CN113409536B - Power equipment potential fire alarm recognition system and method based on machine vision - Google Patents
Power equipment potential fire alarm recognition system and method based on machine vision Download PDFInfo
- Publication number
- CN113409536B CN113409536B CN202110864710.9A CN202110864710A CN113409536B CN 113409536 B CN113409536 B CN 113409536B CN 202110864710 A CN202110864710 A CN 202110864710A CN 113409536 B CN113409536 B CN 113409536B
- Authority
- CN
- China
- Prior art keywords
- fire
- module
- image acquisition
- image
- identification
- 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 11
- 238000012790 confirmation Methods 0.000 claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 239000000779 smoke Substances 0.000 claims description 90
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 3
- 238000001931 thermography Methods 0.000 abstract description 5
- 230000002265 prevention Effects 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009835 boiling Methods 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention relates to the technical field of fire monitoring and identification, in particular to a system and a method for identifying potential fire alarms of power equipment based on machine vision, wherein the system comprises an image acquisition module, a data acquisition module and a data processing module, wherein the image acquisition module comprises a plurality of image acquisition devices which are used for respectively acquiring images within an initial distance threshold range; the fire recognition module is used for analyzing and recognizing the fire condition in the image and generating a fire recognition report, wherein the fire recognition report comprises fire occurrence probability and fire position data; the image acquisition range adjusting module is used for expanding the image acquisition range of the image acquisition device according to the fire identification report; and the fire confirmation module is used for generating a fire confirmation report according to the fire identification report generated after the image acquisition range of the image acquisition device is expanded. This scheme can be timely detect the condition of a fire to effectively improve the accuracy that the condition of a fire detected, its cost adopts the remote fire prevention equipment of thermal imaging and infrared combination relatively to carry out the conflagration detection lower simultaneously.
Description
Technical Field
The invention relates to the technical field of fire monitoring and identification, in particular to a system and a method for identifying potential fire alarms of power equipment based on machine vision.
Background
Along with the development of society and the further expansion of urbanization construction, the problem of preventing indoor and outdoor fire disasters is increasingly outstanding, economic loss and casualties caused by the fire disasters are very serious, wherein the fire disasters caused by power equipment faults are numerous, the consequences of the fire disasters caused by the power equipment faults are often unreasonable, and sometimes 'fire burning connecting pieces' can be generated to burn a large amount of power equipment, even electric shock casualty accidents can be generated.
Automatic fire alarm systems are currently in widespread use in various fields, such as: smoke alarms are generally adopted for indoor fire detection and alarm, and thermal imaging and infrared combined remote fire protection equipment is generally adopted for forest fire detection. The two fire alarm systems have corresponding defects, firstly, the smoke alarm has requirements on the smoke concentration and the carbon monoxide concentration, the alarm can be carried out and the spray head is started to extinguish a fire only after the fire reaches a certain degree, and for the fire caused by the failure of the power equipment, due to the self characteristics of the power equipment, if the fire is not found in time, the fire rapidly spreads along with the lapse of time, and the consequence is unreasonable; secondly, although the fire detection is carried out by means of thermal imaging and infrared detection, the cost is high, and the cost of a single camera device can reach tens of thousands or even more than hundreds of thousands. Therefore, it is very important to find a fire identification technology which can timely and accurately detect the fire of the electrical equipment and has relatively low manufacturing cost.
Disclosure of Invention
The invention provides a system and a method for identifying potential fire alarms of electric equipment based on machine vision, which can detect fire conditions in time and effectively improve the accuracy of fire condition detection.
The basic scheme provided by the invention is as follows:
latent fire alarm identification system of power equipment based on machine vision acquires module, fire identification module, image acquisition range adjustment module and fire confirmation module including the image:
the image acquisition module comprises a plurality of image acquisition devices and is used for respectively acquiring images within the range of the initial distance threshold;
the fire identification module is used for analyzing and identifying the fire condition in the image and generating a fire identification report, wherein the fire identification report comprises fire occurrence probability and fire position data;
the image acquisition range adjusting module is used for expanding the image acquisition range of the image acquisition device according to the fire identification report;
and the fire confirmation module is used for generating a fire confirmation report according to a fire recognition report generated after the image acquisition range of the image acquisition device is expanded.
The principle and the advantages of the invention are as follows: in the scheme, the fire disaster condition is identified through the images acquired by the image acquisition devices, and the fire disaster identification report is generated, so that the fire disaster condition can be detected in time, and the aim of early finding and early control is fulfilled; in addition, according to the fire identification report, the image acquisition range of the image acquisition device is expanded, so that the image acquisition range of each image acquisition device can be expanded according to the fire occurrence probability and fire position data, and after the image acquisition range is expanded, other image acquisition devices capable of shooting the fire position also acquire images of the position where the fire is likely to occur, so that fire identification reports are generated according to the images of the fire occurrence position acquired by the plurality of image acquisition devices, and a fire confirmation report is generated, so that when the fire occurrence probability is low, each image acquisition device can be ensured to acquire only images in a small range, the coincidence degree of the images acquired by each image acquisition device is reduced, the workload of a fire identification module is reduced, the working efficiency of the fire identification module is improved, and the fire identification speed of the fire identification module is accelerated; in addition, compare with the remote fire prevention equipment that adopts thermal imaging and infrared combination to carry out the fire detection, only need in this scheme adopt ordinary image acquisition device can, its cost is lower. To sum up, what this scheme of adoption can be timely detects the condition of a fire to effectively improve the accuracy that the condition of a fire detected, its cost adopts the remote fire prevention equipment of thermal imaging and infrared combination relatively to carry out the fire detection lower simultaneously.
Further, the image acquisition module stores an initial distance threshold and a maximum distance threshold, and also stores a field position range corresponding to a boundary in an image when each image acquisition device acquires the image within the maximum distance threshold range;
the image acquisition range adjusting module comprises a probability analysis module, a position comparison module and a threshold value expansion module:
the probability analysis module is used for comparing the fire occurrence probability with a probability threshold value to generate a probability comparison result;
the position comparison module is used for comparing the fire position data with the field position range corresponding to each image acquisition device when the fire occurrence probability is higher than a probability threshold value to generate a position comparison result;
and the threshold value expanding module is used for expanding the image acquiring range of the image acquiring device according to the position comparison result.
Has the beneficial effects that: only when the probability of fire occurrence is higher than the probability threshold, the image acquisition range of the image acquisition device is expanded, so that the identification amount of the fire identification module is reduced, and the efficiency of fire identification is increased. The image acquisition module stores the field position range corresponding to the boundary in the image when each image acquisition device acquires the image within the maximum distance threshold range, so that the maximum range of the image acquired by each image acquisition device in the field can be obtained, and when the image within the maximum distance threshold range is found according to the fire position data in the fire identification report, the image acquisition device capable of acquiring the image at the fire position can be obtained, so that the image acquisition range can be expanded only for the image acquisition device, and the efficiency of fire identification and confirmation can be improved.
Further, the position comparison result is whether the fire position data is in the field position range corresponding to the image acquisition device;
the threshold value expansion module is used for expanding the image acquisition range of the image acquisition device when the fire disaster position data is in the corresponding field position range of the image acquisition device;
the fire identification module is also used for analyzing and identifying the images acquired by the image acquisition devices after the image acquisition range is expanded, and generating fire identification reports corresponding to the images;
and the fire confirmation module is used for generating a fire confirmation report according to the fire identification report corresponding to each image.
Has the advantages that: when the fire position data is in the field position range corresponding to the image acquisition device, the image acquisition range of the image acquisition device is expanded, namely the image acquisition range of the image acquisition device is expanded in a targeted manner, so that the situation that images of positions where fire possibly occurs cannot be acquired and identified is avoided, and the fire identification efficiency is improved.
Further, the fire identification module comprises an image cutting module and a flame smoke identification module:
the image cutting module is used for cutting the image acquired by the image acquisition device according to the fire position data to generate a cut image;
and the flame smoke identification module is used for analyzing and identifying the fire condition in the cut image and generating a fire identification report.
Has the advantages that: after the image acquisition range is enlarged, the area of the image is enlarged, and if the image with the enlarged area is subjected to fire identification directly, the area needing to be identified is very large, so that the image acquired by the image acquisition device is cut according to the fire position data, the area of the image is reduced, and the range of fire identification to be carried out is narrowed.
Further, the flame smoke identification module comprises a flame identification module, a smoke identification module, a relative position comparison module and a probability position generation module:
the flame identification module is used for carrying out flame identification on the image and acquiring position data of the flame;
the smoke identification module is used for carrying out smoke identification on the image and acquiring position data of smoke;
the relative position comparison module is used for comparing the relative positions of the flame and the smoke according to the position data of the flame and the position data of the smoke to generate relative position data;
and the probability position generating module is used for generating the fire occurrence probability and fire position data according to the relative position data.
Has the advantages that: the fire and the smoke are identified and the position data of the fire and the smoke are respectively obtained, and then the fire occurrence probability and the fire position data are judged according to the relative position data of the fire and the smoke, so that the fire condition false alarm caused by the type conditions of small-sized light flicker, water boiling of an electric kettle and the like is avoided.
The system further comprises a position marking module, a position marking module and a fire disaster marking module, wherein the position marking module is used for marking the position of the flame and the position of the smoke in an image according to the position data of the flame and the position data of the smoke to generate a fire disaster marking image; the fire confirmation report comprises a fire marking image and fire confirmation information for confirming whether a fire happens or not.
Has the advantages that: the positions of the flames and the positions of the smoke are marked, so that the positions of fire disasters can be conveniently checked.
Further, the labels include circling labels and arrow labels.
Has the advantages that: labeling is done in a number of ways.
And the fire condition confirming information is used for sending alarm information and a fire marking image to the cloud server when confirming that the fire happens.
Has the advantages that: when a fire disaster happens, a user can know the fire disaster condition in time through the alarm information, and the alarm information and the fire disaster marking image can be checked through the cloud server.
A machine vision-based power equipment potential fire alarm identification method is characterized by comprising the following steps: the method comprises the following steps:
an image acquisition step, wherein images within an initial distance threshold range are acquired;
a fire identification step, wherein the fire condition in the image is analyzed and identified, and a fire identification report is generated, wherein the fire identification report comprises the fire occurrence probability and fire position data;
an image acquisition range adjusting step of expanding an image acquisition range of an image acquisition device according to the fire identification report;
and a fire confirmation step of generating a fire confirmation report based on a fire recognition report generated by enlarging the image acquisition range of the image acquisition device.
Drawings
Fig. 1 is a logic block diagram of a power equipment potential fire alarm recognition system based on machine vision according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for identifying a potential fire alarm of an electrical device based on machine vision according to an embodiment of the present invention.
Detailed Description
The following is further detailed by way of specific embodiments:
example 1:
example 1 is substantially as shown in figure 1:
latent fire alarm identification system of power equipment based on machine vision acquires module, fire identification module, image acquisition range adjustment module and fire confirmation module including the image:
the image acquisition module comprises a plurality of image acquisition devices for respectively acquiring images within an initial distance threshold range, and in the embodiment, the image acquisition module comprises 4 image acquisition devices arranged in a transverse array manner; the image acquisition module stores an initial distance threshold value and a maximum distance threshold value, and also stores a field position range corresponding to a boundary in an image when each image acquisition device acquires the image within the maximum distance threshold value range;
the fire recognition module is used for analyzing and recognizing the fire condition in the image and generating a fire recognition report, wherein the fire recognition report comprises the fire occurrence probability and fire position data, and the fire position data refers to the fire occurrence point in the image and the position corresponding to the fire occurrence point in the field.
And the image acquisition range adjusting module is used for expanding the image acquisition range of the image acquisition device according to the fire identification report. The image acquisition range adjusting module comprises a probability analysis module, a position comparison module and a threshold value expansion module: the probability analysis module is used for comparing the fire occurrence probability with a probability threshold value to generate a probability comparison result; the position comparison module is used for comparing the position corresponding to the fire occurrence point in the field with the field position range corresponding to each image acquisition device when the fire occurrence probability is higher than a probability threshold value, and generating a position comparison result, wherein the position comparison result is whether the position corresponding to the fire occurrence point in the field is in the field position range corresponding to the image acquisition device or not; the threshold value expanding module is used for expanding the image acquiring range of the image acquiring device when the corresponding position of the fire occurrence point in the field is in the field position range corresponding to the image acquiring device.
The fire identification module is also used for analyzing and identifying the images acquired by the image acquisition devices after the image acquisition range is expanded, and generating fire identification reports corresponding to the images; the fire identification module comprises an image cutting module and a flame smoke identification module: the image cutting module is used for cutting the image acquired by the image acquisition device according to the fire occurrence point in the image to generate a cut image; and the flame smoke identification module is used for analyzing and identifying the fire condition in the cut image and generating a fire identification report. The flame smoke identification module comprises a flame identification module, a smoke identification module, a relative position comparison module and a probability position generation module: the flame identification module is used for carrying out flame identification on the image and acquiring position data of the flame; the smoke identification module is used for carrying out smoke identification on the image and acquiring position data of smoke; the relative position comparison module is used for comparing the relative positions of the flame and the smoke according to the position data of the flame and the position data of the smoke to generate relative position data, and specifically, because the positions of the flame and the smoke have relevance, namely, under a general condition, the position of the flame is under the smoke and the flame and the smoke have a connection point, in this embodiment, the relative positions of the flame and the smoke are compared, specifically, whether the flame is under the smoke and whether the flame and the smoke have the connection point are analyzed, and a corresponding result is generated; the probability position generating module is used for generating fire occurrence probability and fire position data according to the relative position data, and specifically, when the flame is below the smoke and the flame and the smoke have a connection point, the fire occurrence probability is generated to be 100%; when the flame is above the smoke and the flame is not connected with the smoke, generating a fire occurrence probability of 20%; the rest of the time, the probability of fire occurrence is 50%.
The fire confirmation module is used for generating a fire recognition report according to the fire recognition report corresponding to each image after the image acquisition range of the image acquisition device is expanded, and generating a fire confirmation report, wherein the fire confirmation report comprises fire confirmation information for confirming whether a fire happens or not. Specifically, the fire occurrence probability in the fire identification report corresponding to each image is averaged, fire confirmation information for confirming whether a fire occurs is generated according to the average, when the average is higher than 70%, the fire confirmation information for confirming that the fire occurs is generated, otherwise, the fire confirmation information for confirming that the fire does not occur is generated.
The fire disaster identification system further comprises a position marking module, wherein the position marking module is used for marking the position of the flame and the position of the smoke in the image according to the position data of the flame and the position data of the smoke to generate a fire disaster marking image, and the fire disaster confirmation report further comprises the fire disaster marking image. Specifically, in this embodiment, the flame is marked by an arrow, and the smoke is marked by a circle.
The fire disaster alarming system further comprises an alarming module used for sending alarming information and a fire disaster labeling image to the cloud server when the fire disaster confirming information confirms that a fire disaster occurs.
Example 2:
example 2 is substantially as shown in figure 2:
the method for identifying the potential fire alarm of the power equipment based on the machine vision comprises an image acquisition step, a fire identification step, an image acquisition range adjustment step and a fire confirmation step:
in the image acquisition step, a plurality of image acquisition devices are adopted to respectively acquire images within an initial distance threshold range, and in the embodiment, the image acquisition device comprises 4 image acquisition devices which are arranged in a transverse array manner;
and a fire recognition step of analyzing and recognizing the fire condition in the image and generating a fire recognition report, wherein the fire recognition report comprises the fire occurrence probability and fire position data, and the fire position data refers to the fire occurrence point in the image and the position corresponding to the fire occurrence point in the field.
And adjusting the image acquisition range, namely expanding the image acquisition range of the image acquisition device according to the fire identification report. The image acquisition range adjusting step comprises a probability analysis step, a position comparison step and a threshold value expanding step: the probability analysis step is to compare the fire occurrence probability with a probability threshold value to generate a probability comparison result; comparing the position corresponding to the fire occurrence point in the field with the field position range corresponding to each image acquisition device when the fire occurrence probability is higher than a probability threshold value, and generating a position comparison result, wherein the position comparison result is whether the position corresponding to the fire occurrence point in the field is in the field position range corresponding to the image acquisition device or not; and a threshold value expansion step of expanding an image acquisition range of the image acquisition device when a position corresponding to the fire occurrence point in the field is within a field position range corresponding to the image acquisition device.
The fire identification step is used for analyzing and identifying the images acquired by the image acquisition devices after the image acquisition range is expanded, and generating fire identification reports corresponding to the images; the fire identification step comprises an image cutting step and a flame smoke identification step: the image cutting step is to cut the image acquired by the image acquisition device according to the fire occurrence point in the image and generate a cut image; and the flame smoke identification step is used for analyzing and identifying the fire condition in the cut image and generating a fire identification report. The flame and smoke identification step comprises a flame identification step, a smoke identification step, a relative position comparison step and a probability position generation step: the flame identification step is to identify the flame of the image and acquire position data of the flame; the smoke identification step is to identify smoke of the image and acquire position data of the smoke; the relative position comparing step compares the relative positions of the flame and the smoke according to the position data of the flame and the position data of the smoke to generate relative position data, and specifically, since the positions of the flame and the smoke have relevance, that is, under a general condition, the position of the flame is below the smoke and the flame and the smoke should have a connection point, in this embodiment, the relative positions of the flame and the smoke are compared, specifically, whether the flame is below the smoke and whether the flame and the smoke have the connection point are analyzed, and a corresponding result is generated; the probability position generating step is to generate fire occurrence probability and fire position data according to the relative position data, and specifically, when the flame is below the smoke and has a connection point with the smoke, the fire occurrence probability is generated to be 100%; when the flame is above the smoke and the flame is not connected with the smoke, generating a fire occurrence probability of 20%; otherwise, the fire occurrence probability is 50 percent.
And a fire confirmation step of generating a fire recognition report including fire confirmation information for confirming whether a fire occurs, based on the fire recognition report generated based on the fire recognition report corresponding to each image after the image acquisition range of the image acquisition device is expanded. Specifically, the fire occurrence probability in the fire identification reports corresponding to the images is averaged, fire confirmation information for confirming whether a fire occurs is generated according to the average value, when the average value is higher than 70%, the fire confirmation information for confirming that the fire occurs is generated, otherwise, the fire confirmation information for confirming that the fire does not occur is generated.
And a position marking step, marking the position of the flame and the position of the smoke in the image according to the position data of the flame and the position data of the smoke to generate a fire marking image, wherein the fire confirmation report further comprises the fire marking image. Specifically, in this embodiment, the flame is marked by an arrow, and the smoke is marked by a circle.
The method further comprises an alarming step, and when the fire condition confirming information confirms that a fire disaster happens, alarming information and a fire disaster annotation image are sent to the cloud server.
The foregoing are merely exemplary embodiments of the present invention, and no attempt is made to show structural details of the invention in more detail than is necessary for the fundamental understanding of the art, the description taken with the drawings making apparent to those skilled in the art how the several forms of the invention may be embodied in practice with the teachings of the invention. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (5)
1. Latent fire alarm identification system of power equipment based on machine vision, its characterized in that: the fire disaster detection system comprises an image acquisition module, a fire disaster identification module, an image acquisition range adjustment module and a fire condition confirmation module:
the image acquisition module comprises a plurality of image acquisition devices and is used for respectively acquiring images within the range of the initial distance threshold;
the fire identification module is used for analyzing and identifying the fire condition in the image and generating a fire identification report, wherein the fire identification report comprises fire occurrence probability and fire position data;
the image acquisition range adjusting module is used for expanding the image acquisition range of the image acquisition device according to the fire identification report;
the fire confirmation module is used for generating a fire confirmation report according to a fire recognition report generated after the image acquisition range of the image acquisition device is expanded;
the image acquisition module stores an initial distance threshold value and a maximum distance threshold value, and also stores a field position range corresponding to a boundary in an image when each image acquisition device acquires the image within the maximum distance threshold value range;
the image acquisition range adjusting module comprises a probability analysis module, a position comparison module and a threshold value expansion module:
the probability analysis module is used for comparing the fire occurrence probability with a probability threshold value to generate a probability comparison result;
the position comparison module is used for comparing the fire position data with the field position range corresponding to each image acquisition device when the fire occurrence probability is higher than a probability threshold value to generate a position comparison result;
the threshold value expansion module is used for expanding the image acquisition range of the image acquisition device according to the position comparison result;
the position comparison result is whether the fire position data is in the corresponding field position range of the image acquisition device or not;
the threshold value expansion module is used for expanding the image acquisition range of the image acquisition device when the fire disaster position data is in the corresponding field position range of the image acquisition device;
the fire identification module is also used for analyzing and identifying the images acquired by the image acquisition devices after the image acquisition range is expanded, and generating fire identification reports corresponding to the images;
the fire confirmation module is used for generating a fire confirmation report according to the fire recognition report corresponding to each image;
the fire identification module comprises an image cutting module and a flame smoke identification module:
the image cutting module is used for cutting the image acquired by the image acquisition device according to the fire position data to generate a cut image;
the flame smoke identification module is used for analyzing and identifying the fire condition in the cut image and generating a fire identification report;
the flame smoke identification module comprises a flame identification module, a smoke identification module, a relative position comparison module and a probability position generation module:
the flame identification module is used for carrying out flame identification on the image and acquiring position data of the flame;
the smoke identification module is used for carrying out smoke identification on the image and acquiring position data of smoke;
the relative position comparison module is used for comparing the relative positions of the flame and the smoke according to the position data of the flame and the position data of the smoke to generate relative position data;
the probability position generating module is used for generating fire occurrence probability and fire position data according to the relative position data; when the flame is under the smoke and the flame is connected with the smoke, the fire occurrence probability is 100%; when the flame is above the smoke and the flame is not connected with the smoke, generating a fire occurrence probability of 20%; the fire occurrence probability is 50% in the rest of the time;
the fire confirmation report comprises fire confirmation information for confirming whether the fire happens or not, the fire occurrence probability in the fire recognition reports corresponding to the images is averaged, the fire confirmation information for confirming whether the fire happens or not is generated according to the average value, when the average value is higher than 70%, the fire confirmation information for confirming that the fire happens is generated, otherwise, the fire confirmation information for confirming that the fire does not happen is generated.
2. The machine-vision-based power equipment potential fire alarm identification system of claim 1, wherein: the fire disaster detection system also comprises a position marking module, a fire disaster detection module and a fire disaster detection module, wherein the position marking module is used for marking the position of the fire disaster and the position of the smoke in an image according to the position data of the fire disaster and the position data of the smoke to generate a fire disaster marking image; the fire confirmation report comprises a fire marking image and fire confirmation information for confirming whether a fire happens or not.
3. The machine-vision-based power equipment potential fire alarm identification system of claim 2, wherein: the labels include circling labels and arrow labels.
4. The machine-vision-based power equipment potential fire alarm identification system of claim 2, wherein: the fire disaster alarming system further comprises an alarming module used for sending alarming information and a fire disaster labeling image to the cloud server when the fire disaster confirming information confirms that a fire disaster occurs.
5. A machine vision-based power equipment potential fire alarm identification method is characterized by comprising the following steps: a machine vision based power equipment potential fire identification system using any of the above claims 1-4, comprising the steps of:
an image acquisition step, namely acquiring an image within an initial distance threshold range;
a fire identification step, wherein the fire condition in the image is analyzed and identified, and a fire identification report is generated, wherein the fire identification report comprises the fire occurrence probability and fire position data;
an image acquisition range adjusting step of expanding an image acquisition range of an image acquisition device according to the fire identification report;
a fire confirmation step of generating a fire confirmation report based on a fire recognition report generated after an image acquisition range of the image acquisition device is expanded;
the fire disaster identification step comprises an image cutting step and a flame smoke identification step: the image cutting step is to cut the image acquired by the image acquisition device according to the fire occurrence point in the image and generate a cut image; the flame smoke identification step is used for analyzing and identifying the fire condition in the cut image and generating a fire identification report;
the flame and smoke identification step comprises a flame identification step, a smoke identification step, a relative position comparison step and a probability position generation step: the flame identification step is to identify the flame of the image and acquire position data of the flame; the smoke identification step is to identify smoke of the image and acquire position data of the smoke; comparing the relative positions of the flame and the smoke according to the position data of the flame and the position data of the smoke to generate relative position data; the probability position generating step of generating fire occurrence probability and fire position data based on the relative position data; when the flame is under the smoke and the flame is connected with the smoke, the fire occurrence probability is 100%; when the flame is above the smoke and the flame and the smoke have no connection point, generating a fire occurrence probability of 20%; the rest of the time, the probability of fire occurrence is 50%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110864710.9A CN113409536B (en) | 2021-07-29 | 2021-07-29 | Power equipment potential fire alarm recognition system and method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110864710.9A CN113409536B (en) | 2021-07-29 | 2021-07-29 | Power equipment potential fire alarm recognition system and method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113409536A CN113409536A (en) | 2021-09-17 |
| CN113409536B true CN113409536B (en) | 2022-11-29 |
Family
ID=77687982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110864710.9A Active CN113409536B (en) | 2021-07-29 | 2021-07-29 | Power equipment potential fire alarm recognition system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409536B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004304249A (en) * | 2003-03-28 | 2004-10-28 | Nohmi Bosai Ltd | Fire detecting apparatus and disaster prevention system |
| GB0906858D0 (en) * | 2008-04-25 | 2009-06-03 | Bosch Gmbh Robert | Detection device and method of detecting fires along a monitoring section |
| CN101527073A (en) * | 2009-02-17 | 2009-09-09 | 丁国锋 | Fire detection system and method thereof |
| KR101294840B1 (en) * | 2013-01-25 | 2013-08-16 | 주식회사 포딕스시스템 | Controlling system of cctv |
| CN104811654A (en) * | 2014-01-26 | 2015-07-29 | 杭州华为企业通信技术有限公司 | Internet of things-based monitoring method, device and system |
| CN105931409A (en) * | 2016-05-30 | 2016-09-07 | 重庆大学 | Infrared and visible light camera linkage-based forest fire monitoring method |
| CN107871178A (en) * | 2017-06-12 | 2018-04-03 | 中海油信息科技有限公司 | Evacuate path planning and command system |
| CN108369764A (en) * | 2015-10-16 | 2018-08-03 | 霍尼韦尔国际公司 | Method and system for the visual field for adjusting flame detector |
| CN110652685A (en) * | 2019-10-17 | 2020-01-07 | 广东德臻消防机电工程有限公司 | Indoor fire extinguishing method and system |
| CN212933695U (en) * | 2020-08-17 | 2021-04-09 | 华东交通大学 | Accurate discriminating gear of family's conflagration |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102004056958B3 (en) * | 2004-11-22 | 2006-08-10 | IQ wireless GmbH, Entwicklungsgesellschaft für Systeme und Technologien der Telekommunikation | Surveillance of territories for detection of forest and wildfires |
| EP2178056B1 (en) * | 2008-10-14 | 2012-02-01 | Nohmi Bosai Ltd. | Smoke detecting apparatus |
| CN101587622B (en) * | 2009-06-18 | 2012-09-05 | 李秋华 | Forest rocket detecting and identifying method and apparatus based on video image intelligent analysis |
| DE102012213125A1 (en) * | 2012-07-26 | 2014-01-30 | Robert Bosch Gmbh | Fire control system |
| DE102014002599B3 (en) * | 2014-02-24 | 2015-08-20 | Mobotix Ag | CAMERA ARRANGEMENT |
| CN104410830A (en) * | 2014-12-01 | 2015-03-11 | 天津艾思科尔科技有限公司 | Device based on video smoke detection, and method based on video smoke detection |
| US10687022B2 (en) * | 2014-12-05 | 2020-06-16 | Avigilon Fortress Corporation | Systems and methods for automated visual surveillance |
| SG10201501222XA (en) * | 2015-02-17 | 2016-09-29 | Nec Asia Pacific Pte Ltd | System for monitoring event related data |
| CN106600888B (en) * | 2016-12-30 | 2020-10-30 | 陕西烽火实业有限公司 | Automatic forest fire detection method and system |
| US10331960B2 (en) * | 2017-05-10 | 2019-06-25 | Fotonation Limited | Methods for detecting, identifying and displaying object information with a multi-camera vision system |
| WO2018222052A1 (en) * | 2017-05-31 | 2018-12-06 | Travision As | Control and monitoring devices and system for shooting range |
| CN107527466A (en) * | 2017-07-31 | 2017-12-29 | 努比亚技术有限公司 | A kind of fire alarm method, terminal and computer-readable recording medium |
-
2021
- 2021-07-29 CN CN202110864710.9A patent/CN113409536B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004304249A (en) * | 2003-03-28 | 2004-10-28 | Nohmi Bosai Ltd | Fire detecting apparatus and disaster prevention system |
| GB0906858D0 (en) * | 2008-04-25 | 2009-06-03 | Bosch Gmbh Robert | Detection device and method of detecting fires along a monitoring section |
| CN101527073A (en) * | 2009-02-17 | 2009-09-09 | 丁国锋 | Fire detection system and method thereof |
| KR101294840B1 (en) * | 2013-01-25 | 2013-08-16 | 주식회사 포딕스시스템 | Controlling system of cctv |
| CN104811654A (en) * | 2014-01-26 | 2015-07-29 | 杭州华为企业通信技术有限公司 | Internet of things-based monitoring method, device and system |
| CN108369764A (en) * | 2015-10-16 | 2018-08-03 | 霍尼韦尔国际公司 | Method and system for the visual field for adjusting flame detector |
| CN105931409A (en) * | 2016-05-30 | 2016-09-07 | 重庆大学 | Infrared and visible light camera linkage-based forest fire monitoring method |
| CN107871178A (en) * | 2017-06-12 | 2018-04-03 | 中海油信息科技有限公司 | Evacuate path planning and command system |
| CN110652685A (en) * | 2019-10-17 | 2020-01-07 | 广东德臻消防机电工程有限公司 | Indoor fire extinguishing method and system |
| CN212933695U (en) * | 2020-08-17 | 2021-04-09 | 华东交通大学 | Accurate discriminating gear of family's conflagration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113409536A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108389359B (en) | Deep learning-based urban fire alarm method | |
| CN106251568A (en) | A kind of fire alarm safety-protection system based on ultraviolet and image detecting technique and method | |
| CN113450551A (en) | Automatic fire alarm equipment management system | |
| CN112785809B (en) | Fire re-ignition prediction method and system based on AI image recognition | |
| CN111582235A (en) | Alarm method, system and equipment for monitoring abnormal events in station in real time | |
| CN105279878A (en) | Wireless video anti-burglary automatic alarm system and method thereof | |
| CN102663032A (en) | Fiber grating fence invasion event mode recognition method | |
| KR20210097500A (en) | Apparatus for Monitoring Fire And System having the same | |
| CN116778406A (en) | Fire monitoring method and system based on domestic CPU and OS under multi-image fusion | |
| CN110222216B (en) | Multifunctional intelligent defense system | |
| CN113409536B (en) | Power equipment potential fire alarm recognition system and method based on machine vision | |
| CN110428579A (en) | Indoor Monitoring System, method and device based on image recognition | |
| CN116307740B (en) | Fire point analysis method, system, equipment and medium based on digital twin city | |
| Mwedzi et al. | Machine learning applications for fire detection in a residential building | |
| CN114723972A (en) | Safety management and control method and safety management and control system based on data and image comparison | |
| CN112820063A (en) | Fire control early warning system based on image data processing | |
| CN206058456U (en) | It is a kind of for fire identification can monitor in real time image processing system | |
| CN115083096A (en) | Fire early warning and positioning system based on multi-sensor information fusion | |
| CN116545377A (en) | Phase-locked technology-based photovoltaic module monitoring method | |
| CN116311729A (en) | AI-based power grid infrastructure site safety management system | |
| CN111882800B (en) | Fire-fighting early warning method and system based on multi-dimensional data linkage | |
| KR20230107035A (en) | Image recognition-based fire response system and method for power facility | |
| CN112802297A (en) | Method, server, system and storage medium for forest fire identification by using computer program | |
| CN116170104A (en) | System and method for detecting and calibrating time abnormality of video and image acquisition equipment in real time | |
| CN117671608B (en) | Method and system for starting fire-fighting operation of battery energy storage system and computing equipment |
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 |