, and the specific structure and form thereof are not described any more, as long as the infrared thermal imaging image (i.e. thermal image) can be acquired. Each pixel value in the infrared thermal imaging map reflects the temperature of a position, so that the temperature field distribution in the target area can be reflected by the infrared thermal imaging map. In the invention, the sensor in the infrared thermal imaging acquisition device is recommended to be a sensor capable of acquiring 8-14 um continuous wave band infrared radiation. The device is an image type flame detection device, and can acquire an infrared thermal imaging image under the current scene after processing an acquired image signal, wherein the image reflects the temperature and distribution condition of each position in the scene and is not influenced by light.
The above-mentioned infrared thermal imaging image acquisition device is mainly used for acquiring a thermal image signal, but the signal processing thereof needs to be performed by a second signal processing device. In the second signal processing device, whether an area which accords with the flame characteristics exists in the infrared thermal imaging image or not can be analyzed, and a corresponding second flame detection signal is output.
In the present invention, the processing flow in the second signal processing apparatus may adopt the following manner: firstly, whether a high-temperature area meeting the flame temperature range exists in an infrared thermal imaging image of a target area is analyzed, if yes, whether the shape change, the temperature change and the shaking condition of the high-temperature area meet the flame characteristics is further analyzed, and if yes, the flame in the current target area is judged.
It should be noted that, when the shape change, the temperature change and the jitter condition analysis of the high temperature region are performed, these several indexes are dynamic, so that the change analysis needs to be performed according to the continuous image frames in a period of time. A specific method for determining whether there is a region corresponding to the flame characteristic in the second signal processing device is given below with reference to fig. 2, and the steps are as follows:
and S1, aiming at the infrared thermal imaging image of each frame of target area acquired in real time, identifying whether a high-temperature area higher than the flame temperature threshold T exists, if so, extracting the high-temperature area and calculating the area size, the temperature average value, the HOG and the flicker intensity of the high-temperature area. And if the image does not exist, continuing to judge the next frame of image.
The flame temperature threshold T can be optimized and calibrated according to actual conditions, and different sensors can have different optimal values so as to accurately identify a real flame region.
In the invention, the area size of the high-temperature area can be determined by the number of the pixels of the high-temperature area. The average temperature value of the high-temperature area can adopt the average pixel value of all pixels in the high-temperature area. The HOG, i.e. the histogram of gradient directions, can be obtained by the calculation principle of HOG. The flicker intensity is defined as the mean value of the pixel values in the high temperature region.
The above step of S1 needs to be performed for each frame of ir thermographic image of the target area in order to observe the dynamic changes of the target area subsequently.
Generally, to facilitate implementation of the method, we can define a period, which is assumed to contain M consecutive infrared thermal imaging image frames. The specific value of M can be adjusted according to actual needs.
S2, if the high-temperature region exists in the infrared thermal imaging images of the continuous N frames of target regions in one period, it is indicated that the region may have a continuous high-temperature phenomenon and is most likely to belong to a flame region, so that feature extraction needs to be performed on all the N frames of image frames stored in the high-temperature region in the current period to obtain several flame features, specifically including an area change rate feature, a temperature change rate feature, an HOG feature and a flicker intensity change rate feature.
The value of N may be adjusted according to actual needs, for example, N is 30, N is 60, or N is 100.
The area change rate characteristic is the mean value of the absolute change of the area sizes of N-1 groups of adjacent image frames in the current period.
The temperature change rate is characterized by the mean value of the absolute change amounts of the temperature mean values of N-1 groups of adjacent image frames in the current period.
The HOG feature is the average of the aforementioned HOG absolute variation of N-1 sets of adjacent image frames in the current period.
The flicker intensity change rate is characterized by the mean value of the absolute change amounts of the flicker intensities of N-1 groups of adjacent image frames in the current period.
It should be noted that the above four features are the mean absolute variation of a certain parameter of adjacent image frames in the current period, and only N-1 groups of adjacent image frames in the period where the above high temperature region exists need to be calculated in the calculation. For example, when the area change rate characteristic is calculated, N image frames form N-1 groups of adjacent image frames pairwise, each group of adjacent image frames calculates the difference value deltaS of the area size of the high-temperature area, and the absolute value is taken to obtain the absolute value deltaS |; and then taking the average value of the N-1 deltaS | to obtain the area change rate characteristic.
In addition, it should be noted that the M image frames in the above one period are updated in real time, so as to reflect whether there is a flame in the current target area in real time, and implement real-time detection.
And S3, forming the four features extracted in S2 into feature vectors, outputting a judgment result whether the current feature vectors accord with the flame features or not in a classifier which is trained in advance, judging whether flames exist in a target area and outputting an alarm signal if the current feature vectors accord with the flame features.
It should be noted that the classifier can be any model capable of implementing label classification, and preferably a two-classifier, such as an SVM classifier, is used. The SVM classifier needs to be trained by using a large number of training data sets, and the trained classifier can be used for accurately judging whether the current feature vector accords with the flame feature.
In the execution process of S1 to S3, only when the classifier outputs the determination result that the current feature vector matches the flame feature, the determination result included in the second determination signal is regarded as having a real flame, but all the other cases (for example, there is no high temperature region in N consecutive image frames, the classifier determines that the current feature vector does not match the flame feature, and the like) are regarded as having no flame.
Finally, the detection signals of the multiband infrared detection device and the infrared thermal imaging image acquisition device output a judgment signal through the corresponding signal processing device respectively, and the judgment signal is a first judgment signal and a second judgment signal respectively. The two judgment signals respectively comprise a judgment result of whether flames exist in the target area or not, and the specific selection of which judgment result needs to be fused according to the alarm mode. The fusion process is realized by an alarm output device. That is to say, the alarm output device is used for acquiring the first judgment signal and the second judgment signal, fusing the first judgment signal and the second judgment signal according to a preset alarm mode, and outputting a final flame detection signal.
In the present invention, the preset alarm mode in the alarm output device can be set according to the actual situation, and is not limited. The first determination signal and the second determination signal may be used in combination of logical and, or the like. In a preferred embodiment of the present invention, the alarm modes may include one or more of a multiband alarm mode, a thermographic alarm mode, an arbitrary alarm mode, and a dual alarm mode, wherein each mode is implemented as follows:
in the multiband alarm mode, if the first flame detection signal judges that flame exists in the target area, the flame exists in the target area.
In the thermal imaging alarm mode, if the second flame detection signal judges that flame exists in the target area, the flame exists in the target area is finally judged.
In any alarm mode, if the first flame detection signal or the second flame detection signal judges that flame exists in the target area, the flame exists in the target area is finally judged.
In the dual alarm mode, if the first flame detection signal and the second flame detection signal both judge that flame exists in the target area, the flame exists in the target area is finally judged.
The four alarm modes can be configured according to practical application scenes, and the defect of a single alarm mode is avoided.
In addition, in order to send out alarm, the alarm output device can be provided with a corresponding alarm module, wherein the form of the sent alarm signal can be selected from one or more of sound, light, electricity, images and characters. These alarm signals may be sent directly at the machine end of the flame detection device or may be sent by an external terminal by sending signals to the external terminal. The external terminal comprises an audible and visual alarm, a mobile phone, a cloud platform, a server and the like, and has the main effects of attracting the attention of related personnel at the first time and hopefully dealing with the potential safety hazard in time to avoid dangerous accidents.
It should be noted that, in the multiband infrared detection device, the infrared thermal imaging image acquisition device, the first signal processing device, the second signal processing device and the alarm output device, the multiband infrared detection device and the infrared thermal imaging image acquisition device need to be installed on a monitoring site, and the arrangement positions of the first signal processing device, the second signal processing device and the alarm output device may be various. First signal processing device, second signal processing device and alarm output device can with multiband infrared detection device and infrared thermal imaging image acquisition device integration, all install on field device, also can set up alone on remote server or high in the clouds. For example, in the embodiment shown in fig. 3, the first signal processing device and the second signal processing device may be integrally designed and integrated in the same device, but the two signals are processed separately, so as to reduce the hardware requirement.
The flame detection device based on the multiple sensors can further improve the flame detection effect, and is mainly embodied in three aspects, namely, the flame detection device can detect the flame at an earlier stage and is a supplement to the multiband infrared sensor; secondly, for a large-area fire source, the device can be combined with a multiband infrared sensor to perform double confirmation, so that the false alarm rate is further reduced; and thirdly, the detection time is short, the moving flame can be detected, the flame detection device can be used for monitoring the flame of a moving target, and the application scene of the flame detection device is expanded.
The above-described embodiments are merely preferred embodiments of the present invention, which should not be construed as limiting the invention. Various changes and modifications may be made by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present invention. Therefore, the technical scheme obtained by adopting the mode of equivalent replacement or equivalent transformation is within the protection scope of the invention.
Claims (10)
1. A flame detection device based on multiple sensors is characterized by comprising a multiband infrared detection device, an infrared thermal imaging image acquisition device, a first signal processing device, a second signal processing device and an alarm output device;
the multiband infrared detection device is used for detecting infrared radiation data of different wavebands in a target area through a plurality of infrared sensors, transmitting the infrared radiation data to the first signal processing device in real time, judging whether flame exists in the target area through the first signal processing device, and outputting a corresponding first flame detection signal;
the infrared thermal imaging image acquisition device is used for acquiring an infrared thermal imaging image of a target area, transmitting the infrared thermal imaging image to the second signal processing device in real time, analyzing whether an area which accords with flame characteristics exists in the infrared thermal imaging image or not by the second signal processing device, and outputting a corresponding second flame detection signal;
and the alarm output device is used for acquiring the first judgment signal and the second judgment signal, fusing the first judgment signal and the second judgment signal according to a preset alarm mode and outputting a final flame detection signal.
2. The multi-sensor based flame detection device of claim 1, wherein the multi-band infrared detection device is a three-band infrared detection device.
3. The multi-sensor based flame detection device of claim 2, wherein the three detection bands of the three-band infrared detection device are respectively 3.8um, 4.3um and 5.2um for respectively identifying infrared radiation and CO of the heat source2Radiation and background infrared radiation.
4. The multi-sensor based flame detection device of claim 1, wherein a sensor capable of collecting 8-14 um continuous wave band infrared radiation is built in the infrared thermal imaging image collection device.
5. The multi-sensor based flame detection device of claim 1, wherein the second signal processing device first analyzes whether a high temperature region corresponding to a flame temperature range exists in the infrared thermal imaging image of the target region, further analyzes whether the shape change, the temperature change and the shaking condition of the high temperature region correspond to the flame characteristics if the high temperature region exists, and judges that flame exists in the target region if the high temperature region, the temperature change and the shaking condition correspond to the flame characteristics.
6. The multi-sensor based flame detection device of claim 1, wherein the specific method of determining whether there is a region conforming to the flame characteristics in the second signal processing device is as follows:
s1, aiming at the infrared thermal imaging image of each frame of target area acquired in real time, identifying whether a high-temperature area higher than a flame temperature threshold exists or not, if so, extracting the high-temperature area and calculating the area size, the temperature average value, the HOG and the flicker intensity of the high-temperature area; the flicker intensity is the average value of the pixel values in the high-temperature area;
s2, if the high-temperature region exists in the infrared thermal imaging images of continuous multi-frame target regions in one period, performing feature extraction on all image frames in the high-temperature region in the current period to obtain an area change rate feature, a temperature change rate feature, an HOG feature and a flicker intensity change rate feature;
the area change rate characteristic is the mean value of the absolute change of the area of the adjacent image frames in the current period;
the temperature change rate is characterized by being the average value of the absolute change of the temperature average value of the adjacent image frames in the current period;
the HOG characteristic is the mean value of the HOG absolute variation of adjacent image frames in the current period;
the flicker intensity change rate is characterized by being the average value of the flicker intensity absolute change of the adjacent image frames in the current period;
and S3, forming the four features extracted in S2 into feature vectors, outputting a judgment result whether the current feature vectors accord with the flame features or not in a classifier which is trained in advance, judging whether flames exist in a target area and outputting an alarm signal if the current feature vectors accord with the flame features.
7. The multi-sensor based flame detection device of claim 6, wherein the classifier is an SVM classifier.
8. The multi-sensor based flame detection device of claim 1, wherein the first signal processing device and the second signal processing device are integrated into a same signal processing device.
9. The multi-sensor based flame detection device of claim 1, wherein the preset alarm modes in the alarm output device include one or more of a multi-band alarm mode, a thermal imaging alarm mode, an arbitrary alarm mode, and a dual alarm mode;
in the multiband alarm mode, if the first flame detection signal judges that flame exists in a target area, the flame exists in the target area finally;
in the thermal imaging alarm mode, if the second flame detection signal judges that flame exists in the target area, the flame exists in the target area is finally judged;
in any alarm mode, if the first flame detection signal or the second flame detection signal judges that flame exists in the target area, the flame exists in the target area is finally judged;
in the dual alarm mode, if the first flame detection signal and the second flame detection signal both judge that flame exists in the target area, the flame exists in the target area is finally judged.
10. The multi-sensor based flame detection device of claim 1, wherein the alarm output device is in the form of one or more of sound, light, electricity, text, and image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419871.7A CN113160513A (en) | 2021-04-19 | 2021-04-19 | Flame detection device based on multisensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419871.7A CN113160513A (en) | 2021-04-19 | 2021-04-19 | Flame detection device based on multisensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113160513A true CN113160513A (en) | 2021-07-23 |
Family
ID=76868675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110419871.7A Pending CN113160513A (en) | 2021-04-19 | 2021-04-19 | Flame detection device based on multisensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113160513A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674502A (en) * | 2021-08-09 | 2021-11-19 | 上海腾盛智能安全科技股份有限公司 | Detection system based on infrared image recognition |
| CN114112074A (en) * | 2021-12-03 | 2022-03-01 | 无锡格林通安全装备有限公司 | Flame detector light path self-checking method and device and flame detector |
| CN115083103A (en) * | 2022-06-10 | 2022-09-20 | 西安中核核仪器股份有限公司 | Multi-band infrared pyroelectric flame detector based on deep learning and detection method |
| CN115364401A (en) * | 2022-08-15 | 2022-11-22 | 山东瑞美油气装备技术创新中心有限公司 | Method and device for extinguishing fire |
| EP4328554A1 (en) * | 2022-07-14 | 2024-02-28 | Honeywell International Inc. | Thermal camera and infrared sensor based flame detection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034329A (en) * | 2010-12-29 | 2011-04-27 | 上海大学 | Infrared fire detection method based on multiband and multi-feature |
| CN102708647A (en) * | 2012-06-25 | 2012-10-03 | 北京中恩时代科技有限责任公司 | Image and multi-band infrared-ultraviolet compound fire disaster detection system and method |
| CN203588412U (en) * | 2013-11-19 | 2014-05-07 | 上海安誉智能科技有限公司 | Triple-wave infrared and video image composite flame detector |
| CN105354974A (en) * | 2015-11-30 | 2016-02-24 | 无锡拓能自动化科技有限公司 | Flame detection method based on three-wavelength infrared flame detector |
| CN106203334A (en) * | 2016-07-11 | 2016-12-07 | 电子科技大学 | A kind of indoor scene flare detection method |
| CN111354152A (en) * | 2018-12-24 | 2020-06-30 | 北京华航无线电测量研究所 | Flame detecting and positioning system |
-
2021
- 2021-04-19 CN CN202110419871.7A patent/CN113160513A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034329A (en) * | 2010-12-29 | 2011-04-27 | 上海大学 | Infrared fire detection method based on multiband and multi-feature |
| CN102708647A (en) * | 2012-06-25 | 2012-10-03 | 北京中恩时代科技有限责任公司 | Image and multi-band infrared-ultraviolet compound fire disaster detection system and method |
| CN203588412U (en) * | 2013-11-19 | 2014-05-07 | 上海安誉智能科技有限公司 | Triple-wave infrared and video image composite flame detector |
| CN105354974A (en) * | 2015-11-30 | 2016-02-24 | 无锡拓能自动化科技有限公司 | Flame detection method based on three-wavelength infrared flame detector |
| CN106203334A (en) * | 2016-07-11 | 2016-12-07 | 电子科技大学 | A kind of indoor scene flare detection method |
| CN111354152A (en) * | 2018-12-24 | 2020-06-30 | 北京华航无线电测量研究所 | Flame detecting and positioning system |
Non-Patent Citations (2)
| Title |
|---|
| 蒋先刚: "《基于稀疏表达的火焰与烟雾探测方法研究》", 31 August 2017 * |
| 黄庆东: ""基于红外热成像的火灾检测算法研究"", 《中国优秀博硕士学位论文全文数据库(硕士).信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674502A (en) * | 2021-08-09 | 2021-11-19 | 上海腾盛智能安全科技股份有限公司 | Detection system based on infrared image recognition |
| CN114112074A (en) * | 2021-12-03 | 2022-03-01 | 无锡格林通安全装备有限公司 | Flame detector light path self-checking method and device and flame detector |
| CN114112074B (en) * | 2021-12-03 | 2023-11-03 | 无锡格林通安全装备有限公司 | Flame detector light path self-checking method and device and flame detector |
| CN115083103A (en) * | 2022-06-10 | 2022-09-20 | 西安中核核仪器股份有限公司 | Multi-band infrared pyroelectric flame detector based on deep learning and detection method |
| EP4328554A1 (en) * | 2022-07-14 | 2024-02-28 | Honeywell International Inc. | Thermal camera and infrared sensor based flame detection |
| CN115364401A (en) * | 2022-08-15 | 2022-11-22 | 山东瑞美油气装备技术创新中心有限公司 | Method and device for extinguishing fire |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113160513A (en) | Flame detection device based on multisensor | |
| CN104966372B (en) | The forest fire intelligent identifying system and method for multi-data fusion | |
| US11835676B2 (en) | Early-warning fire detection system based on a multivariable approach | |
| CN101577033A (en) | Multiband infrared image-type fire detecting system and fire alarm system thereof | |
| CN101334924B (en) | Fire hazard probe system and its fire hazard detection method | |
| US9250135B2 (en) | MWIR sensor for flame detection | |
| CN103337123B (en) | Based on the field joint stations fire alarm method of video image | |
| CN105336085A (en) | Remote large-space fire monitoring alarm method based on image processing technology | |
| CN108648400A (en) | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning | |
| Sousa et al. | Classification of potential fire outbreaks: A fuzzy modeling approach based on thermal images | |
| CN112542020A (en) | Infrared flame detection method and system based on dual-waveband | |
| CN202033865U (en) | Ultraviolet and infrared composite flame detector | |
| CN105354974A (en) | Flame detection method based on three-wavelength infrared flame detector | |
| KR20190130801A (en) | Combined fire alarm system using stand-alone fire alarm and visible light camera | |
| CN201091014Y (en) | Fire detecting device | |
| EP1233386B1 (en) | Improvements to fire detection sensors | |
| CN108010254A (en) | One kind is based on four wave band infrared flame detectors and its flame identification algorithm | |
| CN112263803A (en) | Unmanned vehicle intelligent security system based on real-time scene inspection and automatic detection fire extinguishing and control method | |
| CN108682105A (en) | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning | |
| US20110304728A1 (en) | Video-Enhanced Optical Detector | |
| CN201616160U (en) | Multi-waveband infrared image-type large-space fire detector | |
| CN110097732B (en) | Flame detection monitoring device and processing method thereof | |
| Yuanbin et al. | Fire detection based on image processing in coal mine | |
| CN111476971A (en) | Transmission line closely mountain fire monitoring devices | |
| CN203706339U (en) | Multi-parameter fire hazard detector |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |