CN115439996B - Fire identification method and device based on space point energy analysis - Google Patents
Fire identification method and device based on space point energy analysis Download PDFInfo
- Publication number
- CN115439996B CN115439996B CN202211051581.2A CN202211051581A CN115439996B CN 115439996 B CN115439996 B CN 115439996B CN 202211051581 A CN202211051581 A CN 202211051581A CN 115439996 B CN115439996 B CN 115439996B
- Authority
- CN
- China
- Prior art keywords
- fire
- observation
- energy
- value
- point
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000000779 smoke Substances 0.000 claims abstract description 24
- 238000001931 thermography Methods 0.000 claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000005070 sampling Methods 0.000 claims abstract description 5
- 238000004891 communication Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 3
- 230000008054 signal transmission Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Abstract
The invention belongs to the technical field of fire monitoring, and particularly relates to a fire identification method based on space point energy analysis, which comprises the following steps: dividing an observation area into a plurality of sector-shaped observation surfaces by taking an observation point as a center; acquiring a high-definition image of a target observation surface acquired by an observation point and thermal imaging data, inputting the acquired data into a deep learning target detection model to identify visible light smoke and flame, calculating smoke and fire energy values, calculating a high-temperature energy value through a temperature map, and obtaining a space ignition energy value after weighted average; and controlling the observation points to traverse the observation surfaces in all the observation areas, and obtaining the ignition energy values of all the spaces of the observation areas after the traversal is finished. The current and historical space point energy sample sets of each observation surface are compared, the fire condition is judged, the historical space point energy sample sets are updated, when the fire condition is judged initially, sampling is repeated for a plurality of times near the space point through the change of the observation direction and the observation angle, and the influence caused by observation errors is reduced.
Description
Technical Field
The invention belongs to the technical field of fire monitoring, and particularly relates to a fire identification method and device based on space point energy analysis.
Background
Our country has abundant natural resources, forest, mineral products, wetland and grassland … …, the protection of natural environment is the basis of sustainable development, and fire is an important cause of natural resource loss. Because of wide scene ranges of forests, grasslands and the like, the technology prevention replaces the people to discover the fire in advance and becomes a necessary trend. At present, three main modes are adopted, and the first type is to collect temperature information in a scene through a monitoring thermal imaging camera, when the temperature exceeds a certain set value, the fire is considered to exist, the fire can generate high temperature, but a high Wen Weibi represents that the fire exists, for example: high temperatures may also occur in power plants, heat lamps, and residential stoves, so that such methods are more misinformation; the second type is to identify smoke and flame in each frame of image by monitoring a visible light camera and adopting an image analysis and identification algorithm, and the fire condition is considered to exist after the identification is successful, wherein the method is compared with recall rate and accuracy rate which are identified by the aid of the algorithm, and the smoke and the fire are difficult to reach actual use requirements due to the fact that data resources are less and characteristics are unstable; the third method is to combine the two methods to detect smoke and fire and to consider the existence of fire when the two occur simultaneously, and the method can improve a certain accuracy and reduce false alarm but increase the rate of missing report.
It is easy to see that the lack of fire data resources in the prior art causes insufficient generalization capability of the training model due to uncertainty of fire characteristics, and meanwhile, a real-time statistical analysis method deeply aiming at the fire characteristics is lacking, so that the false alarm rate and the false alarm rate are more. From the analysis of actual conditions, once a fire occurs, particularly a forest fire, the fire does not automatically disappear along with time, and the characteristics of the fire always exist, have certain mutation in time and have certain spreading in space.
Disclosure of Invention
The invention aims to provide a fire identification method and device based on space point energy analysis, which overcome the defects of the prior art, judge fire by comparing current and historical space point energy sample sets, and repeatedly sample the fire nearby space points through the change of the observation direction and the observation angle during initial judgment of fire, thereby reducing the influence caused by observation errors.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
a fire identification method based on space point energy analysis specifically comprises the following steps:
firstly, taking an observation point as a center, and dividing an observation area into a plurality of sector-shaped observation surfaces;
step two, obtaining a high-definition image and thermal imaging data of a target observation surface acquired by an observation point;
step three, inputting the acquired data into a deep learning target detection model to identify visible light smoke and flame, calculating smoke and flame energy values, calculating high temperature energy values through a temperature diagram, obtaining a space ignition energy value after weighted average, and judging whether fire exists or not;
and fourthly, controlling the observation points to traverse the observation surfaces in all the observation areas, and obtaining the ignition energy values of all the spaces of the observation areas after the traversal is finished.
Further, the method for processing data based on the model of the space ignition energy analysis comprises the following steps:
(1) Initializing a historical fire energy sample set of each observation surface;
(2) Calculating a change value s (x) of the fire energy value of the current target observation surface; if s (x) is less than 0, judging that no fire exists, updating the current space point historical fire sample set with 1/N probability, and updating the historical fire sample set of the nearby space points with 1/9 probability; if s (x) is more than 0, repeatedly sampling the fire energy values for M times near the fire space point, counting the variation value of the fire energy values sampled for M times, and recording the times K of which the variation value is more than 0;
(3) Judging whether the K/M is larger than a threshold value T, and if the K/M is larger than the threshold value T, outputting a fire finding condition.
Further, the expression of the historical fire energy sample set is:
f(x)＝{E1，E2，……，EN}
wherein E (1, 2, …, N) is a fire energy value.
Further, the calculation formula of the fire energy value E is as follows:
E＝α*E t +β*E s +γ*E f
wherein E is t E is a high temperature energy value s For smoke energy value, E f The fire energy value is alpha, beta and gamma, and the weight of the fire energy value is high temperature, smoke and fire energy respectively.
Further, the high temperature energy value E t To calculate according to the highest point temperature value and fire temperature distribution of the target areaA probability value of the fire condition of the target point; the smoke energy value E s The maximum probability value of the smoke recognition result of the target area is obtained; the fire energy value E f And identifying the maximum probability value of the result for the flame in the target area.
Further, the change value s (x) of the fire energy value is expressed as:
s(x)＝|g(x)-f(x)|-R
wherein g (x) is the current real-time fire energy value of the point x, and R is the energy change radius.
The invention also discloses a fire identification device based on the spatial point energy analysis, which comprises
The high-definition camera is used for shooting a high-definition image of the target observation surface;
the thermal imaging camera is used for shooting a thermal imaging image of the target observation surface;
the intelligent analysis module is used for receiving the high-definition image and the thermal imaging image, inputting the images into the deep learning target detection model for calculation and outputting whether fire exists or not;
and the double-shaft driving unit is used for driving the high-definition camera and the thermal imaging camera to rotate transversely and longitudinally so as to traverse all observation surfaces of the observation area.
Further, the fire identification device comprises a mounting base, a driving disc fixedly arranged on the upper end face of the mounting base, a shell rotationally arranged on the upper end face of the driving disc and a ball machine rotationally arranged in the shell, and the high-definition camera and the thermal imaging camera are embedded in the front end face of the ball machine.
Further, the dual-shaft driving unit includes two driving motors, and the two driving motors are respectively installed in the driving disc and the casing for driving the casing and the ball machine to rotate along their central axes.
Further, a controller and a wireless communication module are installed in the shell, the controller is used for controlling the opening and closing of each component and the transmission of signals, and the wireless communication module is used for conveying fire signals to the remote alarm terminal.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, according to the mutation and the propagation of fire, a statistical method based on a space point energy model is adopted, the fire is judged by comparing current and historical space point energy sample sets of each observation surface, when the fire is judged initially, sampling is repeated for a plurality of times near the space point through the change of the observation direction and the observation angle, the influence caused by observation errors is reduced, meanwhile, the energy value is distributed with weights according to the accuracy of each classifier, a plurality of weak classifiers are combined into one strong classifier, and the false recognition rate and the missing recognition rate of fire recognition are improved without depending on the observation result of one classifier.
Drawings
Fig. 1 is a schematic structural diagram of a fire recognition device based on spatial point energy analysis.
Fig. 2 is a schematic block diagram of a fire recognition device based on spatial point energy analysis.
In the figure: 1. a mounting base; 2. a drive plate; 3. a housing; 4. a ball machine; 5. a thermal imaging camera; 6. high definition camera.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The embodiment discloses a fire identification method based on spatial point energy analysis, which specifically comprises the following steps:
step one, taking an observation point as a center, and dividing an observation area into a plurality of sector-shaped observation surfaces.
And step two, obtaining a high-definition image and thermal imaging data of a target observation surface acquired by the observation point.
And thirdly, inputting the acquired data into a deep learning target detection model to identify visible light smoke and flame, calculating smoke and flame energy values, calculating high temperature energy values through a temperature diagram, obtaining space ignition energy values after weighted average, and judging whether fire exists according to the change of the fire energy values.
The method for processing data by the deep learning target detection model comprises the following steps:
(1) Initializing a historical fire energy sample set of each observation surface;
(2) Calculating a change value s (x) of the fire energy value of the current target observation surface; if s (x) is less than 0, judging that no fire exists, updating the current space point historical fire sample set with 1/N probability, and updating the historical fire sample set of the nearby space points with 1/9 probability; if s (x) is more than 0, repeatedly sampling the fire energy values for M times near the fire space point, counting the variation value of the fire energy values sampled for M times, and recording the times K of which the variation value is more than 0;
(3) Judging whether the K/M is larger than a threshold value T, and if the K/M is larger than the threshold value T, outputting a fire finding condition. The expression of the historical fire energy sample set is:
f(x)＝{E1，E2，……，EN}
wherein E (1, 2, …, N) is a fire energy value.
The fire energy value E is calculated as follows:
E＝α*E t +β*E s +γ*E f
wherein E is t E is a high temperature energy value s For smoke energy value, E f The fire energy value is alpha, beta and gamma, and the weight of the fire energy value is high temperature, smoke and fire energy respectively.
High temperature energy value E t The fire probability value of the target point is calculated according to the highest point temperature value and the fire temperature distribution of the target area; smoke energy value E s The maximum probability value of the smoke recognition result of the target area is obtained; fire energy value E f And identifying the maximum probability value of the result for the flame in the target area.
And alpha, beta and gamma are determined according to the weight distribution of the high temperature, smoke recognition and fire recognition model recognition rate.
The expression of the change value s (x) of the fire energy value is:
s(x)＝|g(x)-f(x)|-R
wherein g (x) is the current real-time fire energy value of x point, R is the energy change radius
And fourthly, controlling the observation points to traverse the observation surfaces in all the observation areas, and obtaining the ignition energy values of all the spaces of the observation areas after the traversal is finished.
Example 2
The embodiment discloses a fire identification device based on space point energy analysis based on the embodiment 1, which comprises
The high-definition camera 6 is used for shooting a high-definition image of the target observation surface;
a thermal imaging camera 5 for taking a thermal imaging image of the observation surface of the object;
the intelligent analysis module is used for receiving the high-definition image and the thermal imaging image, inputting the images into the deep learning target detection model for calculation and outputting whether fire exists or not;
and the biaxial driving unit is used for driving the high-definition camera and the thermal imaging camera 5 to rotate transversely and longitudinally so as to traverse all observation surfaces of the observation area.
The fire identification device comprises a mounting base 1, a driving disc 2 fixedly arranged on the upper end face of the mounting base 1, a shell 3 rotatably arranged on the upper end face of the driving disc 2, and a dome camera 4 rotatably arranged in the shell 3, wherein a high-definition camera 6 and a thermal imaging camera 5 are embedded in the front end face of the dome camera 4.
The biaxial drive unit includes two drive motors, and the two drive motors are respectively installed in the drive disk 2 and the housing 3 for driving the housing 3 and the ball machine 4 to rotate along their central axes.
The shell 3 is internally provided with a controller and a wireless communication module, the controller is used for controlling the opening and closing of each component and the transmission of signals, and the wireless communication module is used for transmitting fire signals to the remote alarm terminal.
When the spherical camera is used, the shell 3 and the spherical camera 4 are controlled to rotate through the double-shaft driving unit, so that the high-definition camera 6 and the thermal imaging camera 5 cover a spherical observation area; after the device enters a working state, each space point in an observation area is scanned according to a given sequence, the fire energy value is analyzed and sampled, the fire is judged according to a space ignition energy model, a history space ignition energy sample set is updated, after the fire occurs, a fire picture is snap shot and stored, the fire picture is transmitted to a remote alarm device at a background through a wireless communication module, the fire is put out in advance in linkage with police, and the loss of people and property is reduced.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (6)
1. A fire identification method based on space point energy analysis is characterized in that: the method specifically comprises the following steps:
firstly, taking an observation point as a center, and dividing an observation area into a plurality of sector-shaped observation surfaces;
step two, obtaining a high-definition image and thermal imaging data of a target observation surface acquired by an observation point;
step three, inputting the acquired data into a deep learning target detection model to identify visible light smoke and flame, calculating smoke and flame energy values, calculating high temperature energy values through a temperature diagram, obtaining a space ignition energy value after weighted average, and judging whether fire exists or not;
step four, controlling the observation points to traverse the observation surfaces in all the observation areas, and obtaining all the space ignition condition energy values of the observation areas after the traversal is finished;
the method for processing data by the deep learning target detection model comprises the following steps:
(1) Initializing a historical fire energy sample set;
(2) Calculating a change value s (x) of the fire energy value of the current target observation surface; if s (x) is less than 0, judging that no fire exists, updating the current space point historical fire sample set with 1/N probability, and updating the historical fire sample set of the nearby space points with 1/9 probability; if s (x) is more than 0, repeatedly sampling the fire energy values for M times near the fire space point, counting the variation value of the fire energy values sampled for M times, and recording the times K of which the variation value is more than 0;
(3) Judging whether K/M is larger than a threshold T, and if K/M is larger than the threshold T, outputting a fire finding condition;
the expression of the historical fire energy sample set is as follows:
f(x)＝{E1，E2，……，EN}
wherein E1, E2, E3, … and EN are fire energy values;
the calculation formula of the fire energy value E is as follows:
E＝α*E t +β*E s +γ*E f
wherein E is t E is a high temperature energy value s For smoke energy value, E f The fire energy value is alpha, beta and gamma, and the weight of the fire energy value is high temperature, smoke and fire energy respectively;
the high temperature energy value E t The fire probability value of the target point is calculated according to the highest point temperature value and the fire temperature distribution of the target area; the smoke energy value E s The maximum probability value of the smoke recognition result of the target area is obtained; the fire energy value E f And identifying the maximum probability value of the result for the flame in the target area.
2. A fire identification method based on spatial point energy analysis according to claim 1, characterized in that: the expression of the change value s (x) of the fire energy value is as follows:
s(x)＝g(x)-f(x)-R
wherein g (x) is the current real-time fire energy value of the point x, and R is the energy change radius.
3. A fire identification device based on spatial point energy analysis for implementing the fire identification method based on spatial point energy analysis as set forth in claim 1 or 2, characterized in that: comprising
The high-definition camera (6) is used for shooting a high-definition image of the target observation surface;
a thermal imaging camera (5) for taking a thermal imaging image of the target observation surface;
the intelligent analysis module is used for receiving the high-definition image and the thermal imaging image, inputting the images into the deep learning target detection model for calculation and outputting whether fire exists or not;
and the double-shaft driving unit is used for driving the high-definition camera (6) and the thermal imaging camera (5) to rotate transversely and longitudinally so as to traverse all observation surfaces of the observation area.
4. A fire identification device based on spatial point energy analysis as claimed in claim 3, wherein: the fire identification device comprises a mounting base (1), a driving disc (2) fixedly arranged on the upper end face of the mounting base (1), a shell (3) rotatably arranged on the upper end face of the driving disc (2) and a ball machine (4) rotatably arranged in the shell (3), wherein the high-definition camera (6) and the thermal imaging camera (5) are embedded in the front end face of the ball machine (4).
5. A fire identification device based on spatial point energy analysis as set forth in claim 4, wherein: the double-shaft driving unit comprises two driving motors, and the two driving motors are respectively arranged in the driving disc (2) and the shell (3) and used for driving the shell (3) and the ball machine (4) to rotate along the central axes of the shell and the ball machine.
6. A fire identification device based on spatial point energy analysis as set forth in claim 5, wherein: the fire alarm device is characterized in that a controller and a wireless communication module are arranged in the shell (3), the controller is used for controlling the opening and closing of each component and the transmission of signals, and the wireless communication module is used for conveying fire signals to the remote alarm terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211051581.2A CN115439996B (en) | 2022-08-31 | 2022-08-31 | Fire identification method and device based on space point energy analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211051581.2A CN115439996B (en) | 2022-08-31 | 2022-08-31 | Fire identification method and device based on space point energy analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115439996A CN115439996A (en) | 2022-12-06 |
| CN115439996B true CN115439996B (en) | 2024-02-13 |
Family
ID=84244861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211051581.2A Active CN115439996B (en) | 2022-08-31 | 2022-08-31 | Fire identification method and device based on space point energy analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115439996B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458865A (en) * | 2008-05-09 | 2009-06-17 | 丁国锋 | Fire disaster probe system and method |
| CN202720745U (en) * | 2012-05-23 | 2013-02-06 | 无锡蓝天电子有限公司 | Image type smoke fire detector |
| KR20150131841A (en) * | 2014-05-16 | 2015-11-25 | 사단법인 한국화재보험협회 | Intelligent fire detection system using fuzzy logic |
| CN105678419A (en) * | 2016-01-05 | 2016-06-15 | 天津大学 | Fine grit-based forest fire hazard probability forecasting system |
| CN106971485A (en) * | 2017-03-30 | 2017-07-21 | 浙江大学 | Realtime graphic based on FPGA monitors multi-functional fire wireless alarm system and method |
| CN107437318A (en) * | 2016-05-25 | 2017-12-05 | 知晓（北京）通信科技有限公司 | A kind of visible ray Intelligent Recognition algorithm |
| KR20200119921A (en) * | 2019-03-19 | 2020-10-21 | 경북대학교 산학협력단 | Intelligent fire identification apparatus, intelligent fire identification method and recording medium |
| CN111932817A (en) * | 2020-08-03 | 2020-11-13 | 上海理工大学 | Fire detection early warning system and method |
| CN212379949U (en) * | 2020-09-10 | 2021-01-19 | 天津市港建讯达信息技术有限公司 | Alarm device for identifying smoke and fire and positioning in subareas by adopting video analysis technology |
| CN113762314A (en) * | 2021-02-02 | 2021-12-07 | 北京京东振世信息技术有限公司 | Smoke and fire detection method and device |
-
2022
- 2022-08-31 CN CN202211051581.2A patent/CN115439996B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458865A (en) * | 2008-05-09 | 2009-06-17 | 丁国锋 | Fire disaster probe system and method |
| CN202720745U (en) * | 2012-05-23 | 2013-02-06 | 无锡蓝天电子有限公司 | Image type smoke fire detector |
| KR20150131841A (en) * | 2014-05-16 | 2015-11-25 | 사단법인 한국화재보험협회 | Intelligent fire detection system using fuzzy logic |
| CN105678419A (en) * | 2016-01-05 | 2016-06-15 | 天津大学 | Fine grit-based forest fire hazard probability forecasting system |
| CN107437318A (en) * | 2016-05-25 | 2017-12-05 | 知晓（北京）通信科技有限公司 | A kind of visible ray Intelligent Recognition algorithm |
| CN106971485A (en) * | 2017-03-30 | 2017-07-21 | 浙江大学 | Realtime graphic based on FPGA monitors multi-functional fire wireless alarm system and method |
| KR20200119921A (en) * | 2019-03-19 | 2020-10-21 | 경북대학교 산학협력단 | Intelligent fire identification apparatus, intelligent fire identification method and recording medium |
| CN111932817A (en) * | 2020-08-03 | 2020-11-13 | 上海理工大学 | Fire detection early warning system and method |
| CN212379949U (en) * | 2020-09-10 | 2021-01-19 | 天津市港建讯达信息技术有限公司 | Alarm device for identifying smoke and fire and positioning in subareas by adopting video analysis technology |
| CN113762314A (en) * | 2021-02-02 | 2021-12-07 | 北京京东振世信息技术有限公司 | Smoke and fire detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115439996A (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108389359B (en) | Deep learning-based urban fire alarm method | |
| US7991187B2 (en) | Intelligent image smoke/flame sensor and detection system | |
| CN109448292A (en) | A kind of power grid mountain fire monitoring and pre-alarming method | |
| CN109815904B (en) | Fire identification method based on convolutional neural network | |
| CN109243130A (en) | More methods physics fusion fire monitoring system and its predict fire probability | |
| CN111985365A (en) | Straw burning monitoring method and system based on target detection technology | |
| CN112068111A (en) | Unmanned aerial vehicle target detection method based on multi-sensor information fusion | |
| CN105574468B (en) | Video flame detection method, device and system | |
| CN110633643A (en) | Abnormal behavior detection method and system for smart community | |
| CN113936413B (en) | Early fire monitoring and early warning method and device | |
| CN112257554A (en) | Forest fire recognition method, system, program and storage medium | |
| US11887374B2 (en) | Systems and methods for 2D detections and tracking | |
| CN112862150A (en) | Forest fire early warning method based on image and video multi-model | |
| CN114913663A (en) | Anomaly detection method and device, computer equipment and storage medium | |
| CN116187740A (en) | Mountain fire monitoring method and system along power transmission line | |
| CN115439996B (en) | Fire identification method and device based on space point energy analysis | |
| CN114677640A (en) | Intelligent construction site safety monitoring system and method based on machine vision | |
| CN105160799B (en) | A kind of condition of a fire based on infrared thermal imaging uncorrected data and thermal source detection method and device | |
| CN114120171A (en) | Fire smoke detection method, device and equipment based on video frame and storage medium | |
| CN104243894A (en) | Audio and video fused monitoring method | |
| Batista et al. | Improved real-time wildfire detection using a surveillance system | |
| CN116052360B (en) | Fire alarm system | |
| CN115862296A (en) | Fire risk early warning method, system, equipment and medium for railway construction site | |
| CN110674764A (en) | Method, device and system for detecting exposed earthwork of construction site | |
| CN111626095A (en) | Power distribution inspection system based on Ethernet |
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 |