CN109191765B - Fire alarm method, apparatus and computer readable storage medium - Google Patents
Fire alarm method, apparatus and computer readable storage medium Download PDFInfo
- Publication number
- CN109191765B CN109191765B CN201811484960.4A CN201811484960A CN109191765B CN 109191765 B CN109191765 B CN 109191765B CN 201811484960 A CN201811484960 A CN 201811484960A CN 109191765 B CN109191765 B CN 109191765B
- Authority
- CN
- China
- Prior art keywords
- value
- characteristic
- area
- alarm level
- fire
- 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 35
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 5
- 230000003247 decreasing effect Effects 0.000 claims description 5
- 230000005611 electricity Effects 0.000 abstract description 14
- 239000000779 smoke Substances 0.000 description 24
- 238000001931 thermography Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229910052732 germanium Inorganic materials 0.000 description 1
- GNPVGFCGXDBREM-UHFFFAOYSA-N germanium atom Chemical compound [Ge] GNPVGFCGXDBREM-UHFFFAOYSA-N 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fire-Detection Mechanisms (AREA)
- Fire Alarms (AREA)
Abstract
The present embodiments relate to intelligent security guard field, a kind of fire alarm method, apparatus and computer readable storage medium are disclosed.Fire alarm method includes: the characteristic image obtained for characterizing monitor area temperature, wherein monitor area includes with fiery electricity consumption region, with non-with fiery electricity consumption region except fiery electricity consumption region；Characteristic image is divided into and is used to characterize the non-fisrt feature image with fiery electricity consumption regional temperature, is used to characterize the second feature image with fiery electricity consumption regional temperature；It obtains in fisrt feature image for characterizing the non-background value with fiery electricity consumption regional temperature；Using the first preset duration as interval, the intermittent characteristic value obtained in second feature image for characterizing with fiery electricity consumption regional temperature；Alert level is obtained according to characteristic value and background value, when alert level is greater than default alert level, sends warning message.Fire alarm method, apparatus provided by the invention and computer readable storage medium being capable of early warning in time, at low cost and be suitable for any scene.
Description
Technical Field
The embodiment of the invention relates to the field of intelligent security and protection, in particular to a fire early warning method and device and a computer readable storage medium.
Background
Indoor fires can cause significant loss of people and property, especially in densely populated areas, where the loss of fire is more pronounced due to fire or improper electricity usage. Although warehouses and storage areas are usually provided with fire alarm systems and fire protection systems, the systems only start to work after a fire is triggered, and the fire protection policy of China is 'prevention-oriented and fire protection-combined' to combine fire prevention and fire suppression, and in the fire protection work, fire prevention is put at the head to try to prevent the fire. According to the characteristic that the temperature of an indoor fire changes along with time, the initial stage of the fire generally means within 15 minutes of the initial stage of the fire, and the stage is characterized in that the local temperature at the ignition point is high, the burning area is not large, the burning development is mostly slow, and the fire possibly forms and can be automatically extinguished midway. Therefore, the fire disaster early-stage early-warning device can timely find and early-warn in the fire disaster development early stage, and can provide precious time for timely controlling the fire disaster. The initial stage of a fire is characterized by a local temperature rise and a slow development. The fire point is detected before the fire disaster happens, and related personnel can take necessary measures in time conveniently. The fire early warning method in the prior art has three types: the first is a smoke detector or smoke detector, namely the smoke detector or smoke detector realizes fire alarm by monitoring the change of smoke concentration, the working principle is that the infrared beam of the infrared emission tube is scattered by smoke particles, when smoke exists in the environment, the smoke particles enter a cavity similar to a labyrinth of the detector to scatter the infrared light emitted by the emission tube, the intensity of the scattered infrared light has a certain linear relation with the smoke concentration (the intensity of scattered light is in direct proportion to the smoke concentration), so the intensity of the infrared beam received by the photosensitive tube can be changed and converted into an electric signal, and finally the electric signal is converted into an alarm signal; the second is an infrared thermal imaging camera solution, since the amount of thermal radiation energy of an object is directly related to the temperature of the object surface, this property of thermal radiation allows one to use this physical property for contactless temperature measurement of the object. Infrared thermal imaging uses an infrared photoelectric sensor to detect an optical signal with infrared specific wavelength of object thermal radiation, converts the signal into a thermal distribution image for visual resolution, and can further calculate a temperature value; the third is the detection of smoke by computer vision, which is now used successfully in the fields of industrial automation, face detection and recognition, and thus there are attempts to detect smoke and fire by computer vision. Usually, computer vision technology extracts appearance features such as shape and color of a detected object under a clearly visible condition.
The inventor finds that at least the following problems exist in the prior art: in the scheme of using the smoke concentration after fire as an alarm condition, as no smoke with enough concentration is generated at the initial stage of fire occurrence, early warning cannot be timely carried out; in the scheme of utilizing the infrared thermal imaging camera, the infrared thermal imaging array of the core device of the thermal imaging camera has high cost of the whole machine due to high cost of manufacturing materials and complex manufacturing process, and the service life of the thermal imaging camera is relatively shorter compared with that of a monitoring camera; in the scheme of using a computer to visually detect smoke, the shape and the color of the smoke are difficult to accurately extract due to the imaging characteristics of the smoke, so that the detection of the smoke is always difficult in the field, and the smoke is difficult to detect when a fire occurs at night or under the condition of non-ideal light conditions, and in addition, the problem that objects on fire cannot be shielded needs to be considered. Similarly, flame detection is technically difficult, so that the method is limited by technical conditions, and the scheme for detecting smoke by using the computer vision technology has high requirements on the conditions of the surrounding environment and limited applicable scenes.
Disclosure of Invention
An object of embodiments of the present invention is to provide a fire early warning method, a fire early warning device, and a computer-readable storage medium, which can early warn in time, and have low cost and wide application range.
In order to solve the above technical problem, an embodiment of the present invention provides a fire early warning method, including:
acquiring a characteristic image for representing the temperature of a monitoring area, wherein the monitoring area comprises a fire power utilization area and a non-fire power utilization area outside the fire power utilization area; dividing the characteristic image into a first characteristic image for representing the temperature of the non-powered area and a second characteristic image for representing the temperature of the powered area; acquiring a background value used for representing the temperature of the non-fire electricity utilization area in the first characteristic image; intermittently acquiring a characteristic value used for representing the temperature of the fire power utilization area in the second characteristic image by taking a first preset time length as an interval; and acquiring the alarm level of the fire power utilization area according to the characteristic value and the background value, and sending alarm information when the alarm level is greater than a preset alarm level.
The embodiment of the present invention also provides a fire early warning device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the fire early warning method described above.
Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which when executed by a processor implements the fire early warning method described above.
Compared with the prior art, the embodiment of the invention acquires the characteristic image for representing the temperature of the monitoring area, divides the characteristic image into the first characteristic image for representing the temperature of the non-power-consumption area and the second characteristic image for representing the temperature of the power-consumption area, so that the temperatures of the power-consumption area and the non-power-consumption area in the monitoring area can be known according to the characteristic image, acquires the background value for representing the temperature of the non-power-consumption area in the first characteristic image, intermittently acquires the characteristic value for representing the temperature of the power-consumption area in the second characteristic image at intervals of a first preset time length, thereby being capable of mastering the change condition of the temperature of the power-consumption area in real time, and finally acquires the alarm level of the power-consumption area according to the characteristic value and the background value, and when the alarm level is greater than a preset alarm level, sending alarm information. Since only the temperature in the electric fire area changes (gradually increases) at the initial stage of fire occurrence, but the temperature in the electric fire area does not basically remain unchanged, the alarm level obtained through the background value and the characteristic value changes as long as the temperature in the electric fire area changes (namely the characteristic value changes), and when the alarm level is greater than the preset alarm level, alarm information is immediately sent, so that early warning is timely, and the situation that the early warning cannot be timely realized because smoke with sufficient concentration is not generated at the initial stage of fire occurrence is effectively avoided; meanwhile, an infrared thermal imaging camera with higher cost does not need to be used, and a security monitoring camera with low cost and high reliability can be used, so that the cost of the fire early warning method is reduced; in addition, the color and the shape of the smoke do not need to be extracted through a computer vision technology, the method is not limited by any technology, and the application scene is wide.
In addition, the obtaining of the background value used for characterizing the temperature of the non-live fire electricity utilization region in the first characteristic image specifically includes: acquiring N first pixel values of the first characteristic image, wherein N is an integer greater than 1; and calculating a first average value of the N first pixel values, and taking the first average value as the background value. This approach provides a specific solution for obtaining a background value that is indicative of the temperature of the non-live zone.
In addition, the intermittently obtaining the characteristic value used for representing the temperature of the fire power utilization area in the second characteristic image by taking the first preset time period as an interval specifically comprises: intermittently acquiring M second pixel values of the second characteristic image by taking the first preset time length as an interval, wherein M is an integer greater than 1; subtracting the first average value from the M second pixel values respectively to obtain M intermediate values; and calculating a second average value of the M intermediate values, and taking the second average value as the characteristic value. This provides a specific solution for obtaining a characteristic value for characterizing the temperature of the live zone.
In addition, the acquiring of the alarm level of the fire power utilization area according to the characteristic value and the background value and the sending of alarm information when the alarm level is greater than a preset alarm level specifically include: and judging whether the characteristic value is greater than the background value, increasing the alarm level when judging that the characteristic value is greater than the background value, and sending alarm information until the alarm level is greater than a preset alarm level in a second preset time length, wherein the second preset time length is greater than or equal to the first preset time length and is an integral multiple of the first preset time length.
In addition, the acquiring of the alarm level of the fire power utilization area according to the characteristic value and the background value and the sending of alarm information when the alarm level is greater than a preset alarm level specifically include: judging whether the characteristic value is greater than the background value, increasing the alarm level when judging that the characteristic value is greater than the background value, reducing the alarm level when judging that the characteristic value is less than the background value, and sending alarm information until the alarm level is greater than the preset alarm level in a second preset time period, wherein the second preset time period is greater than or equal to the first preset time period and is an integral multiple of the first preset time period. Due to the fact that other factors (such as sunlight irradiation and the like) can also cause the characteristic value to be larger than the background value at a certain moment, the alarm level is increased when the characteristic value is judged to be larger than the background value, and the alarm level is reduced when the characteristic value is judged to be smaller than the background value, so that misjudgment on whether a fire disaster happens or not is effectively avoided, and the accuracy of fire early warning is improved.
In addition, the determining whether the feature value is greater than the background value, increasing the alarm level when determining that the feature value is greater than the background value, and decreasing the alarm level when determining that the feature value is less than the background value specifically includes: and judging whether the characteristic value is greater than the background value, adding 1 to the alarm level when judging that the characteristic value is greater than the background value, and subtracting 1 from the alarm level when judging that the characteristic value is less than the background value.
In addition, the acquiring of the characteristic image for characterizing the temperature of the monitoring area specifically includes: and acquiring an image of the monitoring area in a near infrared band, and taking the image in the near infrared band as the characteristic image.
In addition, the dividing the characteristic image into a first characteristic image for representing the temperature of the non-powered electrical region and a second characteristic image for representing the temperature of the powered electrical region specifically includes: setting a target area as an area to be measured in coordinates in the characteristic image; acquiring the image coordinates of the area to be measured in coordinates; calculating a circumscribed circle of the image coordinate according to the image coordinate; and taking the area where the circumscribed circle is located as the fire power utilization area, taking the area outside the circumscribed circle as the non-fire power utilization area, taking the image corresponding to the non-fire power utilization area as the first characteristic image, and taking the image corresponding to the fire power utilization area as the second characteristic image.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
Fig. 1 is a flowchart of a fire early warning method according to a first embodiment of the present invention;
fig. 2 is a schematic diagram of an ideal filter segment according to a first embodiment of the present invention;
FIG. 3 is a schematic view of a camera and alarm system apparatus according to a first embodiment of the present invention;
fig. 4 is a flowchart of a fire early warning method according to a second embodiment of the present invention;
fig. 5 is a schematic structural view of a fire early warning apparatus according to a third embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present invention in its various embodiments. However, the technical solution claimed in the present invention can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the present invention relates to a fire early warning method, and the specific flow is shown in fig. 1, and includes:
s101: a characteristic image is acquired that is characteristic of the temperature of the monitored area.
In step S101, specifically, the monitoring area includes a fire power utilization area and a non-fire power utilization area outside the fire power utilization area, and the obtaining of the characteristic image for representing the temperature of the monitoring area may be: and acquiring an image of the monitoring area in a near infrared band, and taking the image in the near infrared band as the characteristic image. It is understood that the near infrared band is an electromagnetic wavelength range between the visible light band and the mid infrared band, and belongs to a band invisible to human eyes, and the temperature condition of the monitored area can be known by observing the image of the near infrared band of the monitored area. It should be noted that the sensor used in the camera in this embodiment is a Complementary Metal Oxide Semiconductor (CMOS) sensor, which belongs to a photoelectric imaging device manufactured by using semiconductor materials silicon Si and germanium Ge, and the infrared signal collection capability can be improved by using two characteristics of the sensor, namely, high dynamics and high signal-to-noise ratio.
It is worth mentioning that, for the clear near-infrared signal of better collection, can add infrared filter in the front of the camera in this embodiment, through carrying out the coating film or increasing the filter at the detector front end to optical lens, filter the partial photon of visible light, strengthened the ability of collecting near-infrared photon in other words. The key parameter of the filter is called cut-off wavelength, the cut-off wavelength is used as a specific wavelength threshold value, energy with the wavelength smaller than the cut-off wavelength is rejected to pass, energy with the wavelength larger than the cut-off wavelength is allowed to pass, and the filter is a filter with the selected wavelength. The schematic diagram of the ideal filter is shown in fig. 2, and the cutoff wavelength of the infrared filter is designed in the band range of 700 and 800 nm (i.e. 0.7-0.8 μm).
Specifically, the schematic diagram of the camera and the alarm system device is shown in fig. 3: the camera is fixed above the monitoring area to ensure clear visual field. The camera is connected with the computer through a data cable. The video captured by the camera is further processed as input by an image processing program. The output part of the computer is connected with an automatic alarm system, and the automatic alarm system informs related workers through a network.
S102: the characteristic image is divided into a first characteristic image used for representing the temperature of the non-live electric region and a second characteristic image used for representing the temperature of the live electric region.
In step S102, specifically, the dividing the characteristic image into a first characteristic image for representing the temperature of the non-utility power region and a second characteristic image for representing the temperature of the utility power region may be: setting a target area as an area to be measured in coordinates in the characteristic image; acquiring the image coordinates of the area to be measured in coordinates; calculating a circumscribed circle of the image coordinate according to the image coordinate; and taking the area where the circumscribed circle is located as the fire power utilization area, taking the area outside the circumscribed circle as the non-fire power utilization area, taking the image corresponding to the non-fire power utilization area as the first characteristic image, and taking the image corresponding to the fire power utilization area as the second characteristic image. It can be understood that, after the camera captures the feature image of the monitored area, the area to be measured in coordinates can be manually selected from the feature image, so as to obtain the area using fire.
S103: and acquiring a background value used for representing the temperature of the non-live electric region in the first characteristic image.
In step S103, specifically, the obtaining of the background value in the first characteristic image for characterizing the temperature of the non-live fire electricity utilization region may be: acquiring N first pixel values of the first characteristic image, wherein N is an integer greater than 1; and calculating a first average value of the N first pixel values, and taking the first average value as the background value.
S104: and intermittently acquiring a characteristic value used for representing the temperature of the fire electricity utilization area in the second characteristic image by taking the first preset time length as an interval.
In step S104, specifically, M second pixel values of the second feature image are intermittently obtained at intervals of the first preset time duration, where M is an integer greater than 1; subtracting the first average value from the M second pixel values respectively to obtain M intermediate values; and calculating a second average value of the M intermediate values, and taking the second average value as the characteristic value.
S105: and judging whether the characteristic value is greater than the background value, increasing the alarm level when the characteristic value is greater than the background value, and sending alarm information until the alarm level is greater than the preset alarm level within a second preset time.
In step S105, specifically, if the first preset time period is 15 seconds, the second preset time period is 3 minutes, and the preset alarm level is 10, the alarm level is increased to 12 and 10 if the feature value is always greater than the background value within 3 minutes, and then alarm information is generated.
Compared with the prior art, the embodiment of the invention acquires the characteristic image for representing the temperature of the monitoring area, divides the characteristic image into the first characteristic image for representing the temperature of the non-power-consumption area and the second characteristic image for representing the temperature of the power-consumption area, so that the temperatures of the power-consumption area and the non-power-consumption area in the monitoring area can be known according to the characteristic image, acquires the background value for representing the temperature of the non-power-consumption area in the first characteristic image, intermittently acquires the characteristic value for representing the temperature of the power-consumption area in the second characteristic image at intervals of a first preset time length, thereby being capable of mastering the change condition of the temperature of the power-consumption area in real time, and finally acquires the alarm level of the power-consumption area according to the characteristic value and the background value, and when the alarm level is greater than a preset alarm level, sending alarm information. Since only the temperature in the electric fire area changes (gradually increases) at the initial stage of fire occurrence, but the temperature in the electric fire area does not basically remain unchanged, the alarm level obtained through the background value and the characteristic value changes as long as the temperature in the electric fire area changes (namely the characteristic value changes), and when the alarm level is greater than the preset alarm level, alarm information is immediately sent, so that early warning is timely, and the situation that the early warning cannot be timely realized because smoke with sufficient concentration is not generated at the initial stage of fire occurrence is effectively avoided; meanwhile, an infrared thermal imaging camera with higher cost does not need to be used, and a security monitoring camera with low cost and high reliability can be used, so that the cost of the fire early warning method is reduced; in addition, the color and the shape of the smoke do not need to be extracted through a computer vision technology, the method is not limited by any technology, and the method is suitable for any scene.
A second embodiment of the present invention is a fire alarm method, and the second embodiment is substantially the same as the first embodiment, and is mainly different in that in the first embodiment, the acquiring an alarm level of the fire electricity utilization area based on the characteristic value and the background value, and transmitting alarm information when the alarm level is greater than a preset alarm level, specifically includes: and judging whether the characteristic value is greater than the background value, increasing the alarm level when judging that the characteristic value is greater than the background value, and sending alarm information until the alarm level is greater than a preset alarm level in a second preset time length, wherein the second preset time length is greater than or equal to the first preset time length and is an integral multiple of the first preset time length. In a second embodiment, the acquiring an alarm level of the fire power utilization area according to the characteristic value and the background value, and sending alarm information when the alarm level is greater than a preset alarm level specifically includes: judging whether the characteristic value is greater than the background value, increasing the alarm level when judging that the characteristic value is greater than the background value, reducing the alarm level when judging that the characteristic value is less than the background value, and sending alarm information until the alarm level is greater than the preset alarm level in a second preset time period, wherein the second preset time period is greater than or equal to the first preset time period and is an integral multiple of the first preset time period. Due to the fact that other factors (such as sunlight irradiation and the like) can also cause the characteristic value to be larger than the background value at a certain moment, the alarm level is increased when the characteristic value is judged to be larger than the background value, and the alarm level is reduced when the characteristic value is judged to be smaller than the background value, so that misjudgment on whether a fire disaster happens or not is effectively avoided, and the accuracy of fire early warning is improved.
As shown in fig. 4, a specific flow of the present embodiment includes:
s201: a characteristic image is acquired that is characteristic of the temperature of the monitored area.
S202: the characteristic image is divided into a first characteristic image used for representing the temperature of the non-live electric region and a second characteristic image used for representing the temperature of the live electric region.
S203: and acquiring a background value used for representing the temperature of the non-live electric region in the first characteristic image.
S204: and intermittently acquiring a characteristic value used for representing the temperature of the fire electricity utilization area in the second characteristic image by taking the first preset time length as an interval.
Steps S201 to S204 in this embodiment are similar to steps S101 to S104 in the first embodiment, and are not repeated here to avoid repetition.
S205: and judging whether the characteristic value is greater than the background value, increasing the alarm level when the characteristic value is greater than the background value, reducing the alarm level when the characteristic value is less than the background value, and sending alarm information until the alarm level is greater than the preset alarm level within a second preset time.
Specifically, in step S205, in this embodiment, when the feature value is determined to be greater than the background value, the alarm level is increased, and when the feature value is determined to be less than the background value, the alarm level is decreased by: and when the characteristic value is judged to be larger than the background value, adding 1 to the alarm level, and when the characteristic value is judged to be smaller than the background value, subtracting 1 from the alarm level. It can be understood that the interference of external conditions except for the occurrence of a fire may also cause an increase in the characteristic value, and when it is determined that the characteristic value is smaller than the background value, the alarm level is decreased by 1, so that the alarm level is not increased all the time within a certain time period due to other reasons (non-fire), which may cause an erroneous determination of the alarm system, thereby improving the accuracy of fire early warning. It will be appreciated by those skilled in the art that the present embodiment can achieve the same technical effects as the foregoing embodiment.
For convenience of understanding, the following specifically describes the processing flow of the feature image in the present embodiment:
1. in a focus monitoring area, such as a fire-using electric area such as a heating table or a cooking bench, a local area is set in the image as an area of interest. The setting method is that the image coordinate of the area is obtained and stored, the circumcircle of the group of coordinates is calculated to obtain the center coordinate (Xc, Yc) and the radius distance r of the circle, and the circumcircle is set as the ROI (region of interest);
2. and obtaining an image captured by the infrared filter camera. Calculating the average value of pixel values outside the ROI area as a background value background;
3. calculating each pixel value in the ROI area minus background, and storing as ROI _ cut _ bg;
4. and (3) taking the average value ROI _ avg of the ROI _ cut _ bg, collecting the ROI _ avg at intervals of a fixed time interval t, and sequentially saving the ROI _ avg _1, the ROI _ avg _2 and the ROI _ avg _3 … … ROI _ avg _ n.
5. And when the ROI _ avg _ i is smaller than the ROI _ avg _ fire _ alarm, the alarm level alarm _ degree is decreased by 1. When the alarm _ degree exceeds the threshold value, the fire is considered to be detected, and staff are informed to process through an alarm system.
A third embodiment of the present invention relates to a fire early warning device, as shown in fig. 5, including:
at least one processor 301; and the number of the first and second groups,
a memory 302 communicatively coupled to the at least one processor 301; wherein,
the memory 302 stores instructions executable by the at least one processor 301, the instructions being executable by the at least one processor 301 to enable the at least one processor 301 to perform the fire early warning method described above.
Where the memory 302 and the processor 301 are coupled in a bus, the bus may comprise any number of interconnected buses and bridges, the buses coupling one or more of the various circuits of the processor 301 and the memory 302. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 301 is transmitted over a wireless medium through an antenna, which further receives the data and transmits the data to the processor 301.
The processor 301 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 302 may be used to store data used by processor 301 in performing operations.
A fourth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program realizes the above-described method embodiments when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (8)
1. A fire early warning method, comprising:
acquiring a characteristic image for representing the temperature of a monitoring area, wherein the monitoring area comprises a fire power utilization area and a non-fire power utilization area outside the fire power utilization area;
dividing the characteristic image into a first characteristic image for representing the temperature of the non-powered area and a second characteristic image for representing the temperature of the powered area;
acquiring N first pixel values of the first characteristic image, wherein N is an integer greater than 1;
calculating a first average value of the N first pixel values, and taking the first average value as a background value;
intermittently acquiring M second pixel values of the second characteristic image by taking a first preset time length as an interval, wherein M is an integer greater than 1;
subtracting the first average value from the M second pixel values respectively to obtain M intermediate values;
calculating a second average value of the M intermediate values, and taking the second average value as a characteristic value;
and acquiring the alarm level of the fire power utilization area according to the characteristic value and the background value, and sending alarm information when the alarm level is greater than a preset alarm level.
2. A fire early warning method according to claim 1, wherein the acquiring an alarm level of the fire power utilization area according to the eigenvalue and the background value, and sending alarm information when the alarm level is greater than a preset alarm level specifically comprises:
and judging whether the characteristic value is greater than the background value, increasing the alarm level when judging that the characteristic value is greater than the background value, and sending alarm information until the alarm level is greater than a preset alarm level in a second preset time length, wherein the second preset time length is greater than or equal to the first preset time length and is an integral multiple of the first preset time length.
3. A fire early warning method according to claim 1, wherein the acquiring an alarm level of the fire power utilization area according to the eigenvalue and the background value, and sending alarm information when the alarm level is greater than a preset alarm level specifically comprises:
judging whether the characteristic value is greater than the background value, increasing the alarm level when judging that the characteristic value is greater than the background value, reducing the alarm level when judging that the characteristic value is less than the background value, and sending alarm information until the alarm level is greater than the preset alarm level in a second preset time period, wherein the second preset time period is greater than or equal to the first preset time period and is an integral multiple of the first preset time period.
4. A fire warning method according to claim 3, wherein the determining whether the characteristic value is greater than the background value, increasing the alarm level when determining that the characteristic value is greater than the background value, and decreasing the alarm level when determining that the characteristic value is less than the background value specifically includes:
and judging whether the characteristic value is greater than the background value, adding 1 to the alarm level when judging that the characteristic value is greater than the background value, and subtracting 1 from the alarm level when judging that the characteristic value is less than the background value.
5. A fire warning method according to claim 1, wherein the acquiring a characteristic image for characterizing the temperature of the monitored area specifically comprises:
and acquiring an image of the monitoring area in a near infrared band, and taking the image in the near infrared band as the characteristic image.
6. A fire early warning method according to claim 1, wherein the dividing the characteristic image into a first characteristic image for representing the temperature of the non-powered area and a second characteristic image for representing the temperature of the powered area specifically comprises:
setting a target area as an area to be measured in coordinates in the characteristic image;
acquiring the image coordinates of the area to be measured in coordinates;
calculating a circumscribed circle of the image coordinate according to the image coordinate;
and taking the area where the circumscribed circle is located as the fire power utilization area, taking the area outside the circumscribed circle as the non-fire power utilization area, taking the image corresponding to the non-fire power utilization area as the first characteristic image, and taking the image corresponding to the fire power utilization area as the second characteristic image.
7. A fire warning device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the fire alerting method of any one of claims 1-6.
8. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the fire early warning method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811484960.4A CN109191765B (en) | 2018-12-06 | 2018-12-06 | Fire alarm method, apparatus and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811484960.4A CN109191765B (en) | 2018-12-06 | 2018-12-06 | Fire alarm method, apparatus and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109191765A CN109191765A (en) | 2019-01-11 |
| CN109191765B true CN109191765B (en) | 2019-03-15 |
Family
ID=64938474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811484960.4A Active CN109191765B (en) | 2018-12-06 | 2018-12-06 | Fire alarm method, apparatus and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109191765B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109847255B (en) * | 2019-01-29 | 2021-04-27 | 迅捷安消防及救援科技（深圳）有限公司 | Movable modular intelligent fire-fighting on-duty guarantee equipment and related products |
| CN109977993A (en) * | 2019-02-01 | 2019-07-05 | 深兰科技（上海）有限公司 | A kind of fire alarm method, apparatus and computer readable storage medium |
| CN111951508B (en) * | 2020-07-03 | 2023-01-17 | 北京中安安博文化科技有限公司 | Fire classification method, device, medium and electronic equipment |
| CN115050159A (en) * | 2022-06-08 | 2022-09-13 | 重庆工商大学 | Chemical laboratory fire prevention early warning method and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050265423A1 (en) * | 2004-05-26 | 2005-12-01 | Mahowald Peter H | Monitoring system for cooking station |
| CN101882811B (en) * | 2010-07-26 | 2014-08-13 | 广州科易光电技术有限公司 | Monitoring system and method of remote temperature image of substation |
| JP6190862B2 (en) * | 2015-11-26 | 2017-08-30 | 株式会社日立国際八木ソリューションズ | Monitoring system and monitoring control device thereof |
| CN106504461B (en) * | 2016-10-21 | 2019-02-12 | 国网山东省电力公司泰安供电公司 | A kind of electric fire monitoring device and method |
| CN107958567A (en) * | 2017-11-07 | 2018-04-24 | 佛山市云米电器科技有限公司 | Visual response alarm system, method and device |
-
2018
- 2018-12-06 CN CN201811484960.4A patent/CN109191765B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109191765A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109191765B (en) | Fire alarm method, apparatus and computer readable storage medium | |
| CN104751593B (en) | Method and system for fire detection, warning, positioning and extinguishing | |
| CN108806148B (en) | Security alarm method, infrared thermal imaging sensor and server | |
| CN105261142A (en) | Intelligent fire detecting and extinguishing system for outdoor large space and operation method thereof | |
| EP3745371A1 (en) | Smoke detection method, smoke detection device, smoke alarm and storage medium | |
| US20120262583A1 (en) | Automated method and system for detecting the presence of a lit cigarette | |
| CN112614302B (en) | Fire detection method, device and system and electronic equipment | |
| KR102585066B1 (en) | Combined fire alarm system using stand-alone fire alarm and visible light camera | |
| CN104598895A (en) | Method and device for flame detection based on video image analysis | |
| CN111986436B (en) | Comprehensive flame detection method based on ultraviolet and deep neural networks | |
| CN203630902U (en) | Improved image fire-hazard detector | |
| JP2008268023A (en) | Individual detector | |
| TW201823676A (en) | Surveillance system for robots capable of preventing a robot from falling down and collision in a space by detecting the optical pattern variation of an image, and achieving the purpose of detecting moving objects invading into a space | |
| CN110009863A (en) | A kind of vertical double light path smoke detection labyrinth and its detection method | |
| CN110514592A (en) | Smoke detector and its control method | |
| CN112084813A (en) | Abnormal target detection method and device and storage medium | |
| CN209708270U (en) | A kind of forest fire prevention and control monitoring system convenient for safeguarding | |
| CN103323122B (en) | The detection method of human body heat-releasing electric detection means in motion | |
| CN111366245A (en) | Method for improving detection capability of infrared temperature measurement on abnormal heating | |
| CN210466658U (en) | Intelligent building safety monitoring information system | |
| CN206441312U (en) | Visible ray and the double mode pyrotechnics identifying system of infrared thermal imaging | |
| CN108055449B (en) | Bucket tooth monitoring system based on thermal imaging | |
| CN115294718A (en) | Fire early warning system based on multisource data fusion | |
| CN210090964U (en) | Intelligent building security monitoring system based on double spectrums | |
| CN106954021A (en) | Infrared thermal imaging monitoring intelligent camera shield cloud deck |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240508 Address after: Room 6227, No. 999, Changning District, Shanghai 200050 Patentee after: Shenlan robot (Shanghai) Co.,Ltd. Country or region after: China Address before: 213611 room 103, building 4, chuangyangang, Changzhou science and Education City, No. 18, changwuzhong Road, Wujin District, Changzhou City, Jiangsu Province Patentee before: SHENLAN ARTIFICIAL INTELLIGENCE CHIP RESEARCH INSTITUTE (JIANGSU) Co.,Ltd. Country or region before: China Patentee before: DEEPBLUE TECHNOLOGY (SHANGHAI) Co.,Ltd. Patentee before: DEEPBLUE ROBOT (CHANGZHOU) Co.,Ltd. |