CN111899458A - Artificial intelligence-based fire smoke image identification method - Google Patents
Artificial intelligence-based fire smoke image identification method Download PDFInfo
- Publication number
- CN111899458A CN111899458A CN202010730180.4A CN202010730180A CN111899458A CN 111899458 A CN111899458 A CN 111899458A CN 202010730180 A CN202010730180 A CN 202010730180A CN 111899458 A CN111899458 A CN 111899458A
- Authority
- CN
- China
- Prior art keywords
- monitoring device
- thermal radiation
- fire
- image
- radiation energy
- 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
- 239000000779 smoke Substances 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000012806 monitoring device Methods 0.000 claims abstract description 62
- 230000005855 radiation Effects 0.000 claims abstract description 58
- 238000012544 monitoring process Methods 0.000 claims abstract description 24
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 238000010521 absorption reaction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 239000003546 flue gas Substances 0.000 claims description 3
- 238000002834 transmittance Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 230000002159 abnormal effect Effects 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- 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
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention belongs to the technical field of fire monitoring, and discloses a fire smoke image identification method based on artificial intelligence, which is applied to a monitoring device, wherein the monitoring device comprises a thermal radiation acquisition unit, a thermal radiation comparison unit and a video image data analysis unit, and the method comprises the following steps: starting a monitoring device; A. acquiring thermal radiation energy in a monitoring range of the monitoring device through a thermal radiation acquisition unit in the monitoring device; B. the thermal radiation energy is preferably compared through a thermal radiation comparison unit in the monitoring device; acquiring thermal radiation energy of at least one region according to the comparison result; the invention greatly improves the processing efficiency of the monitoring device, prolongs the service life of the monitoring device, and can acquire data in time because the device only needs to acquire data of abnormal areas, so that workers can take corresponding measures in time, thereby increasing the extinguishing efficiency of fire and reducing the probability of serious fire.
Description
Technical Field
The invention belongs to the technical field of fire monitoring, and particularly relates to a fire smoke image identification method based on artificial intelligence.
Background
A fire refers to a disaster caused by combustion that is out of control in time or space. In a new standard, a fire disaster is defined as combustion which is out of control in time or space, and among various disasters, the fire disaster is one of the main disasters which threaten public safety and social development most frequently and most generally, so that people can timely rescue the fire disaster through real-time monitoring, so that the fire disaster is controlled in advance, and the loss caused by the fire disaster is reduced to the maximum extent.
In chinese patent "CN 201811248760.9", a fire smoke image recognition method based on artificial intelligence is disclosed, which describes that "the method of the present invention extracts the grayish component and contour of the target image after the smoke image is divided in the HIS model, analyzes the characteristics of the smoke image and the interference image by using the image preprocessing technique, and uses the circularity of the smoke contour as the fire recognition criterion, the method can accurately reflect the smoke motion characteristics, so that the result is less affected by the same pixels, the false alarm rate can be greatly reduced, the fire smoke detection function can be quickly and accurately realized", but when the device proposed by the patent is used, a large amount of image data can be collected, which greatly increases the data processing amount of the device, reduces the processing efficiency of the device, shortens the service life of the device, and because the device needs to collect a large amount of data, abnormal areas cannot be collected in time, so that the staff cannot take corresponding measures in time, and the probability of serious fire is increased.
Disclosure of Invention
The invention aims to provide a fire smoke image identification method based on artificial intelligence, and aims to solve the problem of low processing efficiency of the device in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a fire smoke image recognition method based on artificial intelligence is applied to a monitoring device, the monitoring device comprises a thermal radiation acquisition unit, a thermal radiation comparison unit and a video image data analysis unit, and the method comprises the following steps:
starting a monitoring device;
A. acquiring thermal radiation energy in a monitoring range of the monitoring device through a thermal radiation acquisition unit in the monitoring device;
B. the thermal radiation energy is preferably compared through a thermal radiation comparison unit in the monitoring device; acquiring thermal radiation energy of at least one region according to the comparison result;
C. recommending the region obtained in the step B to a monitoring device in the monitoring device;
D. b, acquiring video image data of the area obtained in the step B through a monitoring device;
E. analyzing by a video image data analysis unit in the monitoring device to obtain a smoke image; segmenting the smoke image in an HIS model, and extracting the grey component and the outline of a target image;
F. analyzing the characteristics of the flue gas image and the interference image by utilizing an image preprocessing technology;
G. then, the circularity of the smoke outline is used as a fire identification basis, if the smoke is judged to be fire smoke, the monitoring device sends an instruction, the alarm is controlled to send an alarm signal, the linkage fire extinguishing device is controlled to rapidly start a fire extinguishing function, and a fire occurrence signal is sent to the remote monitoring platform; and if the smoke is judged to be non-fire smoke, returning to the step D, and continuously reading the video image data by the monitoring device.
Preferably, the fire is identified as a fire smoke image according to the image with the circularity greater than 3, and the image with the circularity less than 3 is identified as a non-fire smoke image.
Preferably, the thermal radiation energy is energy transmitted outwards in an electromagnetic wave mode when an object in the monitoring range of the monitoring device is burnt.
Preferably, the calculation method of the thermal radiation energy is Q = Qr + Qa + Qd;
1=Qr/Q+Qa/Q+Qd/Q=r+a+d；
r-reflectance; a-absorption rate; d is the transmittance.
Preferably, the preferred contrast is a magnitude contrast of thermal radiation energy;
if the heat radiation energy in the area is far larger than the heat radiation energy in the room temperature state; step C is performed.
Preferably, the calculation formula of the circularity is C = L2/4 pi a, where L is the perimeter of the shape and a is the area of the shape.
Preferably, the communication mode between the remote monitoring platform and the monitoring device is at least one of WIFI, 3G, 4G, 5G, ethernet and RS 485.
Preferably, the step D is completed by a monitoring camera on the monitoring device, and the video image data collected by the monitoring camera is transmitted to the video image data analysis unit through the ZigBee.
Compared with the prior art, the invention has the beneficial effects that:
(1) according to the invention, the thermal radiation energy in the monitoring range of the monitoring device is acquired by the thermal radiation acquisition unit for comparison, so that video image data acquisition is carried out on the area with abnormal thermal radiation energy in the monitoring range, the monitoring device can acquire videos of the abnormal area more quickly for analysis and processing, the video image data acquisition amount of the monitoring device is reduced, the video image data analysis amount of the monitoring device is also reduced, the processing efficiency of the monitoring device is greatly improved, the service life of the monitoring device is prolonged, and the device only needs to acquire data of the abnormal area, so that the device can acquire data in time, a worker can take counter measures in time, the fire extinguishing efficiency is increased, and the probability of fire hazard severity is reduced.
Drawings
FIG. 1 is a flow chart of a fire smoke image identification method based on artificial intelligence according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides the following technical solutions: the fire smoke image identification method based on artificial intelligence is applied to a monitoring device, the monitoring device comprises a thermal radiation acquisition unit, a thermal radiation comparison unit and a video image data analysis unit, and the method comprises the following steps:
starting a monitoring device;
A. acquiring thermal radiation energy in a monitoring range of the monitoring device through a thermal radiation acquisition unit in the monitoring device;
B. the thermal radiation energy is preferably compared through a thermal radiation comparison unit in the monitoring device; acquiring thermal radiation energy of at least one region according to the comparison result;
C. recommending the region obtained in the step B to a monitoring device in the monitoring device;
D. b, acquiring video image data of the area obtained in the step B through a monitoring device;
E. analyzing by a video image data analysis unit in the monitoring device to obtain a smoke image; segmenting the smoke image in an HIS model, and extracting the grey component and the outline of a target image;
F. analyzing the characteristics of the flue gas image and the interference image by utilizing an image preprocessing technology;
G. then, the circularity of the smoke outline is used as a fire identification basis, if the smoke is judged to be fire smoke, the monitoring device sends an instruction, the alarm is controlled to send an alarm signal, the linkage fire extinguishing device is controlled to rapidly start a fire extinguishing function, and a fire occurrence signal is sent to the remote monitoring platform; and if the smoke is judged to be non-fire smoke, returning to the step D, and continuously reading the video image data by the monitoring device.
The extraction algorithm of the gray component and the contour of the target image comprises the following steps:
selecting a reference point, scanning image pixel points X one by one to obtain R, G, B components and hue H of corresponding pixel points, reserving points with the hue H between 175 and 185, and calculating alpha values of the reserved points, wherein the points with the alpha between 0 and 20 can be used as the reference point A;
normalizing the reference points, namely normalizing the pixel points A selected as the reference points;
calculating the HIS value of the reference point, solving the minimum value and the maximum value of the normalized pixel point, and calculating the HIS value of the point;
calculating the HIS value of the next pixel point, continuously scanning the next pixel point B of the image, and calculating the values of the brightness, the saturation and the hue of the point;
calculating the space distance between the two points AB;
the smoke color area is reserved, the space distance D is smaller than or equal to 0.2, the smoke color area can be reserved as a preliminary target area, the steps are repeated, all pixel points are scanned, the obtained image has noise, the space distance D is smaller than or equal to 0.2, R, G, B component characteristics of the point are not satisfied, the smoke color area is possibly not satisfied, the pixel points of the value range of 0-20 of the preliminary target area are reserved as the target area, other pixel points are used as a white background, and interference noise is filtered.
Further, the thermal radiation energy is energy transmitted outwards in an electromagnetic wave mode when an object in the monitoring range of the monitoring device burns.
Furthermore, the communication mode of the remote monitoring platform and the monitoring device is at least one of WIFI, 3G, 4G, 5G, Ethernet and RS 485.
And further, the step D is completed by a monitoring camera on the monitoring device, and the video image data collected by the monitoring camera is transmitted to the video image data analysis unit through the ZigBee.
The first embodiment is as follows:
the calculation of the thermal radiation energy is Q = Qr + Qa + Qd;
1=Qr/Q+Qa/Q+Qd/Q=r+a+d；
r-reflectance; a-absorption rate; d is the transmittance;
specifically, when the absorption rate a =1, it indicates that the object can absorb all the heat rays projected to its surface, and is called an absolute black body, or simply a black body.
When the reflectivity r =1, it means that the object can totally reflect the heat rays projected on its surface, and is called an absolute white body, or simply a white body.
When the mirror is specular (incidence angle = reflection angle), the mirror is called a mirror body.
When d =1, the transparent body is called an absolute transparent body, or simply called a transparent body, or a mesothermal body or a diathermic body.
Further, the preferable comparison is a magnitude comparison of thermal radiation energy;
if the heat radiation energy in the area is far larger than the heat radiation energy in the room temperature state; executing the step C;
when the thermal radiation energy of the current state of the area monitored by the monitoring device is 1200, the thermal radiation energy of the room temperature state of the area is 600;
when the heat radiation energy of the current state of the second region monitored by the monitoring device is 1000, the heat radiation energy of the second region at room temperature is 980;
the difference between the thermal radiation energy of the current state of the region I and the thermal radiation energy of the state of room temperature is 600;
the difference between the heat radiation energy of the current state of the second region and the heat radiation energy of the room temperature state is 20;
therefore, the difference between the thermal radiation energy of the current state of the area II and the thermal radiation energy of the room temperature state is very small, and the difference between the thermal radiation energy of the current state of the area I and the thermal radiation energy of the room temperature state is very large, the device recommends the area I to the monitoring device.
Example two:
judging the fire smoke image according to the image with the circularity larger than 3 as the fire identification basis, and judging the image with the circularity smaller than 3 as the non-fire smoke image;
the calculation formula of the circularity is C = L2/4 pi A, wherein L is the perimeter of the shape, and A is the area of the shape;
l of the first region is 62.8, a is 2, i.e. the circularity of the first region is C =62.8 × 2/4 pi × 2= 5;
l in the second region is 62.8, a is 5, i.e., the circularity of the second region is C =62.8 × 2/4 pi × 5= 2;
the circularity of the first area is greater than 3, and the circularity of the second area is less than 3;
namely, the first area is in fire and the second area is not in fire.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A fire smoke image identification method based on artificial intelligence is characterized by comprising the following steps: the identification method is applied to a monitoring device, the monitoring device comprises a thermal radiation acquisition unit, a thermal radiation comparison unit and a video image data analysis unit, and the method comprises the following steps:
starting a monitoring device;
A. acquiring thermal radiation energy in a monitoring range of the monitoring device through a thermal radiation acquisition unit in the monitoring device;
B. the thermal radiation energy is preferably compared through a thermal radiation comparison unit in the monitoring device; acquiring thermal radiation energy of at least one region according to the comparison result;
C. recommending the region obtained in the step B to a monitoring device in the monitoring device;
D. b, acquiring video image data of the area obtained in the step B through a monitoring device;
E. analyzing by a video image data analysis unit in the monitoring device to obtain a smoke image; segmenting the smoke image in an HIS model, and extracting the grey component and the outline of a target image;
F. analyzing the characteristics of the flue gas image and the interference image by utilizing an image preprocessing technology;
G. then, the circularity of the smoke outline is used as a fire identification basis, if the smoke is judged to be fire smoke, the monitoring device sends an instruction, the alarm is controlled to send an alarm signal, the linkage fire extinguishing device is controlled to rapidly start a fire extinguishing function, and a fire occurrence signal is sent to the remote monitoring platform; and if the smoke is judged to be non-fire smoke, returning to the step D, and continuously reading the video image data by the monitoring device.
2. The fire smoke image identification method based on artificial intelligence according to claim 1, wherein: the image with the circularity smaller than 3 is judged as a fire smoke image, and the image with the circularity smaller than 3 is judged as a non-fire smoke image.
3. The fire smoke image identification method based on artificial intelligence according to claim 1, wherein: the thermal radiation energy is energy which is transmitted outwards in an electromagnetic wave mode when an object in the monitoring range of the monitoring device burns.
4. The fire smoke image identification method based on artificial intelligence according to claim 1, wherein: the heat radiation energy is calculated in a manner of Q = Qr + Qa + Qd;
1=Qr/Q+Qa/Q+Qd/Q=r+a+d；
r-reflectance; a-absorption rate; d is the transmittance.
5. The fire smoke image identification method based on artificial intelligence according to claim 1, wherein: the preferred contrast is the magnitude contrast of thermal radiation energy;
if the heat radiation energy in the area is far larger than the heat radiation energy in the room temperature state; step C is performed.
6. The fire smoke image identification method based on artificial intelligence according to claim 1, wherein: the circularity is calculated as C = L2/4 π A, where L is the perimeter of the shape and A is the area of the shape.
7. The fire smoke image identification method based on artificial intelligence according to claim 1, wherein: the communication mode of the remote monitoring platform and the monitoring device is at least one of WIFI, 3G, 4G, 5G, Ethernet and RS 485.
8. The fire smoke image identification method based on artificial intelligence according to claim 1, wherein: and D, the step D is completed by a monitoring camera on the monitoring device, and the video image data acquired by the monitoring camera is transmitted to the video image data analysis unit through the ZigBee.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010730180.4A CN111899458A (en) | 2020-07-27 | 2020-07-27 | Artificial intelligence-based fire smoke image identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010730180.4A CN111899458A (en) | 2020-07-27 | 2020-07-27 | Artificial intelligence-based fire smoke image identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111899458A true CN111899458A (en) | 2020-11-06 |
Family
ID=73190220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010730180.4A Pending CN111899458A (en) | 2020-07-27 | 2020-07-27 | Artificial intelligence-based fire smoke image identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111899458A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10143777A (en) * | 1996-11-07 | 1998-05-29 | Tokai Carbon Co Ltd | Method for detecting fire in high temperature heat treatment process and device therefor |
| CN104867265A (en) * | 2015-04-22 | 2015-08-26 | 深圳市佳信捷技术股份有限公司 | Camera apparatus, and fire detection alarm system and method |
| CN106887108A (en) * | 2015-12-16 | 2017-06-23 | 天维尔信息科技股份有限公司 | Early warning interlock method and system based on thermal imaging |
| CN109147259A (en) * | 2018-11-20 | 2019-01-04 | 武汉理工光科股份有限公司 | A kind of remote fire detection system and method based on video image |
| CN109598194A (en) * | 2018-10-25 | 2019-04-09 | 安徽含光软件开发有限公司 | A kind of fire smoke image-recognizing method based on artificial intelligence |
| CN110428579A (en) * | 2019-08-08 | 2019-11-08 | 冯仙武 | Indoor Monitoring System, method and device based on image recognition |
-
2020
- 2020-07-27 CN CN202010730180.4A patent/CN111899458A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10143777A (en) * | 1996-11-07 | 1998-05-29 | Tokai Carbon Co Ltd | Method for detecting fire in high temperature heat treatment process and device therefor |
| CN104867265A (en) * | 2015-04-22 | 2015-08-26 | 深圳市佳信捷技术股份有限公司 | Camera apparatus, and fire detection alarm system and method |
| CN106887108A (en) * | 2015-12-16 | 2017-06-23 | 天维尔信息科技股份有限公司 | Early warning interlock method and system based on thermal imaging |
| CN109598194A (en) * | 2018-10-25 | 2019-04-09 | 安徽含光软件开发有限公司 | A kind of fire smoke image-recognizing method based on artificial intelligence |
| CN109147259A (en) * | 2018-11-20 | 2019-01-04 | 武汉理工光科股份有限公司 | A kind of remote fire detection system and method based on video image |
| CN110428579A (en) * | 2019-08-08 | 2019-11-08 | 冯仙武 | Indoor Monitoring System, method and device based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112133052B (en) | Image fire detection method for nuclear power plant | |
| CN104966372B (en) | The forest fire intelligent identifying system and method for multi-data fusion | |
| CN110309719A (en) | A kind of electric network operation personnel safety cap wears management control method and system | |
| CN112396658B (en) | Indoor personnel positioning method and system based on video | |
| CN110837822B (en) | Fire-fighting robot injection curve adjusting method and device based on multi-view vision | |
| CN105976365A (en) | Nocturnal fire disaster video detection method | |
| EP3440593B1 (en) | Method and apparatus for iris recognition | |
| CN101625789A (en) | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire | |
| CN102163361A (en) | Image-type fire detection method based on cumulative prospect image | |
| CN112365669A (en) | Dual-band far infrared fusion-superposition imaging and fire early warning method and system | |
| CN108389359A (en) | A kind of Urban Fires alarm method based on deep learning | |
| CN108230607B (en) | Image fire detection method based on regional characteristic analysis | |
| CN111223263A (en) | Full-automatic comprehensive fire early warning response system | |
| CN107609449B (en) | Identification code checking method and system and shared bicycle | |
| CN107688793A (en) | A kind of outside transformer substation fire automatic monitoring method for early warning | |
| CN110381293A (en) | Video monitoring method, device and computer readable storage medium | |
| Chowdhury et al. | Computer vision and smoke sensor based fire detection system | |
| JP5042177B2 (en) | Image sensor | |
| CN109034038B (en) | Fire identification device based on multi-feature fusion | |
| CN114898261A (en) | Sleep quality assessment method and system based on fusion of video and physiological data | |
| CN109598194A (en) | A kind of fire smoke image-recognizing method based on artificial intelligence | |
| CN111144252A (en) | Monitoring and early warning method for people stream analysis | |
| CN113299034B (en) | Flame identification early warning method suitable for multiple scenes | |
| CN111899458A (en) | Artificial intelligence-based fire smoke image identification method | |
| CN112733646B (en) | Liquid medium leakage automatic detection method and system based on thermal imaging |
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 |