CN104410830A - Device based on video smoke detection, and method based on video smoke detection - Google Patents
Device based on video smoke detection, and method based on video smoke detection Download PDFInfo
- Publication number
- CN104410830A CN104410830A CN201410710015.7A CN201410710015A CN104410830A CN 104410830 A CN104410830 A CN 104410830A CN 201410710015 A CN201410710015 A CN 201410710015A CN 104410830 A CN104410830 A CN 104410830A
- Authority
- CN
- China
- Prior art keywords
- unit
- smog
- prospect
- region
- window
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a device based on video smoke detection, and a method based on video smoke detection. The method includes the following steps: scattered foreground points are firstly acquired through a video image acquisition unit and a foreground acquisition unit; de-noising processing of the foreground points is then carried out through a de-noising unit; the foreground points are then accumulated through a foreground accumulation unit; a region connection unit is utilized to connect the accumulated foregrounds and acquire relevant parameters; the average gradient information of connected regions is acquired through a gradient computing unit; the relevant parameters are then set through a false smoke removal unit to remove some false smoke regions; feature matching of suspected smoke regions that are not removed is then carried out through a feature matching unit; a judging and alarming unit finally decides whether an alarm is to be sent by judging whether the matching times exceed a threshold value or not. The invention has the advantages that the foregrounds are acquired through the three frame difference method and accumulated through a fixed window, false smoke is then removed through the multi-feature fusion method, and finally the matching times are judged to decide whether the alarm is to be sent or not.
Description
Technical field
The present invention relates to computer vision field, especially relate to the early-stage smog being applied to field of video monitoring and detect.
Background technology
Prevention and the detection of fire are the emphasis that people pay close attention to always.And during fire generation, the phenomenon more early occurred is smog.Therefore, the detection for smog seems more important.Most adopted detection means is divided at present: smoke detector and video monitoring.
Various sense cigarette type detector needs smog to reach finite concentration and arrives in detector certain limit, just can effectively report to the police, and when tall and big spacious place, this kind of detector effect of seeming is not enough.And along with the high speed development of modern society, high building is increasing.Once breaking out of fire, when this kind of detector sends warning, cause very large loss, lose effect and the object of original detection.
And need a large amount of personnel just can carry out comprehensive, round-the-clock real-time monitoring for common video monitoring.This kind of scheme is difficult to carry out especially.One is need a large amount of personnel could carry out Real Time Observation to numerous video; Two is that monitor staff can not concentrate by round-the-clock energy.
Summary of the invention
The object of the invention is to propose a kind of apparatus and method detected based on video smoke.The present invention can be formed at smog and provide warning fast and effectively in early days.
In order to achieve the above object, the present invention proposes a kind of device detected based on video smoke, and the device of this Smoke Detection comprises:
Video image acquiring unit, utilizes the image of camera Real-time Collection guarded region.
Ask for prospect unit, utilize three frame difference methods to ask for prospect to the video obtained in video image acquiring unit.
Denoising unit, utilizes opening operation to operate and the prospect asked for is done denoising, eliminate trickle noise.
Prospect summing elements, the window of a regulation regular length adds up to the prospect after denoising, finally as the testing result of doubtful smog.
Joint area unit, joint area is carried out to cumulative foreground point and record the relevant parameters such as area, gray scale, barycenter and real-time update as judge report to the police condition.
Gradient calculation unit, obtains the average gradient value of whole join domain, as one of condition judging to report to the police.
Pseudo-smog rejected unit, the relevant parameter obtained according to front Unit two also utilizes the conditions such as the shape of smog, color, movement tendency and neighboring area to carry out the rejecting of pseudo-smog.
Characteristic matching unit, carries out characteristic matching by the smog suspicious region of not rejecting.Whether adopt is that arest neighbors selects condition as matching area.Coupling restrictive condition comprises gray scale and area change.
Judge alarm unit, judge whether to report to the police according to coupling frame number and threshold value relation.
According to another aspect of the present invention, provide a kind of method detected based on video smoke, the method comprising the steps of:
First step, video acquisition, utilizes the video image of camera Real-time Collection guarded region.
Second step, utilizes three frame difference methods to ask for prospect to the video image obtained in first step.
Third step, opening operation removes part noise, may comprise some trickle noises, these noises got rid of by opening operation in the foreground area that in second step, frame difference goes out.
4th step, in window, frame difference prospect adds up, and the window of a regulation regular length adds up to the prospect after denoising in third step, finally as the testing result of doubtful smog.
5th step, cumulative foreground area connects, joint area is carried out to the cumulative foreground point in the 4th step and record the relevant parameters such as area, gray scale, barycenter and real-time update as the condition judging to report to the police.
6th step, foreground area inner gradient calculates, and obtains the average gradient value of whole join domain, as one of condition judging to report to the police.
7th step, non-smoke region is rejected, and the relevant parameter obtained according to the 5th step, the 6th step also utilizes the conditions such as the shape of smog, color, movement tendency and neighboring area to carry out the rejecting of pseudo-smog.
8th step, characteristic matching, carries out characteristic matching by the smog suspicious region of not rejecting in the 7th step.Whether adopt is that arest neighbors selects condition as matching area.Coupling restrictive condition comprises gray scale and area change.
9th step, judges whether to report to the police according to coupling frame number and threshold value relation.
Accompanying drawing explanation
The present invention has six, accompanying drawing:
Fig. 1 shows according to the schematic block diagram based on video smoke checkout gear of the present invention;
Fig. 2 shows the schematic block diagram according to prospect of the asking for unit based on video smoke checkout gear of the present invention;
Fig. 3 shows the schematic block diagram according to the prospect summing elements based on video smoke checkout gear of the present invention;
Fig. 4 shows according to the overall flow figure based on video smoke detection method of the present invention;
Fig. 5 shows according to the first step flow chart based on video smoke detection method of the present invention;
Fig. 6 shows according to the 4th step flow chart based on video smoke detection method of the present invention.
Embodiment
With reference to the accompanying drawings and the present invention is described in detail in conjunction with instantiation.Be to be noted that described example is only for the ease of the understanding of the present invention, therefore do not limit protection scope of the present invention.
Fig. 1 shows the schematic block diagram according to the mist detecting device based on video of the present invention.The each unit of the following stated device all can realize separately through microprocessor, but a processor with high-performance CPU also can be utilized to realize for cost-saving.As shown in Figure 1, comprise according to the mist detecting device based on video of the present invention:
Part I, video image acquiring unit 101, is used for obtaining the vedio data of guarded region and data is passed to and ask for prospect unit 102.
Part II, asks for prospect unit 102, utilizes three frame difference methods to ask for scattered foreground point.Concrete composition as shown in Figure 2, comprising:
Image storage unit 201, is used for the vedio data obtained in store video images acquiring unit 101;
Frame difference computing unit 202, it is poor to be used for the frame of adjacent two frames in computed image memory cell 201;
Frame difference result memory cell 203, be used for preserving frame difference computing unit 202 calculate after result;
Three frame difference computing units 204, carry out and operation neighbor frame difference result in frame difference result memory cell 203;
Three frames difference result memory cell 205, be used for preservation three frame difference computing unit 204 calculate after result.
Part III, denoising unit 103, utilizes opening operation to operate and carries out denoising operation to asking for the prospect that prospect unit 102 asks for, eliminate trickle noise.
Part IV, prospect summing elements 104, the window of a regulation regular length adds up to the prospect after denoising, and concrete composition as shown in Figure 3, comprising:
Window judging unit 301, whether be used for judging in stationary window is that first time is cumulative, carry out different operations according to judged result to data;
Frame difference prospect summing elements 302, if window judging unit 301 judges that stationary window is cumulative as first time, then frame difference prospect summing elements 302 directly carries out adding up to new prospect, if window judging unit 301 judges that stationary window is not that first time is cumulative, then frame difference prospect summing elements 302 is while cumulative new prospect, deducts the prospect just going out window;
Accumulation threshold judging unit 303, is used for judging whether each point accumulative frequency of cumulative foreground point in stationary window exceedes threshold value;
Smog template-setup unit 304, the cumulative foreground point being used for accumulative frequency to reach threshold value makes marks operation in the smog template position of correspondence.
Part V, joint area unit 105, the point labeled to the smog template-setup unit 304 in prospect summing elements 104 carries out joint area and the relevant parameters such as reference area, gray scale, barycenter.
Part VI, gradient calculation unit 106, obtains the average gradient value of join domain in joint area unit 105, as one of condition judging to report to the police.
Part VII, pseudo-smog rejected unit 107, the relevant parameter obtained according to joint area unit 105 and gradient calculation unit 106 also utilizes the conditions such as the shape of smog, color, movement tendency and neighboring area to carry out the rejecting of pseudo-smog.The suspicious region of not rejecting is stored.
Part VIII, characteristic matching unit 108, carries out characteristic matching by the smog suspicious region that pseudo-smog rejected unit 107 is not rejected.Whether mated with historical frames data by current frame data, adopting is that arest neighbors selects condition as matching area.Coupling restrictive condition comprises gray scale and area change.By its matching times, 1 is added for the suspicious region that the match is successful.
Part IX, judges alarm unit 109, and the coupling frame number of each suspicious region recorded according to characteristic matching unit 108 and threshold value relation judge whether to report to the police.
According to another aspect of the present invention, propose a kind of method detected based on video smoke, the present invention utilizes the method for computer vision, carries out real-time analysis process to guarded region, when guarded region has smog to occur, identification is carried out to smog and judges and automatically provide warning message.In addition, due to the difference of actual scene, the threshold value in following can be different, and best threshold value could need be determined according to after reality test.Therefore, no longer enumerate actual data to be here described.As shown in Figure 4, overall flow of the present invention is divided into nine steps:
Step 401, obtains color video, utilizes camera to obtain the real time video image data of guarded region.
Step 402, three frame differences ask for scattered foreground area.As shown in Figure 5, two frames adjacent in video, by the appropriate threshold value T1 of setting, are done frame difference and saving result by step 501; Neighbor frame difference result is carried out and operation by step 502 again, and when two parts frame difference result all meets threshold value T1, three frame difference results of this some correspondence are true; Three frame difference result assignment are given in three corresponding frame differential mode plates by step 503.
Step 403, carries out opening operation to frame difference result, carries out opening operation remove noise to the three frame difference results obtained in step 402.Some trickle noises may be comprised in the foreground area that in step 402, frame difference goes out, by opening operation, these noises be got rid of.And the edge of suspicious region is done smoothing processing by opening operation.
Step 404, stationary window frame interior difference result adds up, and adds up in the window that frame number is fixing continuously in time of the every frame foreground point after denoising.As shown in Figure 6, step 601 judges whether setting window carries out first time and add up, and carries out different steps according to judged result difference; If step 601 judges that setting window is not that first time is cumulative, then the prospect newly entering window is added by step 602; Then the prospect just having gone out window the time cuts by step 603; If step 601 judges to set window as cumulative for the first time, then step 604 directly adds up to the prospect newly entered; Step 605 judges that in setting window, whether each foreground point accumulative frequency exceedes setting threshold T2, if exceed threshold value T2, is then set as 1 by this correspondence position, otherwise is set as 0 in smog template.Window size is set as 30, i.e. continuous print 30 frame three frame difference result on accumulation interval.
Step 405, prospect connects, and step 404 is set as in smog template the point of 1 carries out joint area.Centered by a certain gauge point, carry out four neighborhood connection handlings, all adjacent gauge points are carried out joint area.Calculate the area of join domain, average gray, barycenter, girth simultaneously.
Step 406, intra-zone gradient calculation.The distribution of smog interior intensity should present more level and smooth feature, can be used as judge that whether doubtful foreground area is a standard of smog according to this feature.According to certain any 4 Grad calculating these points up and down.Gradient calculation formula is:
nAvgGrad=(∑nGrad)/Num
nGrad=
|f1-f2
|+
|f3-f4
|
Wherein
nAvgGradfor the average gradient value of foreground area;
nGradfor the Grad of foreground area every bit;
numfor the gauge point number of foreground area;
f1, f2, f3, f4for four neighborhood point gray values of required point.
Step 407, according to the pseudo-smoke region of pre-conditioned exclusive segment.The rejecting of pseudo-smog is carried out according to the shape of smog, color, movement tendency and neighboring area.Mainly comprise following a few part:
1, the eliminating of essential characteristic, restrictive condition is respectively:
(1) whether suspicious region size meets setting threshold.Some too small or excessive pseudo-smoke region are got rid of by the minimax region area of smog in setting detected image.
(2) suspicious region average gray restriction.Black smoke, white cigarette, its gray value of blue or green cigarette, all in certain scope, is undertaken getting rid of pseudo-smoke region by the intensity value ranges setting suspicious region.
(3) suspicious region filling rate restriction.Filling rate is the ratio of suspicious region area and suspicious region minimum enclosed rectangle.Smog has stronger diversity, utilizing this character of smog by setting suitable filling rate, effectively can get rid of most of pseudo-smoke region.
(4) suspicious region the ratio of width to height restriction.Smog is in the process of waving, and its ratio of width to height changes within the specific limits.The false smoke region of exclusive segment is come by the ratio of width to height setting suspicious region.
(5) whether inside, suspicious region is level and smooth.The inner smooth features in the average gradient information response suspicious region calculated in step 406.No matter be which kind of smog, its inside all shows smoothness properties.Can effective exclusive segment puppet smoke region by setting average gradient threshold value.Gradient operator in step 406 can take any one, and its threshold value is different according to the difference of operator.
2, get rid of according to color-values feature.The no matter inclined grey black in smoke region or white, the difference of R, G, B component is all less, gets rid of by setting R, G, B threshold value the suspicious region that color information does not meet smoke characteristics.The color image format that the present invention adopts is YUV, and YUV image directly can not embody the color information of object, therefore determinating area is carried out color space conversion.Wherein YUV changes RGB and can adopt any one mode.
3, suspicious region peripheral information judges.This judgement is mainly for the suspicious region compared with small size.The black smoke that igniting generates, a key character is that in smoke region, below has one piece of highlight regions.Judge whether suspicious region is smog by the position relationship detecting suspicious region and highlight regions.Above detecting that if continue highlight regions is in smog suspicious region, then think and do not meet established standards, this smog suspicious region is rejected.
Step 408, template resets, and the smog template of the pseudo-smoke region of rejecting in step 407 is reset.The doubtful smoke region of not rejecting and related data are carried out preserving as historical data.
Step 409, characteristic matching.Matching operation is carried out to the suspicious region do not excluded in step 7.Suspicious region in the previous frame historical data of the suspicious region occurred in present frame and step 408 being preserved is mated.Matching condition comprises gray scale and area change.If the suspicious region in the suspicious region in present frame and historical data all changes not quite in average gray, area change, meet setting threshold, then think coupling, matching times adds 1.
Step 410, judges whether to report to the police according to coupling frame number and threshold value relation.Think that this suspicious region is smog generation area when matching times arrives setting threshold T3, provide warning.
The above; be only the embodiment in the present invention, but protection scope of the present invention is not limited thereto, any researcher being familiar with this technology is in the technical scope disclosed by the present invention; according to the multiple change that actual conditions are made, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection range of claims.
Claims (10)
1., based on the apparatus and method that video smoke detects, it is characterized in that, this device comprises:
Part I, video image acquiring unit, is used for obtaining the vedio data of guarded region and data is passed to and ask for prospect unit;
Part II, asks for prospect unit, utilizes three frame difference methods to ask for scattered foreground point;
Part III, denoising unit, utilizes opening operation to operate and carries out denoising operation to the prospect that the prospect unit of asking for is asked for, eliminate trickle noise;
Part IV, prospect summing elements, the window of a regulation regular length adds up to the prospect after denoising;
Part V, joint area unit, the point cumulative prospect being reached threshold value carries out joint area and the relevant parameters such as reference area, gray scale, barycenter;
Part VI, gradient calculation unit, obtains the average gradient value of join domain in joint area unit, as one of condition judging to report to the police;
Part VII, pseudo-smog rejected unit, the relevant parameter obtained according to joint area unit and gradient calculation unit also utilizes the conditions such as the shape of smog, color, movement tendency and neighboring area to carry out the rejecting of pseudo-smog, is stored the suspicious region of not rejecting;
Part VIII, characteristic matching unit, characteristic matching is carried out in the smog suspicious region that pseudo-smog rejected unit is not rejected, current frame data is mated with historical frames data, whether adopt is that arest neighbors selects condition as matching area, coupling restrictive condition comprises gray scale and area change, for the suspicious region that the match is successful, its matching times is added 1;
Part IX, judges alarm unit, judges whether to report to the police according to the coupling frame number of each suspicious region of characteristic matching unit record and threshold value relation.
2. according to device according to claim 1, it is characterized in that, the prospect unit of asking for comprises:
Image storage unit, is used for the vedio data obtained in store video images acquiring unit;
Frame difference computing unit, it is poor to be used for the frame of adjacent two frames in computed image memory cell;
Frame difference result memory cell, be used for preserving frame difference computing unit calculate after result;
Three frame difference computing units, carry out and operation neighbor frame difference result in frame difference result memory cell;
Three frames difference result memory cell, be used for preservation three frame difference computing unit calculate after result.
3. according to device according to claim 1, it is characterized in that, prospect summing elements comprises:
Window judging unit, whether be used for judging in stationary window is that first time is cumulative, carry out different operations according to judged result to data;
Frame difference prospect summing elements, if window judging unit judges that stationary window is cumulative as first time, then frame difference prospect summing elements directly carries out adding up to new prospect, if window judging unit judges that stationary window is not that first time is cumulative, then frame difference prospect summing elements is while cumulative new prospect, deducts the prospect just going out window;
Accumulation threshold judging unit, is used for judging whether each point accumulative frequency of cumulative foreground point in stationary window exceedes threshold value;
Smog template-setup unit, the cumulative foreground point being used for accumulative frequency to reach threshold value makes marks operation in the smog template position of correspondence.
4., based on the apparatus and method that video smoke detects, it is characterized in that, the method step comprises:
First step, video acquisition, utilizes the video image of camera Real-time Collection guarded region;
Second step, utilizes three frame difference methods to ask for prospect to the video image obtained in first step;
Third step, opening operation removes part noise, may comprise some trickle noises, these noises got rid of by opening operation in the foreground area that in second step, frame difference goes out;
4th step, in window, frame difference prospect adds up, and adds up in the window that frame number is fixing continuously in time of the every frame foreground point after denoising, finally as the testing result of doubtful smog;
5th step, cumulative foreground area connects, joint area is carried out to the cumulative foreground point in the 4th step and record the relevant parameters such as area, gray scale, barycenter and real-time update as the condition judging to report to the police;
6th step, foreground area inner gradient calculates, and obtains the average gradient value of whole join domain, as one of condition judging to report to the police;
7th step, non-smoke region is rejected, and the relevant parameter obtained according to the 5th step, the 6th step also utilizes the conditions such as the shape of smog, color, movement tendency and neighboring area to carry out the rejecting of pseudo-smog;
8th step, characteristic matching, carries out characteristic matching by the smog suspicious region of not rejecting in the 7th step, and whether be arest neighbors as matching area select condition, coupling restrictive condition comprises gray scale and area change if adopting;
9th step, judges whether to report to the police according to coupling frame number and threshold value relation.
5. in accordance with the method for claim 4, it is characterized in that, the 4th step comprises:
A) judge whether setting window carries out first time and add up, and carries out different steps according to judged result difference;
If b) judge, setting window is not that first time is cumulative, then the prospect newly entering window be added, then the prospect just having gone out window the time cut;
If c) judge to set window as cumulative for the first time, then the direct prospect to newly entering adds up;
D) judge in setting window, whether each foreground point accumulative frequency exceedes setting threshold, if exceed threshold value, then in smog template, this correspondence position is set as 1, otherwise is set as 0, wherein window size is set as 30, i.e. continuous print 30 frame three frame difference result on accumulation interval.
6. in accordance with the method for claim 4, it is characterized in that, in the 6th step, gradient calculation formula is:
nAvgGrad=(∑nGrad)/Num
nGrad=
|f1-f2
|+
|f3-f4
|
Wherein
nAvgGradfor the average gradient value of foreground area;
nGradfor the Grad of foreground area every bit;
numfor the gauge point number of foreground area;
f1,
f2,
f3,
f4for four neighborhood point gray values of required point.
7. in accordance with the method for claim 4, it is characterized in that, the 7th step comprises:
E) eliminating of essential characteristic;
F) get rid of according to color-values feature;
G) suspicious region peripheral information judges.
8. in accordance with the method for claim 7, it is characterized in that, step e) comprises:
(1) whether suspicious region size meets setting threshold, gets rid of some too small or excessive pseudo-smoke region by the minimax region area of smog in setting detected image;
(2) suspicious region average gray restriction, black smoke, white cigarette, its gray value of blue or green cigarette, all in certain scope, is undertaken getting rid of pseudo-smoke region by the intensity value ranges setting suspicious region;
(3) suspicious region filling rate restriction, smog has stronger diversity, utilizing this character of smog by setting suitable filling rate, effectively can get rid of most of pseudo-smoke region;
(4) suspicious region the ratio of width to height restriction, smog is in the process of waving, and its ratio of width to height changes within the specific limits, comes the false smoke region of exclusive segment by the ratio of width to height setting suspicious region;
(5) whether inside, suspicious region is level and smooth, can effective exclusive segment puppet smoke region by setting average gradient threshold value.
9. in accordance with the method for claim 7, it is characterized in that, step f) comprises: the no matter inclined grey black in smoke region or white, the difference of R, G, B component is all less, gets rid of by setting R, G, B threshold value the suspicious region that color information does not meet smoke characteristics.
10. in accordance with the method for claim 7, it is characterized in that, step g) comprises: the black smoke that igniting generates, a key character is that in smoke region, below has one piece of highlight regions, judge whether suspicious region is smog by the position relationship detecting suspicious region and highlight regions, above detecting that if continue highlight regions is in smog suspicious region, then think and do not meet established standards, this smog suspicious region is rejected.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410710015.7A CN104410830A (en) | 2014-12-01 | 2014-12-01 | Device based on video smoke detection, and method based on video smoke detection |
| CN201510595413.3A CN105185023A (en) | 2014-12-01 | 2015-09-18 | Detector with stable heat radiation structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410710015.7A CN104410830A (en) | 2014-12-01 | 2014-12-01 | Device based on video smoke detection, and method based on video smoke detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104410830A true CN104410830A (en) | 2015-03-11 |
Family
ID=52648417
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410710015.7A Pending CN104410830A (en) | 2014-12-01 | 2014-12-01 | Device based on video smoke detection, and method based on video smoke detection |
| CN201510595413.3A Pending CN105185023A (en) | 2014-12-01 | 2015-09-18 | Detector with stable heat radiation structure |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510595413.3A Pending CN105185023A (en) | 2014-12-01 | 2015-09-18 | Detector with stable heat radiation structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN104410830A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105185023A (en) * | 2014-12-01 | 2015-12-23 | 天津艾思科尔科技有限公司 | Detector with stable heat radiation structure |
| CN105741477A (en) * | 2015-11-03 | 2016-07-06 | 天津艾思科尔科技有限公司 | Aircraft with intelligent fire control voice assistant |
| CN105764304A (en) * | 2015-11-03 | 2016-07-13 | 天津艾思科尔科技有限公司 | Aircraft provided with detector with stable heat dissipation structure |
| CN105752352A (en) * | 2015-11-03 | 2016-07-13 | 天津艾思科尔科技有限公司 | Unmanned aerial vehicle having detector with anti-static device |
| CN105763842A (en) * | 2015-11-03 | 2016-07-13 | 天津艾思科尔科技有限公司 | Aircraft with fire-fighting detection function |
| CN106872973A (en) * | 2017-04-26 | 2017-06-20 | 福建省龙岩市气象局 | The method monitored using CINRAD/SA weather radars and track forest fires echo |
| CN108760590A (en) * | 2018-03-08 | 2018-11-06 | 佛山市云米电器科技有限公司 | A kind of kitchen fume Concentration Testing based on image procossing and interference elimination method |
| CN108827967A (en) * | 2018-03-08 | 2018-11-16 | 佛山市云米电器科技有限公司 | Oil smoke image-pickup method and oil smoke concentration detection and interference elimination method |
| CN108898782A (en) * | 2018-07-20 | 2018-11-27 | 武汉理工光科股份有限公司 | The smoke detection method and system that infrared image temperature information for tunnel fire proofing identifies |
| CN109028233A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | Kitchen fume concentration division methods and oil smoke image identification system and kitchen ventilator |
| CN109272469A (en) * | 2018-09-29 | 2019-01-25 | 佛山市云米电器科技有限公司 | A kind of acquisition method and its device of kitchen range oil smoke image |
| CN110021137A (en) * | 2019-03-28 | 2019-07-16 | 赛特威尔电子股份有限公司 | A kind of smog alarm method, apparatus, smoke alarm device and storage medium |
| CN111122188A (en) * | 2018-10-30 | 2020-05-08 | 宁波方太厨具有限公司 | Device for collecting flue gas flowing condition on boiler side of stove and display method |
| CN111462451A (en) * | 2019-11-01 | 2020-07-28 | 武汉纺织大学 | Straw burning detection alarm system based on video information |
| CN113409536A (en) * | 2021-07-29 | 2021-09-17 | 重庆予胜远升网络科技有限公司 | Power equipment potential fire alarm recognition system and method based on machine vision |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6573713B2 (en) * | 2016-03-23 | 2019-09-11 | 日立オートモティブシステムズ株式会社 | In-vehicle image processing device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3372140B2 (en) * | 1995-06-27 | 2003-01-27 | 松下電工株式会社 | Combined smoke and heat detector |
| CN201813490U (en) * | 2010-10-19 | 2011-04-27 | 王兆群 | Vehicle-mounted security monitoring camera device |
| CN103685895B (en) * | 2013-12-30 | 2017-04-26 | 博康智能网络科技有限公司 | Surveillance camera housing |
| 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 |
| CN204496642U (en) * | 2015-04-08 | 2015-07-22 | 天津艾思科尔科技有限公司 | A kind of dual-band image type fire detecting arrangement |
-
2014
- 2014-12-01 CN CN201410710015.7A patent/CN104410830A/en active Pending
-
2015
- 2015-09-18 CN CN201510595413.3A patent/CN105185023A/en active Pending
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105185023A (en) * | 2014-12-01 | 2015-12-23 | 天津艾思科尔科技有限公司 | Detector with stable heat radiation structure |
| CN105741477A (en) * | 2015-11-03 | 2016-07-06 | 天津艾思科尔科技有限公司 | Aircraft with intelligent fire control voice assistant |
| CN105764304A (en) * | 2015-11-03 | 2016-07-13 | 天津艾思科尔科技有限公司 | Aircraft provided with detector with stable heat dissipation structure |
| CN105752352A (en) * | 2015-11-03 | 2016-07-13 | 天津艾思科尔科技有限公司 | Unmanned aerial vehicle having detector with anti-static device |
| CN105763842A (en) * | 2015-11-03 | 2016-07-13 | 天津艾思科尔科技有限公司 | Aircraft with fire-fighting detection function |
| CN105741477B (en) * | 2015-11-03 | 2018-06-12 | 天津艾思科尔科技有限公司 | Aircraft with intelligent fire voice assistant |
| CN105764304B (en) * | 2015-11-03 | 2018-10-16 | 天津艾思科尔科技有限公司 | Detector carries the aircraft of steady type radiator structure |
| CN106872973B (en) * | 2017-04-26 | 2021-05-18 | 福建省龙岩市气象局 | Method for monitoring and tracking forest fire echo by using CINRAD/SA weather radar |
| CN106872973A (en) * | 2017-04-26 | 2017-06-20 | 福建省龙岩市气象局 | The method monitored using CINRAD/SA weather radars and track forest fires echo |
| CN108760590A (en) * | 2018-03-08 | 2018-11-06 | 佛山市云米电器科技有限公司 | A kind of kitchen fume Concentration Testing based on image procossing and interference elimination method |
| CN108827967A (en) * | 2018-03-08 | 2018-11-16 | 佛山市云米电器科技有限公司 | Oil smoke image-pickup method and oil smoke concentration detection and interference elimination method |
| CN108898782A (en) * | 2018-07-20 | 2018-11-27 | 武汉理工光科股份有限公司 | The smoke detection method and system that infrared image temperature information for tunnel fire proofing identifies |
| CN108898782B (en) * | 2018-07-20 | 2020-12-11 | 湖北烽火平安智能消防科技有限公司 | Smoke detection method and system for infrared image temperature information identification for tunnel fire prevention |
| CN109028233A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | Kitchen fume concentration division methods and oil smoke image identification system and kitchen ventilator |
| CN109272469A (en) * | 2018-09-29 | 2019-01-25 | 佛山市云米电器科技有限公司 | A kind of acquisition method and its device of kitchen range oil smoke image |
| CN111122188A (en) * | 2018-10-30 | 2020-05-08 | 宁波方太厨具有限公司 | Device for collecting flue gas flowing condition on boiler side of stove and display method |
| CN110021137A (en) * | 2019-03-28 | 2019-07-16 | 赛特威尔电子股份有限公司 | A kind of smog alarm method, apparatus, smoke alarm device and storage medium |
| CN111462451A (en) * | 2019-11-01 | 2020-07-28 | 武汉纺织大学 | Straw burning detection alarm system based on video information |
| CN113409536A (en) * | 2021-07-29 | 2021-09-17 | 重庆予胜远升网络科技有限公司 | Power equipment potential fire alarm recognition system and method based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105185023A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104410830A (en) | Device based on video smoke detection, and method based on video smoke detection | |
| CN110516609B (en) | Fire disaster video detection and early warning method based on image multi-feature fusion | |
| CN109076198B (en) | Video-based object tracking occlusion detection system, method and equipment | |
| CN109507192B (en) | Magnetic core surface defect detection method based on machine vision | |
| CN102881106B (en) | Dual-detection forest fire identification system through thermal imaging video and identification method thereof | |
| CN101441771B (en) | Video fire hazard smoke detecting method based on color saturation degree and movement mode | |
| RU2529905C2 (en) | Measuring device of filling degree, agricultural vehicle and method of control of filling target area | |
| CN107085714B (en) | Forest fire detection method based on video | |
| JP6764481B2 (en) | Monitoring device | |
| CN104282011B (en) | The method and device of interference stripes in a kind of detection video image | |
| CN106897653B (en) | Forest region smoke and fire detection method and detection system based on infrared and visible light video fusion | |
| CN109447011B (en) | Real-time monitoring method for infrared leakage of steam pipeline | |
| CN112528861B (en) | Foreign matter detection method and device applied to ballast bed in railway tunnel | |
| JP2012098045A (en) | Crack detector and crack detection program | |
| CN101916372A (en) | Video-based smoke detection device and method according to multi-feature fusion | |
| CN111008998A (en) | Automatic fire water monitor flame detection method based on binocular vision | |
| JP2017030380A (en) | Train detection system and train detection method | |
| KR100696725B1 (en) | Shadow casting method using symmetric and distance feature of the object region | |
| JP5710230B2 (en) | Monitoring system and monitoring method | |
| JP5243486B2 (en) | Cable position detection device, cable position detection method, and cable position detection program | |
| CN205140128U (en) | Detecting device with cooling fin structure | |
| JP3729933B2 (en) | Automatic monitoring device | |
| CN116109587A (en) | Sealing nail welding seam quality detection method in complex environment | |
| CN101930541A (en) | Video-based flame detecting device and method | |
| JP6348020B2 (en) | Image processing apparatus, image processing method, and inspection method using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150311 |