CN113486942A - Repeated fire alarm determination method and device, electronic equipment and storage medium - Google Patents
Repeated fire alarm determination method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113486942A CN113486942A CN202110744006.XA CN202110744006A CN113486942A CN 113486942 A CN113486942 A CN 113486942A CN 202110744006 A CN202110744006 A CN 202110744006A CN 113486942 A CN113486942 A CN 113486942A
- Authority
- CN
- China
- Prior art keywords
- fire
- identified
- characteristic diagram
- image
- scene
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000010586 diagram Methods 0.000 claims abstract description 186
- 239000013598 vector Substances 0.000 claims description 22
- 230000003252 repetitive effect Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000003502 gasoline Substances 0.000 description 1
- 239000003915 liquefied petroleum gas Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a repeated fire alarm determination method, a repeated fire alarm determination device, electronic equipment and a computer readable storage medium, wherein the method comprises the steps of obtaining a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified; respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified; and acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeat alarm fire according to the matching degree. The embodiment of the invention provides a repeated fire alarm determination method, which improves the accuracy of repeated fire alarm determination.
Description
Technical Field
The invention relates to the technical field of repeated alarm determination, in particular to a repeated fire alarm determination method, a repeated fire alarm determination device, electronic equipment and a computer-readable storage medium.
Background
The same alarm condition is reported repeatedly in the fire fighting alarm receiving and processing work, and the existing processing of the repeated alarm condition generally adopts alarm calls and manual judgment, so that the efficiency is lower. In the prior art, a method, a device and equipment for judging whether the alarm condition is repeated or not are calculated according to the similarity of current alarm information and historical alarm records, and the analysis of the existing repeated alarm condition judgment method shows that the alarm condition judgment is basically carried out according to the analysis of telephone numbers, voiceprint information and text information, the voiceprint information and the text information are subject to spoken factors, the language description difference is large and the like, and the judgment accuracy rate is possibly lower.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus, an electronic device and a computer readable storage medium for repetitive fire alarm determination, which are used to solve the problem of low accuracy of repetitive fire alarm determination in the prior art.
In order to solve the above problems, the present invention provides a repetitive fire alarm determination method, including:
acquiring a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
and acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeat alarm fire according to the matching degree.
Further, acquiring similarity coefficients of a fire characteristic diagram to be identified and a scene characteristic diagram to be identified specifically comprises:
and respectively acquiring the fire characteristic diagram to be identified and the shape context characteristic based on the corner points of the scene characteristic diagram to be identified by utilizing a Euclidean distance algorithm, and respectively taking the fire characteristic diagram to be identified and the shape context characteristic based on the corner points of the scene characteristic diagram to be identified as the similarity coefficient of the fire characteristic diagram to be identified and the scene characteristic diagram to be identified.
Further, acquiring similarity coefficients of a fire characteristic diagram to be identified and a scene characteristic diagram to be identified specifically comprises:
respectively acquiring the fire characteristic image to be identified and the shape context characteristic of the scene characteristic image to be identified based on the angular points by using a Euclidean distance algorithm, and respectively acquiring SIFT vector similarity coefficients of the fire characteristic image to be identified and the scene characteristic image to be identified by using a cosine similarity algorithm;
carrying out weighted average on the shape context features based on the angular points and the SIFT vector similarity coefficients of the fire feature images to be identified to obtain the similarity coefficients of the fire feature images to be identified;
and carrying out weighted average on the shape context features based on the corners of the scene feature map to be identified and the SIFT vector similarity coefficients to obtain the similarity coefficients of the scene feature map to be identified.
Further, the method for acquiring the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified respectively specifically comprises the following steps:
and respectively acquiring SIFT vector similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified by utilizing a cosine similarity algorithm, and taking the corresponding SIFT vector similarity coefficients as the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified.
Further, according to the similarity coefficient of the fire characteristic diagram to be recognized, the scene characteristic diagram to be recognized and the fire source characteristic diagram to be recognized, the matching degree of the fire image to be recognized and the historical fire image is obtained, and the method specifically comprises the following steps:
and carrying out weighted average on the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified to obtain an average similarity coefficient of the fire image to be identified, and acquiring the matching degree of the fire image to be identified and the historical fire image according to the average similarity coefficient of the fire image to be identified.
Further, the method for acquiring the fire image to be identified includes the following steps:
carrying out weighted average on the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified by utilizing a weighted average formula to obtain an average similarity coefficient of the fire image to be identified, wherein the weighted average formula is that d ═ α dsift+β*dsc+(1-α-β)dlpqWherein d is the average similarity coefficient of the fire image to be identified, both alpha and beta are the similarity coefficients, dsift、dsc、dlpqThe similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified are respectively.
Further, whether the fire to be identified is a repeat alarm fire is judged according to the matching degree, and the method specifically comprises the following steps: and if the matching degree exceeds a set threshold value, judging that the fire to be identified is a repeat alarm fire, otherwise, judging that the fire to be identified is a non-repeat alarm fire.
The invention also provides a repeated fire alarm judging device, which comprises an image acquisition module, a similarity coefficient acquisition module and a repeated fire alarm judging module;
the image acquisition module is used for acquiring a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
the similarity coefficient acquisition module is used for respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
the repeated fire alarm judging module is used for acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeated alarm fire according to the matching degree.
The invention also provides an electronic device, which comprises a memory and a processor, wherein the memory is stored with a computer program, and when the computer program is executed by the processor, the repeated fire alarm determination method according to any technical scheme is realized.
The present invention also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the repetitive fire alarm determination method according to any of the above-mentioned aspects.
The beneficial effects of adopting the above embodiment are: acquiring a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified; respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified; acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeat alarm fire according to the matching degree; the accuracy of repeated fire alarm determination is improved.
Drawings
FIG. 1 is a schematic flow chart illustrating a repetitive fire alarm determination method according to an embodiment of the present invention;
fig. 2 is a block diagram of a repetitive fire alarm determination device according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
A specific embodiment of the present invention discloses a repetitive fire alarm determination method, a flow diagram of which is shown in fig. 1, the repetitive fire alarm determination method including:
s1, acquiring a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
s2, respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
and step S3, acquiring the matching degree of the fire image to be identified and the historical fire image according to the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the similarity coefficient of the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeat alarm fire according to the matching degree.
It should be noted that, at present, the fire alarm modes are diversified, and support personnel report on-site pictures or videos through a platform, a mobile phone and the like; the fire characteristics comprise open fire, smoke and the like, the scene characteristics comprise the environment where the fire happens, such as residential buildings, public buildings, industrial buildings, roads and the like, and the fire source characteristics comprise wood, cloth, gasoline, liquefied petroleum gas, metal, charged objects and the like; and similarly, the historical fire alarm image in the alarm record can be processed in the same way to obtain a historical fire characteristic map, a historical scene characteristic map and a historical fire source characteristic map. In specific implementation, graying and filtering processing can be respectively carried out on the fire image to be identified and the historical fire image. The similarity coefficient of the to-be-identified fire characteristic diagram, the to-be-identified scene characteristic diagram and the to-be-identified fire source characteristic diagram refers to that the to-be-identified fire characteristic diagram, the to-be-identified scene characteristic diagram and the to-be-identified fire source characteristic diagram are respectively compared with the historical fire characteristic diagram, the historical scene characteristic diagram and the historical fire source characteristic diagram.
As a preferred embodiment, the obtaining of the similarity coefficient of the fire characteristic diagram to be identified and the scene characteristic diagram to be identified specifically includes:
and respectively acquiring the fire characteristic diagram to be identified and the shape context characteristic based on the corner points of the scene characteristic diagram to be identified by utilizing a Euclidean distance algorithm, and respectively taking the fire characteristic diagram to be identified and the shape context characteristic based on the corner points of the scene characteristic diagram to be identified as the similarity coefficient of the fire characteristic diagram to be identified and the scene characteristic diagram to be identified.
In one embodiment, the shape context feature based on the corner point is obtained by using a Euclidean distance algorithm, wherein the formula of the Euclidean distance algorithm is
aiThe ith bit, b, in the shape context feature description of any key point for historical fire images (including fire feature maps and scene feature maps)iThe method is characterized in that the ith position in the shape context feature description of any key point in a fire image to be identified (including a fire feature map and a scene feature map) is defined, and n is the number of the key points in the shape context feature description in the fire image to be identified.
As a preferred embodiment, the obtaining of the similarity coefficient of the fire characteristic diagram to be identified and the scene characteristic diagram to be identified specifically includes:
respectively acquiring the fire characteristic image to be identified and the shape context characteristic of the scene characteristic image to be identified based on the angular points by using a Euclidean distance algorithm, and respectively acquiring SIFT vector similarity coefficients of the fire characteristic image to be identified and the scene characteristic image to be identified by using a cosine similarity algorithm;
carrying out weighted average on the shape context features based on the angular points and the SIFT vector similarity coefficients of the fire feature images to be identified to obtain the similarity coefficients of the fire feature images to be identified;
and carrying out weighted average on the shape context features based on the corners of the scene feature map to be identified and the SIFT vector similarity coefficients to obtain the similarity coefficients of the scene feature map to be identified.
In a specific embodiment, the SIFT vector similarity coefficients of the fire feature map to be identified and the scene feature map to be identified are respectively obtained by using a cosine similarity algorithm, and the formula of the cosine similarity algorithm is as follows
D issIs the SIFT vector similarity coefficient, and the similarity coefficient,
are respectively historyThe SIFT vectors of the fire image and the fire image to be identified; it should be noted that before the SIFT vector similarity coefficient is calculated, normalization processing can be performed on the SIFT vector; the normalization processing step comprises the steps of drawing a circle by taking the key point as the center of the circle and any radius, and taking the main direction of the key point as the direction of an abscissa axis; and (3) taking an m multiplied by m neighborhood around the key point, dividing the neighborhood into sub-neighborhoods, performing calculation statistics on eight directional gradient histograms in each sub-neighborhood to form a certain number of SIFT feature vectors, and normalizing the obtained SIFT feature vectors.
As a preferred embodiment, the method for obtaining similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified, and a fire source characteristic diagram to be identified respectively includes:
and respectively acquiring SIFT vector similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified by utilizing a cosine similarity algorithm, and taking the corresponding SIFT vector similarity coefficients as the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified.
As a preferred embodiment, the method for obtaining the matching degree between the fire image to be identified and the historical fire image according to the similarity coefficient between the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified specifically includes:
and carrying out weighted average on the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified to obtain an average similarity coefficient of the fire image to be identified, and acquiring the matching degree of the fire image to be identified and the historical fire image according to the average similarity coefficient of the fire image to be identified.
As a preferred embodiment, the method for obtaining the average similarity coefficient of the fire image to be identified by performing weighted average on the similarity coefficients of the fire feature map to be identified, the scene feature map to be identified and the fire source feature map to be identified specifically includes:
weighting the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified by using a weighted average formulaAveraging to obtain an average similarity coefficient of the fire disaster image to be identified, wherein the weighted average formula is that d is alpha dsift+β*dsc+(1-α-β)dlpqWherein d is the average similarity coefficient of the fire image to be identified, both alpha and beta are the similarity coefficients, dsift、dsc、dlpqThe similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified are respectively.
In a specific embodiment, according to the priorities of the fire characteristic diagram, the scene characteristic diagram and the fire source characteristic diagram, the corresponding three similarity coefficients are weighted and averaged, and the matching degree between the fire image to be identified and the historical fire image, namely d, is calculatedsiftGreater than dsc，dscGreater than dlpq(ii) a Mismatching in the matching can be eliminated through a PROSAC algorithm, and the matching precision is improved.
As a preferred embodiment, determining whether the fire to be identified is a repeat alarm fire according to the matching degree specifically includes: and if the matching degree exceeds a set threshold value, judging that the fire to be identified is a repeat alarm fire, otherwise, judging that the fire to be identified is a non-repeat alarm fire.
The embodiment of the invention provides a repeated fire alarm determination device, which has a structural block diagram, as shown in fig. 2, and comprises an image acquisition module 1, a similarity coefficient acquisition module 2 and a repeated fire alarm determination module 3;
the image acquisition module 1 is used for acquiring a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
the similarity coefficient acquisition module 2 is used for respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
and the repeated fire alarm determination module 3 is used for acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and determining whether the fire to be identified is a repeated alarm fire according to the matching degree.
An embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the method for determining a repetitive fire alarm according to any of the above embodiments is implemented.
An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements a repetitive fire alarm determination method as described in any of the above embodiments.
The invention discloses a repeated fire alarm determination method, a repeated fire alarm determination device, electronic equipment and a computer readable storage medium.A fire image to be identified is obtained and comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified; respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified; acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeat alarm fire according to the matching degree; the accuracy of repeated fire alarm determination is improved.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A repetitive fire alarm determination method, comprising:
acquiring a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
and acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeat alarm fire according to the matching degree.
2. The repetitive fire alarm determination method according to claim 1, wherein the obtaining of the similarity coefficient between the fire characteristic diagram to be recognized and the scene characteristic diagram to be recognized specifically comprises:
and respectively acquiring the fire characteristic diagram to be identified and the shape context characteristic based on the corner points of the scene characteristic diagram to be identified by utilizing a Euclidean distance algorithm, and respectively taking the fire characteristic diagram to be identified and the shape context characteristic based on the corner points of the scene characteristic diagram to be identified as the similarity coefficient of the fire characteristic diagram to be identified and the scene characteristic diagram to be identified.
3. The repetitive fire alarm determination method according to claim 1, wherein the obtaining of the similarity coefficient between the fire characteristic diagram to be recognized and the scene characteristic diagram to be recognized specifically comprises:
respectively acquiring the fire characteristic image to be identified and the shape context characteristic of the scene characteristic image to be identified based on the angular points by using a Euclidean distance algorithm, and respectively acquiring SIFT vector similarity coefficients of the fire characteristic image to be identified and the scene characteristic image to be identified by using a cosine similarity algorithm;
carrying out weighted average on the shape context features based on the angular points and the SIFT vector similarity coefficients of the fire feature images to be identified to obtain the similarity coefficients of the fire feature images to be identified;
and carrying out weighted average on the shape context features based on the corners of the scene feature map to be identified and the SIFT vector similarity coefficients to obtain the similarity coefficients of the scene feature map to be identified.
4. The repetitive fire alarm determination method according to claim 1, wherein the obtaining of the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified, and the fire source characteristic diagram to be identified respectively specifically comprises:
and respectively acquiring SIFT vector similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified by utilizing a cosine similarity algorithm, and taking the corresponding SIFT vector similarity coefficients as the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified.
5. The repetitive fire alarm determination method according to claim 1, wherein the obtaining of the matching degree between the fire image to be recognized and the historical fire image according to the similarity coefficient between the fire feature map to be recognized, the scene feature map to be recognized, and the fire source feature map to be recognized specifically comprises:
and carrying out weighted average on the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified to obtain an average similarity coefficient of the fire image to be identified, and acquiring the matching degree of the fire image to be identified and the historical fire image according to the average similarity coefficient of the fire image to be identified.
6. The repetitive fire alarm determination method according to claim 1, wherein the weighted average of the similarity coefficients of the fire feature map to be recognized, the scene feature map to be recognized, and the fire source feature map to be recognized is performed to obtain an average similarity coefficient of the fire image to be recognized, and specifically includes:
carrying out weighted average on the similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified by utilizing a weighted average formula to obtain an average similarity coefficient of the fire image to be identified, wherein the weighted average formula is that d ═ α dsift+β*dsc+(1-α-β)dlpqWherein d is the average similarity coefficient of the fire image to be identified, both alpha and beta are the similarity coefficients, dsift、dsc、dlpqThe similarity coefficients of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified are respectively.
7. The repetitive fire alarm determination method according to claim 1, wherein determining whether the fire to be identified is a repetitive alarm fire according to the matching degree specifically includes: and if the matching degree exceeds a set threshold value, judging that the fire to be identified is a repeat alarm fire, otherwise, judging that the fire to be identified is a non-repeat alarm fire.
8. A repeated fire alarm determination device is characterized by comprising an image acquisition module, a similarity coefficient acquisition module and a repeated fire alarm determination module;
the image acquisition module is used for acquiring a fire image to be identified, wherein the fire image to be identified comprises a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
the similarity coefficient acquisition module is used for respectively acquiring similarity coefficients of a fire characteristic diagram to be identified, a scene characteristic diagram to be identified and a fire source characteristic diagram to be identified;
the repeated fire alarm judging module is used for acquiring the matching degree of the fire image to be identified and the historical fire image according to the similarity coefficient of the fire characteristic diagram to be identified, the scene characteristic diagram to be identified and the fire source characteristic diagram to be identified, and judging whether the fire to be identified is a repeated alarm fire according to the matching degree.
9. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program that, when executed by the processor, implements the repetitive fire alarm determination method of any of claims 1-7.
10. A computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing a repetitive fire alarm determination method as claimed in any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110744006.XA CN113486942A (en) | 2021-06-30 | 2021-06-30 | Repeated fire alarm determination method and device, electronic equipment and storage medium |
| PCT/CN2022/093306 WO2023273665A1 (en) | 2021-06-30 | 2022-05-17 | Repeated fire alarm determining method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110744006.XA CN113486942A (en) | 2021-06-30 | 2021-06-30 | Repeated fire alarm determination method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113486942A true CN113486942A (en) | 2021-10-08 |
Family
ID=77937445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110744006.XA Pending CN113486942A (en) | 2021-06-30 | 2021-06-30 | Repeated fire alarm determination method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113486942A (en) |
| WO (1) | WO2023273665A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023273665A1 (en) * | 2021-06-30 | 2023-01-05 | 武汉理工光科股份有限公司 | Repeated fire alarm determining method and apparatus, electronic device, and storage medium |
| WO2024045229A1 (en) * | 2022-08-29 | 2024-03-07 | 武汉理工光科股份有限公司 | Early-warning blocking method and apparatus for special scenario, and electronic device and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116168345B (en) * | 2023-04-21 | 2023-07-21 | 深圳开鸿数字产业发展有限公司 | Fire detection method and related equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018079400A1 (en) * | 2016-10-24 | 2018-05-03 | ホーチキ株式会社 | Fire monitoring system |
| CN108875561A (en) * | 2018-04-27 | 2018-11-23 | 山东信通电子股份有限公司 | A kind of hidden danger repetition method of discrimination of transmission line of electricity monitoring hidden danger early warning image |
| CN109727428A (en) * | 2019-01-10 | 2019-05-07 | 成都国铁电气设备有限公司 | Repetition of alarms suppressing method based on deep learning |
| CN109754399A (en) * | 2019-01-17 | 2019-05-14 | 成都国铁电气设备有限公司 | A kind of railway power supply detection repetition of alarms analysis method based on image segmentation |
| CN110044486A (en) * | 2019-03-11 | 2019-07-23 | 武汉高德智感科技有限公司 | Method, apparatus, the equipment of repetition of alarms are avoided for human body inspection and quarantine system |
| CN111178244A (en) * | 2019-12-27 | 2020-05-19 | 北京首钢自动化信息技术有限公司 | Method for identifying abnormal production scene |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679189B (en) * | 2012-09-14 | 2017-02-01 | 华为技术有限公司 | Method and device for recognizing scene |
| CN110188217A (en) * | 2019-05-29 | 2019-08-30 | 京东方科技集团股份有限公司 | Image duplicate checking method, apparatus, equipment and computer-readable storage media |
| CN110781917B (en) * | 2019-09-18 | 2021-03-02 | 北京三快在线科技有限公司 | Method and device for detecting repeated image, electronic equipment and readable storage medium |
| CN111899448A (en) * | 2020-03-26 | 2020-11-06 | 中国铁建电气化局集团第二工程有限公司 | Method and system for filtering intelligent inspection information of traction substation |
| CN113486942A (en) * | 2021-06-30 | 2021-10-08 | 武汉理工光科股份有限公司 | Repeated fire alarm determination method and device, electronic equipment and storage medium |
-
2021
- 2021-06-30 CN CN202110744006.XA patent/CN113486942A/en active Pending
-
2022
- 2022-05-17 WO PCT/CN2022/093306 patent/WO2023273665A1/en unknown
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018079400A1 (en) * | 2016-10-24 | 2018-05-03 | ホーチキ株式会社 | Fire monitoring system |
| CN108875561A (en) * | 2018-04-27 | 2018-11-23 | 山东信通电子股份有限公司 | A kind of hidden danger repetition method of discrimination of transmission line of electricity monitoring hidden danger early warning image |
| CN109727428A (en) * | 2019-01-10 | 2019-05-07 | 成都国铁电气设备有限公司 | Repetition of alarms suppressing method based on deep learning |
| CN109754399A (en) * | 2019-01-17 | 2019-05-14 | 成都国铁电气设备有限公司 | A kind of railway power supply detection repetition of alarms analysis method based on image segmentation |
| CN110044486A (en) * | 2019-03-11 | 2019-07-23 | 武汉高德智感科技有限公司 | Method, apparatus, the equipment of repetition of alarms are avoided for human body inspection and quarantine system |
| CN111178244A (en) * | 2019-12-27 | 2020-05-19 | 北京首钢自动化信息技术有限公司 | Method for identifying abnormal production scene |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023273665A1 (en) * | 2021-06-30 | 2023-01-05 | 武汉理工光科股份有限公司 | Repeated fire alarm determining method and apparatus, electronic device, and storage medium |
| WO2024045229A1 (en) * | 2022-08-29 | 2024-03-07 | 武汉理工光科股份有限公司 | Early-warning blocking method and apparatus for special scenario, and electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023273665A1 (en) | 2023-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113486942A (en) | Repeated fire alarm determination method and device, electronic equipment and storage medium | |
| CN111222466B (en) | Remote sensing image landslide automatic detection method based on three-dimensional space-channel attention mechanism | |
| US6246790B1 (en) | Image indexing using color correlograms | |
| US6959099B2 (en) | Method and apparatus for automatic face blurring | |
| US20140343931A1 (en) | Robust signatures derived from local nonlinear filters | |
| US20080144891A1 (en) | Method and apparatus for calculating similarity of face image, method and apparatus for retrieving face image, and method of synthesizing face image | |
| JP5500024B2 (en) | Image recognition method, apparatus, and program | |
| CN106851087A (en) | Information processor and information processing method | |
| CN113140005B (en) | Target object positioning method, device, equipment and storage medium | |
| CN104715753A (en) | Data processing method and electronic device | |
| CN112802108B (en) | Target object positioning method, target object positioning device, electronic equipment and readable storage medium | |
| CN111507138A (en) | Image recognition method and device, computer equipment and storage medium | |
| Matthews et al. | Lipreading using shape, shading and scale | |
| EP1161098B1 (en) | Signal detection method and apparatus | |
| CN116665101B (en) | Method for extracting key frames of monitoring video based on contourlet transformation | |
| CN116364064A (en) | Audio splicing method, electronic equipment and storage medium | |
| CN113721240B (en) | Target association method, device, electronic equipment and storage medium | |
| CN112926542B (en) | Sex detection method and device, electronic equipment and storage medium | |
| JP3408800B2 (en) | Signal detection method and apparatus, program therefor, and recording medium | |
| CN115457454A (en) | Target detection method, apparatus and storage medium | |
| CN111522988B (en) | Image positioning model obtaining method and related device | |
| CN109118424B (en) | Image processing memory management method and management system for target detection | |
| CN112926552A (en) | Remote sensing image vehicle target recognition model and method based on deep neural network | |
| CN114417946A (en) | Target detection method and device | |
| CN112418120B (en) | Crowd detection method based on peak confidence map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211008 |