CN109101882A - A kind of image-recognizing method and system of fire source - Google Patents
A kind of image-recognizing method and system of fire source Download PDFInfo
- Publication number
- CN109101882A CN109101882A CN201810744479.8A CN201810744479A CN109101882A CN 109101882 A CN109101882 A CN 109101882A CN 201810744479 A CN201810744479 A CN 201810744479A CN 109101882 A CN109101882 A CN 109101882A
- Authority
- CN
- China
- Prior art keywords
- images
- flame
- thermal infrared
- fire source
- visible images
- 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 41
- 238000012545 processing Methods 0.000 claims description 4
- 235000009781 Myrtillocactus geometrizans Nutrition 0.000 claims description 3
- 240000009125 Myrtillocactus geometrizans Species 0.000 claims description 3
- 244000171022 Peltophorum pterocarpum Species 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000011946 reduction process Methods 0.000 claims description 3
- 210000004218 nerve net Anatomy 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 239000000779 smoke Substances 0.000 description 2
- 244000249914 Hemigraphis reptans Species 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003303 reheating Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- 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
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention discloses a kind of image-recognizing methods of fire source, including step S11, obtain the visible images in area to be measured, pre-process to the visible images；Step S21 identifies the target object in the pretreated visible images, to judge whether there is doubtful fire source, when, there are when doubtful fire source, entering step S31 in the visible images；Step S31 obtains the targeted object region of doubtful fire source to there are the regions of doubtful fire source to demarcate in the visible images；Step S41, obtains the thermal infrared images in area to be measured, and obtains the thermal characteristics value of the targeted object region；The thermal characteristics value is compared step S51 with given threshold, and when the thermal characteristics value is more than or equal to given threshold, there are fire sources for judgement.The accurate judgement of the achievable fire of this method.
Description
Technical field
The invention belongs to field of image recognition, and in particular to a kind of image-recognizing method and system of fire source.
Background technique
With economy and industrial development, fire identification technology is rapidly developed, and fire source identification currently on the market is main
Major technique is identified by conventional fire, and such as temperature-sensitive, sense cigarette and vision technique, currently employed image identification system carries out fire
Identification is applied.
However, current office building, market, enterprise, warehouse and forest etc. are higher and higher to the reliability requirement of fire identification,
And current fire identification technology there are accuracy it is lower, rate of false alarm is high and at high cost the problems such as.It is urgent to provide one kind to be based at present
The fire source recognition methods of the high precision of image recognition technology.
Summary of the invention
The technical problem to be solved by the present invention is to solve the above shortcomings of the prior art and to provide a kind of knowledges of the image of fire source
Other method, unified with nature flare up calamity image recognition and thermal infrared images temperature determine in a physical efficiency complete fire it is accurate judge,
It can also be quickly deployed in enterprise, complete intelligent decision monitoring by the existing camera of enterprise.
For this purpose, first aspect present invention provides a kind of image-recognizing method of fire source, comprising the following steps:
Step S11 obtains the visible images in area to be measured, pre-processes to the visible images；
Step S21 identifies the target object in the pretreated visible images, to judge whether there is
Doubtful fire source, when, there are when doubtful fire source, entering step S31 in the visible images；
Step S31 obtains the mesh of doubtful fire source to there are the regions of doubtful fire source to demarcate in the visible images
Mark subject area；
Step S41, obtains the thermal infrared images in area to be measured, and obtains the thermal characteristics value of the targeted object region；
The thermal characteristics value is compared step S51 with given threshold, when the thermal characteristics value is more than or equal to setting threshold
When value, there are fire sources for judgement.
In some embodiments of the invention, the visible images obtain and/or described from visible light monitor video
Thermal infrared images is obtained from thermal infrared monitor video, and preferably described area's thermal infrared images to be measured is to pass through pretreated area to be measured
Thermal infrared images.
In some embodiments of the invention, the pretreatment includes carrying out in gray processing, binaryzation and noise reduction process
It is one or more.
In some embodiments of the invention, in step S21, the target object is flame and/or smog.
In some embodiments of the invention, the flame includes blue flame, purple flame, orange flame, red fire
Flame, white one of flame and yellow flame or a variety of.
In some embodiments of the invention, it in step S21, is calculated using including nerual network technique and/or flame identification
Method identifies the target object in the visible images, it is preferred that the flame identification algorithm is RGB flame identification
Algorithm.
In some embodiments of the invention, in step S41, the thermal infrared images in area to be measured is obtained, calculates visible light figure
As and thermal infrared images regional percentage, then by proportion plus offset targeted object region is calibrated in thermal infrared images, and
Obtain the thermal characteristics value of the targeted object region.
In some embodiments of the invention, in step S41, the thermal characteristics value is temperature value.
In some embodiments of the invention, in step S51, further include judgement there are after fire source, carry out starting alarm,
One of alarm displaying and message push are a variety of.
In some embodiments of the invention, it reads back a frame video image every a timeslice from specified address, obtains institute
The visible images in video image are stated, carry out step S11, and/or when target object is not present in the visible images,
Return step S11, and/or when the thermal characteristics value to be compared with given threshold, the thermal characteristics value is less than the setting
When threshold value, return step S11.
Second aspect of the present invention provides a kind of identifying system of image-recognizing method for the fire source, including,
Image capture module is configured to acquire monitor video in region to be measured, and obtains visible images and thermal infrared
Image, it is preferred that described image acquisition module includes visible image capturing unit and thermal infrared camera unit；
Image pre-processing module is configured to pre-process visible images and/or thermal infrared images；
Visible light identification module is configured to identify the target object in visible images after pretreatment,
And calibrate targeted object region；
Thermal infrared identification module is configured to obtain area's thermal infrared images to be measured, and obtains the target object area
The thermal characteristics value in domain, and fire source is judged whether there is according to the thermal characteristics value；And alarm modules, it is configured to deposit when judgement
Alarm is carried out in fire source.
A kind of image-recognizing method of fire source provided by the present invention, unified with nature flare up calamity image recognition and thermal infrared figure
Picture temperature determines that in one, that is, first using the identification of natural light fire image, reheating infrared image identification decision completes fire
Accurate judgement, effectively prevents wrong report caused by due to anaclasis etc., also big while improving fire source judgment accuracy
It is big to reduce operating cost and reduce thermal infrared instrument damage, in addition, this method can quickly be deployed in enterprise, by enterprise
Existing camera completes intelligent decision monitoring.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example and is used together to explain the present invention, be not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the fire source recognition methods flow diagram of one embodiment provided by the invention；
Fig. 2 is the flow chart of the fire source recognition methods of one embodiment provided by the invention；
Fig. 3 is the identifying system structural schematic diagram of one embodiment provided by the invention.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right to keep the purpose of the present invention, technical solution and advantage easier to understand
Embodiments of the present invention are further elaborated, and to the present invention, how applied technology method is asked to solve technology whereby
Topic, and the realization process for reaching technical effect can be fully understood and implemented.It should be appreciated that specific implementation described herein
Example is not intended to limit the present invention only to explain the present invention.In addition, institute in the various embodiments of the present invention described below
The technical characteristic being related to can be combined with each other as long as they do not conflict with each other.
In addition, step shown in the flowchart of the accompanying drawings can be in the department of computer science of such as a group of computer-executable instructions
It is executed in system, although also, logical order is shown in flow charts, and it in some cases, can be to be different from herein
Sequence execute shown or described step.
First embodiment
As Fig. 1-2 shows the recognition methods of one embodiment of the application.The recognition methods of the present embodiment specifically includes
Following steps:
Step S11 obtains the visible images in area to be measured；Visible images described in the present embodiment and the thermal infrared images
It is preferred that video is accessed network, passes image back from multi-path monitoring video by interception from monitor video；Server every a timeslice from
Read back a frame video image for specified address.Gray processing, binaryzation and noise reduction process are carried out to the visible images of acquisition.
Step S21 is identified to by the target object in pretreated visible images, doubtful to judge whether there is
Like fire source, which includes flame and smog；Specifically, flame is blue flame, purple flame, orange flame, red
Flame, white flame and yellow flame.Using nerual network technique and RGB flame identification algorithm, according to pretreated visible
Doubtful generation fire is judged in light image.When identifying target object, target object is identified in visible images.Work as institute
It states in visible images there are when doubtful fire source, enters step S31.
Step S31 demarcates the region of doubtful fire source present in the visible images, after marking flame point,
The targeted object region of doubtful fire source, i.e. flame and smoke region are made by OPENCV technical bid.
Step S41 obtains the thermal infrared images in area to be measured；And visible images and thermal infrared images regional percentage are calculated,
Again by offset spotting subject area in thermal infrared images is added in proportion, the thermal characteristics value of targeted object region is obtained.
The thermal characteristics value is compared step S51 with given threshold, when the thermal characteristics value is more than or equal to setting threshold
When value, there are fire sources for judgement；Then start alarm, alarm is shown and message push.Given threshold can according to actual needs into
Row setting, such as can be set to 675 DEG C or such as 800 DEG C or such as 500 DEG C lower higher.
Specifically, starting alarm refers to triggering alarm, ring siren；Alarm, which is shown, to be referred to fire source information (such as place
Position coordinates, fire coverage area, fire area, the color of flame, temperature and smoke condition etc.) it shows in specified display screen
On；Message push is the mobile terminal that fire source information is pushed to control centre and/or responsible security against fire personnel.Alarm modules are also
More preferably live intensity of a fire situation, component scaling loss situation and fire burning time can be deduced according to above-mentioned fire source information, with
Conducive to the smooth implementation of subsequent Fire Escape.
Second embodiment
As Fig. 3 shows the identifying system structural schematic diagram of one embodiment of the application.The identifying system of the present embodiment
Including image capture module 101 is configured to acquire monitor video in region to be measured, and obtains visible images and thermal infrared
Image, described image acquisition module 101 include visible image capturing unit and thermal infrared camera unit；Image pre-processing module 102,
It is configured to pre-process visible images and/or thermal infrared images；Visible light identification module 103, is configured to warp
Target object in pretreated visible images is identified, and calibrates targeted object region；Thermal infrared identification module
104, it is configured to obtain area's thermal infrared images to be measured, and obtain the thermal characteristics value of the targeted object region；And according to
The thermal characteristics value is to judging whether there is fire source；And alarm modules 105, it is configured to when there are warned when fire source for judgement
Report.
It should be noted that embodiment described above for explaining only the invention, is not constituted to of the invention any
Limitation.By referring to exemplary embodiments, invention has been described, it should be appreciated that word used in it is descriptive
With explanatory vocabulary, rather than limited vocabulary.The present invention can be made within the scope of the claims by regulation
Modification, and the present invention is revised in without departing substantially from scope and spirit of the present invention.Although the present invention described in it relates to
And specific method, material and embodiment, it is not intended that the present invention is limited to particular case disclosed in it, on the contrary, this hair
It is bright to can be extended to other all methods and applications with the same function.
Claims (10)
1. a kind of image-recognizing method of fire source, comprising the following steps:
Step S11 obtains the visible images in area to be measured, pre-processes to the visible images；
Step S21 identifies the target object in the pretreated visible images, doubtful to judge whether there is
Fire source, when, there are when doubtful fire source, entering step S31 in the visible images；
Step S31 obtains the target pair of doubtful fire source to there are the regions of doubtful fire source to demarcate in the visible images
As region；
Step S41, obtains the thermal infrared images in area to be measured, and obtains the thermal characteristics value of the targeted object region；
The thermal characteristics value is compared step S51 with given threshold, when the thermal characteristics value is more than or equal to given threshold
When, there are fire sources for judgement.
2. the method according to claim 1, wherein the visible images are obtained from visible light monitor video
It takes and/or the thermal infrared images is obtained from thermal infrared monitor video, preferably described area's thermal infrared images to be measured is by pre-
Area's thermal infrared images to be measured of processing.
3. method according to claim 1 or 2, which is characterized in that it is described pretreatment include carry out gray processing, binaryzation and
One of noise reduction process is a variety of.
4. method described in any one of -3 according to claim 1, which is characterized in that in step S21, the target object is
Flame and/or smog.
5. method described in any one of -4 according to claim 1, which is characterized in that the flame includes blue flame, purple
Color flame, orange flame, blushed flame, white one of flame and yellow flame or a variety of.
6. method described in any one of -5 according to claim 1, which is characterized in that in step S21, using including nerve net
Network technology and/or flame identification algorithm, identify the target object in the visible images, it is preferred that the flame
Recognizer is RGB flame identification algorithm.
7. method described in any one of -6 according to claim 1, which is characterized in that in step S41, obtain the heat in area to be measured
Infrared image calculates visible images and thermal infrared images regional percentage, then presses and add offset in thermal infrared images in proportion
Targeted object region is calibrated, and obtains the thermal characteristics value of the targeted object region.
8. method according to any one of claims 1-7, which is characterized in that in step S41, the thermal characteristics value is
Temperature value.
9. method described in any one of -8 according to claim 1, which is characterized in that further include being deposited in judgement in step S51
After fire source, one of starting alarm, alarm displaying and message push or a variety of are carried out.
10. a kind of identifying system for method described in any one of claim 1-9, including,
Image capture module is configured to acquire monitor video in region to be measured, and obtains visible images and thermal infrared images,
Preferably, described image acquisition module includes visible image capturing unit and thermal infrared camera unit；
Image pre-processing module is configured to pre-process visible images and/or thermal infrared images；
Visible light identification module is configured to identify the target object in visible images after pretreatment, and marks
Make targeted object region；
Thermal infrared identification module is configured to obtain area's thermal infrared images to be measured, and obtains the targeted object region
Thermal characteristics value, and fire source is judged whether there is according to the thermal characteristics value；And alarm modules, it is configured to there is fire when judgement
Alarm is carried out when source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810744479.8A CN109101882A (en) | 2018-07-09 | 2018-07-09 | A kind of image-recognizing method and system of fire source |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810744479.8A CN109101882A (en) | 2018-07-09 | 2018-07-09 | A kind of image-recognizing method and system of fire source |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109101882A true CN109101882A (en) | 2018-12-28 |
Family
ID=64845896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810744479.8A Pending CN109101882A (en) | 2018-07-09 | 2018-07-09 | A kind of image-recognizing method and system of fire source |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109101882A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135266A (en) * | 2019-04-17 | 2019-08-16 | 浙江理工大学 | A kind of dual camera electrical fire preventing control method and system based on deep learning |
| CN110363952A (en) * | 2019-08-20 | 2019-10-22 | 宝钢湛江钢铁有限公司 | A kind of contactless early warning system of fire-fighting early stage |
| 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 |
| CN111127810A (en) * | 2019-12-24 | 2020-05-08 | 新疆信息产业有限责任公司 | Automatic alarming method and system for open fire of machine room |
| CN112614302A (en) * | 2020-12-03 | 2021-04-06 | 杭州海康微影传感科技有限公司 | Fire detection method, device and system and electronic equipment |
| CN113837149A (en) * | 2021-11-23 | 2021-12-24 | 航天宏图信息技术股份有限公司 | Automatic identification method and device |
| CN114399882A (en) * | 2022-01-20 | 2022-04-26 | 红骐科技(杭州)有限公司 | Fire source detection, identification and early warning method for fire-fighting robot |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625789A (en) * | 2008-07-07 | 2010-01-13 | 北京东方泰坦科技有限公司 | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire |
| CN101833838A (en) * | 2010-05-27 | 2010-09-15 | 王巍 | Large-range fire disaster analyzing and early warning system |
| CN104867265A (en) * | 2015-04-22 | 2015-08-26 | 深圳市佳信捷技术股份有限公司 | Camera apparatus, and fire detection alarm system and method |
| CN105046868A (en) * | 2015-06-16 | 2015-11-11 | 苏州华启智能科技股份有限公司 | Fire early warning method based on infrared thermal imager in narrow environment |
| CN105976365A (en) * | 2016-04-28 | 2016-09-28 | 天津大学 | Nocturnal fire disaster video detection method |
| US20160314676A1 (en) * | 2015-04-21 | 2016-10-27 | Sintai Optical (Shenzhen) Co., Ltd. | Active protection system |
-
2018
- 2018-07-09 CN CN201810744479.8A patent/CN109101882A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625789A (en) * | 2008-07-07 | 2010-01-13 | 北京东方泰坦科技有限公司 | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire |
| CN101833838A (en) * | 2010-05-27 | 2010-09-15 | 王巍 | Large-range fire disaster analyzing and early warning system |
| US20160314676A1 (en) * | 2015-04-21 | 2016-10-27 | Sintai Optical (Shenzhen) Co., Ltd. | Active protection system |
| CN104867265A (en) * | 2015-04-22 | 2015-08-26 | 深圳市佳信捷技术股份有限公司 | Camera apparatus, and fire detection alarm system and method |
| CN105046868A (en) * | 2015-06-16 | 2015-11-11 | 苏州华启智能科技股份有限公司 | Fire early warning method based on infrared thermal imager in narrow environment |
| CN105976365A (en) * | 2016-04-28 | 2016-09-28 | 天津大学 | Nocturnal fire disaster video detection method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135266A (en) * | 2019-04-17 | 2019-08-16 | 浙江理工大学 | A kind of dual camera electrical fire preventing control method and system based on deep learning |
| CN110363952A (en) * | 2019-08-20 | 2019-10-22 | 宝钢湛江钢铁有限公司 | A kind of contactless early warning system of fire-fighting early stage |
| 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 |
| CN111127810A (en) * | 2019-12-24 | 2020-05-08 | 新疆信息产业有限责任公司 | Automatic alarming method and system for open fire of machine room |
| CN112614302A (en) * | 2020-12-03 | 2021-04-06 | 杭州海康微影传感科技有限公司 | Fire detection method, device and system and electronic equipment |
| CN113837149A (en) * | 2021-11-23 | 2021-12-24 | 航天宏图信息技术股份有限公司 | Automatic identification method and device |
| CN114399882A (en) * | 2022-01-20 | 2022-04-26 | 红骐科技(杭州)有限公司 | Fire source detection, identification and early warning method for fire-fighting robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109101882A (en) | A kind of image-recognizing method and system of fire source | |
| CN109846463A (en) | Infrared face temp measuring method, system, equipment and storage medium | |
| CN105512667B (en) | Infrared and visible light video image fusion recognition fire method | |
| WO2020078229A1 (en) | Target object identification method and apparatus, storage medium and electronic apparatus | |
| CN103208126B (en) | Moving object monitoring method under a kind of physical environment | |
| CN109637068A (en) | Intelligent pyrotechnics identifying system | |
| US20160260306A1 (en) | Method and device for automated early detection of forest fires by means of optical detection of smoke clouds | |
| CN107437318B (en) | Visible light intelligent recognition algorithm | |
| CN106897720A (en) | A kind of firework detecting method and device based on video analysis | |
| CN111339997B (en) | Fire point area determination method and device, storage medium and electronic device | |
| CN108389359A (en) | A kind of Urban Fires alarm method based on deep learning | |
| CN112560547A (en) | Abnormal behavior judgment method and device, terminal and readable storage medium | |
| CN107067412A (en) | A kind of video flame smog detection method of Multi-information acquisition | |
| CN110517441A (en) | Based on the frame-embedded smog of deep learning and flame video alarming system and method | |
| CN112785809B (en) | Fire re-ignition prediction method and system based on AI image recognition | |
| CN109543631A (en) | A kind of fire image detection alarm method based on machine learning | |
| Chowdhury et al. | Computer vision and smoke sensor based fire detection system | |
| KR20140050240A (en) | Identification of friend or foe system based on image processing, and control method of the same | |
| Sathyakala et al. | Computer vision based fire detection with a video alert system | |
| WO2019026518A1 (en) | Fire identification device | |
| KR101476764B1 (en) | Flame dete ction method based on gray imaging signal of a cameras | |
| CN109243135A (en) | A kind of intelligence fire detection and localization method, apparatus and system | |
| CN112347874A (en) | Fire detection method, device, equipment and storage medium | |
| CN105160799A (en) | Fire and heat source detection method and apparatus based on infrared thermal imaging bare data | |
| KR20070028812A (en) | Method and apparatus for monitoring forest fire using images photographed by camera device |
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: 20181228 |