CN109711307A - A kind of smoking evidence collecting method based on recognition of face - Google Patents
A kind of smoking evidence collecting method based on recognition of face Download PDFInfo
- Publication number
- CN109711307A CN109711307A CN201811556670.6A CN201811556670A CN109711307A CN 109711307 A CN109711307 A CN 109711307A CN 201811556670 A CN201811556670 A CN 201811556670A CN 109711307 A CN109711307 A CN 109711307A
- Authority
- CN
- China
- Prior art keywords
- face
- smoking
- speck
- image
- personnel
- 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
- 230000000391 smoking effect Effects 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 34
- 101100117236 Drosophila melanogaster speck gene Proteins 0.000 claims abstract description 74
- 235000019504 cigarettes Nutrition 0.000 claims abstract description 41
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 230000001815 facial effect Effects 0.000 claims abstract description 13
- 238000010191 image analysis Methods 0.000 claims abstract description 13
- 230000002093 peripheral effect Effects 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 208000033748 Device issues Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention proposes a kind of smoking evidence collecting method based on recognition of face, it is specific as follows: A: to enter the face of the personnel of non-smoking area using the video camera shooting with face identification functions, obtain the image of face and its peripheral region and be sent to server；B: server judges whether described image speck occurred by image analysis, if there is speck is crossed, then personnel corresponding to the image is defined as concern personnel, executes step C；Otherwise personnel corresponding to the facial image are defined as ordinary person, return step A；C: server by utilizing remote temperature detection device obtains the temperature of speck position；If the temperature of the speck position is in predetermined temperature range, determine that this speck for cigarette butt, concern personnel is changed and are defined as smoker, video camera described in server by utilizing takes smoker and surrounding image and/or video, for evidence obtaining of smoking；Otherwise concern personnel are changed and is defined as ordinary person；D: return step A.
Description
Technical field
The present invention relates to technical field of face recognition, and in particular to a kind of smoking evidence obtaining side based on recognition of face
Method, to collect evidence for the smoking of non-smoking area.
Background technique
" Smoking is harmful to your health " has been increasingly becoming national consensus, and on this basis, just gradually setting is more prohibited for country
Cigarette district domain, to reduce harm of the secondhand smoke to the public.But many non-smoking areas are just with signboards such as " no smoking " at present
The common people are reminded, fright effect well can not be played to smoker, therefore the taboo speech effect of non-smoking area and bad.
The patent of invention that number of patent application is 201210009281.8 discloses a kind of smoking inspection based on thermal-induced imagery
Examining system and device, comprising: the thermal infrared imager with holder, for acquiring the thermal-induced imagery of presumptive area；The infrared heat
As instrument is built-in with Visible-light CCD；The temperature data of control device, the thermal-induced imagery for acquiring to thermal infrared imager divides
Analysis, and smoking information is judged whether there is based on the analysis results；When judgement has smoking information, Visible-light CCD is controlled to institute
It states smoking information corresponding position to be captured, obtains smoking picture and/or video.Foregoing invention is merely according in thermal-induced imagery
Temperature Distribution obtains smoking target field, and determines smoking information according to the temperature duration of target field, but multiple for situation
For miscellaneous non-smoking area, Temperature Distribution is detected to region one by one, and require to detect the zone of action of cigarette butt size position
Temperature anomaly, be it is very difficult, to the more demanding of hardware device, realize that difficulty is very big.
Summary of the invention
The purpose of the present invention is to propose to a kind of the smoking evidence collecting method based on recognition of face, this kind smoking evidence collecting method cost
It is low, evidence obtaining accuracy is high, is easily achieved, be very suitable for the smoking evidence obtaining of non-smoking area.
Smoking evidence collecting method based on recognition of face of the invention includes the following steps:
A: using have face identification functions video camera shooting enter non-smoking area personnel face, obtain face and
The image of face peripheral region, and obtained image is sent to server；
B: server judges whether speck occurred in the face and its peripheral region by image analysis, if gone out
Speck is now crossed, then personnel corresponding to the facial image are defined as concern personnel, executes step C；If do not occurred bright
Personnel corresponding to the facial image are then defined as ordinary person, return step A by spot；
C: server by utilizing remote temperature detection device detects the face and face peripheral region of the concern personnel
Temperature Distribution obtains the temperature of speck position；If the temperature of the speck position is in predetermined temperature range, (100~200 are taken the photograph
Family name's degree), then determine that this speck for cigarette butt, concern personnel is changed and are defined as smoker, video camera described in server by utilizing is clapped
Lower smoker and surrounding image and/or video, for evidence obtaining of smoking；If the temperature of the speck position is not in pre-
Determine in temperature range, then concern personnel is changed and be defined as ordinary person；
D: return step A.
In above-mentioned smoking evidence collecting method, facial image is obtained first with the video camera with face identification functions,
To exclude the little area image of remaining and cigarette smoking relationship, reduce subsequent image analysis amount, reduces to service
The hardware capabilities demand of device；Then the facial image with speck is filtered out by the method for image analysis again, finds doubtful suction
The facial image of cigarette person finally recycles remote temperature detection device to detect the temperature of speck, determines smoker.Compared to existing
There is technology, the above method is not necessarily to carry out temperature detection to entire non-smoking area, greatly reduces hsrdware requirements, reduce required
Temperature detection time improves the accuracy of detection.
Further, determine whether that the method for speck occur is as follows in the step B:
B1, the image of the face and face peripheral region is converted into grayscale image first, and two-value is carried out to the image
Change processing, forms binary image, is subsequently filled the pixel lacked inside each connected domain in binary image, and formation has
Several figures of closed outline；
B2, the detection that circularity is carried out to the figure, the figure that only circularity is greater than predetermined value are just considered speck.
By the way that color image is converted to binary image, then obtain again in binary image with closed outline
Figure can greatly reduce operand, and improve precision and accuracy；In addition, according to cigarette butt speck generally near circular
Feature, the speck that cigarette butt formation is filtered out using circularity are more reasonable, quick.
B2, the detection that circularity is carried out to the figure, the detection formula of circularity are as follows:Wherein, Q
For circularity, S is speck area, and D is speck maximum width, the principle of above-mentioned circularity detection are as follows: compare the speck area with
Using its maximum width as the circular area of diameter, the two illustrates speck closer to round closer to (i.e. Q value is closer to 1).
Further, in the B2 step, after detecting that circularity is greater than the figure of predetermined value, also using pre-establishing
Difference shine cigarette butt feature templates library the concrete shape of the figure is screened, calculate the figure relative to each spy
The Bayes posterior probability for levying template library, the Bayes posterior probability for finding the figure relative to each feature templates library are maximum
Value, if the Bayes posterior probability maximum value exceeds predetermined value, then it is assumed that the figure is speck.By establishing feature templates
The screening of library and Bayes posterior probability, can further test pattern and cigarette butt shape the degree of approach, to improve cigarette butt
The accuracy of identification.
Further, in the step A, interval shooting enters the personnel of non-smoking area to the video camera to schedule
Face, as long as above-mentioned predetermined time interval setting it is reasonable, so that it may the case where reducing or avoiding missing inspection, and be spaced clap
It takes the photograph, the burden of server can be reduced, the hardware capabilities demand to server is reduced, to reduce cost.
Further, in the step A, the new personnel into non-smoking area are defined as newly into personnel；The step B
In, the image of the every Zhang Xinjin personnel of server analysis, server comes sampling analysis ordinary person's according to scheduled standard for manual sampling
Image.A possibility that detecting, smoking at least once since ordinary person has already passed through is lower, and server is not to ordinary people
Every human face photo of member all carries out image analysis, but the human face photo of sampling analysis ordinary person, can reduce to service
The hardware capabilities demand of device, to enable the server to cope with the smoking forensics analysis of more people.
Further, in the step C, server also judges the size of speck, only speck position by image analysis
The temperature set is in predetermined temperature range, and when the size of speck is in predetermined size range, just determines this speck for cigarette
Otherwise head determines that the speck is not cigarette butt.Since speck may be what other objects were formed, such as color lamp for tool of joking etc., lead to
The accuracy of detection can be improved in the double check of excess temperature and size.Such as say, the area of adult face is generally 300-
400 square centimeters, and the area of cigarette butt is generally 1 square centimeter or so, by comparing speck area and face area, Ji Kehuo
Whether the size of person's speck meets the feature of cigarette butt, (such as says if speck area is excessive and occupies a few minutes of face area
One of), then can affirm the speck not is that cigarette butt is formed.The measuring and calculating of above-mentioned speck and face area is all to utilize pixel method meter
It calculates.
Specifically, the remote temperature detection device is infrared thermal imager, forms people by shooting face location
The thermal-induced imagery of face and its near zone, and then the Temperature Distribution of human face region is obtained, obtain the actual temp of speck position.
Further, the video camera is fixedly connected with remote temperature detection device and constitutes detection agency, the detection
Mechanism has multiple, and is directed at non-smoking area from different perspectives respectively；Or the video camera and remote temperature detection device are fixed
It connects and is set up on rotatable holder, to reduce shooting blind angle amount that may be present, to improve the standard of cigarette smoking detection
True rate.
Further, the server is also connected with the alarming device for being set to non-smoking area, in the step C, service
Device issues alarm signal after determining someone's smoking, through alarming device, to remind smoker to stop cigarette smoking at once.
Further, the server is pre-stored with several face pictures corresponding with known people；The step C
In, server after determining someone's smoking, by the face picture of the face picture of smoker and pre-stored known people into
Row compares, and includes the smoker by the alarm signal that alarming device is issued if smoker is known people
Name.Since above-mentioned alarm signal includes the name of smoker, the vertically hung scroll relative to " no smoking " is more targeted
With warning meaning, smoker can more effectively be promoted to stop smoking.
Further, the alarming device is loudspeaker and/or display screen, directly can play or show smoker
Name.
The present invention reduces the requirement to related hardware and hardware cost by reasonable, evidence collecting method of cleverly smoking, and
The accuracy for improving cigarette smoking detection is very suitable for the smoking evidence obtaining of non-smoking area.
Detailed description of the invention
Fig. 1 is the flow chart of the smoking evidence collecting method based on recognition of face of embodiment 1.
Specific embodiment
It is for example related each to a specific embodiment of the invention by the description to embodiment below against attached drawing
The shape of component, construction, the mutual alignment between each section and connection relationship, the effect of each section and working principle etc. are made into one
The detailed description of step.
Embodiment 1:
The present embodiment proposes a kind of smoking evidence collecting method based on recognition of face, this kind smoke evidence collecting method it is at low cost,
Evidence obtaining accuracy is high, is easily achieved, and is very suitable for the smoking evidence obtaining of non-smoking area.
As shown in Figure 1, the smoking evidence collecting method based on recognition of face of the present embodiment includes the following steps:
A: using have face identification functions video camera shooting enter non-smoking area personnel face, obtain face and
The image of face peripheral region, and obtained image is sent to server；
B: server judges whether speck occurred in the face and its peripheral region by image analysis, if gone out
Speck is now crossed, then personnel corresponding to the facial image are defined as concern personnel, executes step C；If do not occurred bright
Personnel corresponding to the facial image are then defined as ordinary person, return step A by spot；
Wherein, step B comprises the following specific steps that:
B1, the image of the face and face peripheral region is converted into grayscale image first, and two-value is carried out to the image
Change processing, forms binary image, is subsequently filled the pixel lacked inside each connected domain in binary image, and formation has
Several figures of closed outline；
B2, the detection that circularity is carried out to the figure, the detection formula of circularity are as follows:Wherein, Q
For circularity, S is speck area, and D is speck maximum width, the principle of above-mentioned circularity detection are as follows: compare the speck area with
Using its maximum width as the circular area of diameter, the two illustrates speck closer to round closer to (i.e. Q value is closer to 1).
If the circularity of figure is less than or equal to predetermined value, it is not considered as that the figure is speck；If the circularity of figure is greater than predetermined value,
Then the concrete shape of the figure is screened using the feature templates library of the luminous cigarette butt of the difference pre-established, calculates the figure
Bayes posterior probability of the shape relative to each feature templates library finds pattra leaves of the figure relative to each feature templates library
This posterior probability maximum value, if the Bayes posterior probability maximum value exceeds predetermined value, then it is assumed that the figure is speck；
The method for building up in feature templates library is as follows: firstly, various different conditions (such as are said the positive angle of cigarette butt, side
The cigarette butt of the different angles such as angle, depression angle and different cultivars, cigarette butt of different brightness etc.) cigarette butt shoot into figure
Piece finds the minimum circumscribed rectangle in cigarette butt region in picture；The length of the minimum circumscribed rectangle and width are divided into N equal part again,
Constitute N × N number of region；Finally, calculating the accounting of high bright spot in each region, obtainWherein, Wi is each cell
The characteristic value in domain, Sw are white pixel point number, and Sall is the pixel sum of zonule；
By feature extraction, the form of cigarette butt picture can finally be characterized by the eigenmatrix of following N × N:
Pass through following Bayesian inference formulaIt is big to circularity in B2 step
It is screened in the figure of predetermined value:
Wherein, P (ωi| X) it is posterior probability of the figure for the i-th class sample database, P (ωi) be sample database priori
Probability, and P (X | ωi) it is conditional probability density, X is the feature vector of sample to be tested, and thought is, general according to the priori of certain classification
The probability density of rate and feature vector, X in certain category feature space, calculates the probability that X belongs to the category；
For each classification ωi,Value be determining, the then posterior probability of feature vector, X
Hi(x) are as follows: Hi(x)=P (X | ωi)P(ωi)；
In turn, pass through publicityCalculate prior probability P (ωi), wherein niFor sample in each sample set
Quantity, N are the total sample number of all sample sets, therefore, conditional probability density P (X | ωi) can be calculated by normal distribution:Wherein, X is N-dimensional feature vector, μ N
Tie up mean vector, S=E [(X- μ) (X- μ)T] it is N-dimensional covariance matrix；Take Hi(x) logarithm can be obtained as discriminant function:
The figure that circularity in the B2 step is greater than predetermined value is substituted into above formula as X, calculates figure relative to each
The maximum value of the Bayes posterior probability in feature templates libraryIf the shellfish
This posterior probability maximum value of leaf exceeds predetermined value, then it is assumed that the figure is speck；
C: server by utilizing remote temperature detection device detects the face and face peripheral region of the concern personnel
Temperature Distribution obtains the temperature of speck position；If the temperature of the speck position is in predetermined temperature range, determine that this is bright
Spot is cigarette butt, and concern personnel are changed and are defined as smoker, video camera described in server by utilizing takes smoker and its week
The image and/or video enclosed, for evidence obtaining of smoking；If the temperature of the speck position is not in predetermined temperature range,
Concern personnel are changed and are defined as ordinary person；
In the present embodiment, server, which is also connected with, is set to the alarming device of non-smoking area (alarming device is loudspeaker
And/or display screen), server is pre-stored with several face pictures corresponding with known people, and server is determining someone's suction
After cigarette, alarm signal is issued by alarming device, to remind smoker to stop cigarette smoking at once；Server is also by smoking people
The face picture of member is compared with the face picture of pre-stored known people, if smoker is known people, leads to
It crosses the alarm signal that alarming device is issued and includes the name of the smoker, such as say that " XXX please stop using loudspeaker broadcasting
The phonetic warning of only smoking ", or the name for showing smoker is recycled with display.Since above-mentioned alarm signal includes smoking people
The name of member, therefore the vertically hung scroll relative to simple " no smoking " more targetedly and warns meaning, can more effectively promote
Smoker stops smoking；
D: return step A.
In above-mentioned smoking evidence collecting method, facial image is obtained first with the video camera with face identification functions,
To exclude the little area image of remaining and cigarette smoking relationship, reduce subsequent image analysis amount, reduces to service
The hardware capabilities demand of device；Then the facial image with speck is filtered out by the method for image analysis again, finds doubtful suction
The facial image of cigarette person finally recycles remote temperature detection device to detect the temperature of speck, determines smoker.Compared to existing
There is technology, the above method is not necessarily to carry out temperature detection to entire non-smoking area, greatly reduces hsrdware requirements, reduce required
Temperature detection time improves the accuracy of detection.
Further, in the step A, interval shooting enters the personnel of non-smoking area to the video camera to schedule
Face, as long as above-mentioned predetermined time interval setting it is reasonable, so that it may the case where reducing or avoiding missing inspection, and be spaced clap
It takes the photograph, the burden of server can be reduced, the hardware capabilities demand to server is reduced, to reduce cost.
In the present embodiment, in the step A, the new personnel into non-smoking area are defined as newly into personnel；The step
In rapid B, the image of the every Zhang Xinjin personnel of server analysis, server carrys out sampling analysis ordinary person according to scheduled standard for manual sampling
Image.A possibility that detecting, smoking at least once since ordinary person has already passed through is lower, and server is not to common
Every human face photo of personnel all carries out image analysis, but the human face photo of sampling analysis ordinary person, can reduce to clothes
The hardware capabilities demand of business device, to enable the server to cope with the smoking forensics analysis of more people.
In the step C, server also judges the size of speck by image analysis, only at the temperature of speck position
In in predetermined temperature range, and when the size of speck is in predetermined size range, just determine that this speck for cigarette butt, otherwise determines
The speck is not cigarette butt.Since speck may be what other objects were formed, such as color lamp for tool of joking etc., pass through temperature and size
Double check, the accuracy of detection can be improved.Such as say, the area of adult face is generally 300-400 square centimeters, and
The area of cigarette butt is generally 1 square centimeter or so, by comparing speck area and face area, can or the speck size
Whether meet the feature of cigarette butt, if speck area is excessive (such as say and occupy the part of face area), can agree
The fixed speck is not that cigarette butt is formed.The measuring and calculating of above-mentioned speck and face area is calculated using pixel method.
The present embodiment uses remote temperature detection device for infrared thermal imager, forms face by shooting face location
And its thermal-induced imagery of near zone, and then the Temperature Distribution of human face region is obtained, obtain the actual temp of speck position.It takes the photograph
Camera is fixedly connected with remote temperature detection device and constitutes detection agency, the detection agency have it is multiple, and respectively from difference
Theta alignment non-smoking area, to reduce shooting blind angle amount that may be present, to improve the accuracy rate of cigarette smoking detection.
The present invention is exemplarily described above in conjunction with attached drawing, it is clear that the present invention specifically designs not by aforesaid way
Limitation, if use the improvement for the various unsubstantialities that conception and technical scheme of the invention carry out, or it is not improved will
Conception and technical scheme of the invention directly apply to other occasions, within the scope of the present invention.
Claims (10)
1. a kind of smoking evidence collecting method based on recognition of face, it is characterised in that include the following steps:
A: enter the face of the personnel of non-smoking area using the video camera shooting with face identification functions, obtain face and face
The image of peripheral region, and obtained image is sent to server；
B: server judges whether speck occurred in the face and its peripheral region, if there is mistake by image analysis
Personnel corresponding to the facial image are then defined as concern personnel by speck, execute step C；If there is not speck,
Personnel corresponding to the facial image are defined as ordinary person, return step A；
C: server by utilizing remote temperature detection device detects the face of the concern personnel and the temperature of face peripheral region
Distribution, obtains the temperature of speck position；If the temperature of the speck position is in predetermined temperature range, determine that this speck is
Concern personnel are changed and are defined as smoker by cigarette butt, and video camera described in server by utilizing takes smoker and surrounding
Image and/or video, for evidence obtaining of smoking；If the temperature of the speck position is not in predetermined temperature range, should
Concern personnel, which change, is defined as ordinary person；
D: return step A.
2. the smoking evidence collecting method according to claim 1 based on recognition of face, it is characterised in that determine in the step B
The method for speck whether occur is as follows:
B1, the image of the face and face peripheral region is converted into grayscale image first, and the image is carried out at binaryzation
Reason forms binary image, is subsequently filled the pixel lacked inside each connected domain in binary image, and being formed has closing
Several figures of profile；
B2, the detection that circularity is carried out to the figure, the figure that only circularity is greater than predetermined value are just considered speck.
3. the smoking evidence collecting method according to claim 2 based on recognition of face, it is characterised in that in the B2 step, when
After detecting that circularity is greater than the figure of predetermined value, also using the feature templates library of the luminous cigarette butt of the difference pre-established to the figure
The concrete shape of shape is screened, and is calculated Bayes posterior probability of the figure relative to each feature templates library, is found institute
Bayes posterior probability maximum value of the figure relative to each feature templates library is stated, if the Bayes posterior probability maximum value is super
Predetermined value out, then it is assumed that the figure is speck.
4. the smoking evidence collecting method according to claim 1 or 2 or 3 based on recognition of face, it is characterised in that the step A
In, the video camera to schedule interval shooting enter non-smoking area personnel face.
5. the smoking evidence collecting method according to claim 4 based on recognition of face, it is characterised in that, will in the step A
The new personnel into non-smoking area are defined as newly into personnel；In the step B, the image of the every Zhang Xinjin personnel of server analysis,
Server carrys out the image of sampling analysis ordinary person according to scheduled standard for manual sampling.
6. the smoking evidence collecting method according to claim 4 based on recognition of face, it is characterised in that in the step C, clothes
Business device also judges that the size of speck, the only temperature of speck position are in predetermined temperature range by image analysis, and bright
When the size of spot is in predetermined size range, this speck is determined just for cigarette butt, otherwise determine that the speck is not cigarette butt.
7. the smoking evidence collecting method according to claim 6 based on recognition of face, it is characterised in that the remote temperature is visited
Survey device is infrared thermal imager.
8. the smoking evidence collecting method according to claim 6 based on recognition of face, it is characterised in that the video camera and remote
Journey temperature detection device is fixedly connected and constitutes detection agency, and the detection agency has multiple, and is aligned from different perspectives respectively
Non-smoking area；Or the video camera is fixedly connected with remote temperature detection device and is set up on rotatable holder.
9. the smoking evidence collecting method according to claim 6 based on recognition of face, it is characterised in that the server also connects
It is connected to the alarming device for being set to non-smoking area, in the step C, server passes through alarming device after determining someone's smoking
Issue alarm signal.
10. the smoking evidence collecting method according to claim 9 based on recognition of face, it is characterised in that the server prestores
Contain several face pictures corresponding with known people；In the step C, server will smoke after determining someone's smoking
The face picture of personnel is compared with the face picture of pre-stored known people, if smoker is known people,
It include the name of the smoker by the alarm signal that alarming device is issued.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811556670.6A CN109711307A (en) | 2018-12-19 | 2018-12-19 | A kind of smoking evidence collecting method based on recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811556670.6A CN109711307A (en) | 2018-12-19 | 2018-12-19 | A kind of smoking evidence collecting method based on recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109711307A true CN109711307A (en) | 2019-05-03 |
Family
ID=66256871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811556670.6A Pending CN109711307A (en) | 2018-12-19 | 2018-12-19 | A kind of smoking evidence collecting method based on recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711307A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490098A (en) * | 2019-07-31 | 2019-11-22 | 恒大智慧科技有限公司 | Smoking behavior automatic testing method, equipment and the readable storage medium storing program for executing of community user |
| CN110490090A (en) * | 2019-07-29 | 2019-11-22 | 恒大智慧科技有限公司 | Smoking detection method, system and its storage medium based on intelligence community |
| CN110503005A (en) * | 2019-07-29 | 2019-11-26 | 恒大智慧科技有限公司 | Smoking detection method, system and its storage medium based on intelligence community |
| CN111326225A (en) * | 2020-02-17 | 2020-06-23 | 深圳市白美科技有限公司 | Smoking health management and supervision platform |
| CN111553275A (en) * | 2020-04-28 | 2020-08-18 | 厦门博海中天信息科技有限公司 | Smoking monitoring method, module, device and medium based on AI and thermal imaging |
| CN111797757A (en) * | 2020-06-30 | 2020-10-20 | 图为信息科技(深圳)有限公司 | Smoking behavior monitoring method and system |
| CN112200092A (en) * | 2020-10-13 | 2021-01-08 | 深圳龙岗智能视听研究院 | Intelligent smoking detection method based on variable-focus movement of dome camera |
| CN113343859A (en) * | 2021-06-10 | 2021-09-03 | 浙江大华技术股份有限公司 | Smoking behavior detection method and device, storage medium and electronic device |
| CN113505715A (en) * | 2021-07-16 | 2021-10-15 | 厦门柏事特信息科技有限公司 | Vehicle window parabolic detection method based on real-time video |
| CN113761980A (en) * | 2020-06-04 | 2021-12-07 | 杭州海康威视系统技术有限公司 | Smoking detection method and device, electronic equipment and machine-readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519605A (en) * | 2012-01-12 | 2012-06-27 | 安徽大学 | Smoking detection system and device based on infrared thermal image |
| CN104053564A (en) * | 2012-01-17 | 2014-09-17 | 皇家飞利浦有限公司 | Heating system for heating living being |
| CN104978829A (en) * | 2015-06-24 | 2015-10-14 | 国家电网公司 | Indoor smoking monitoring control method and system |
| CN105120215A (en) * | 2015-08-19 | 2015-12-02 | 苏州市新瑞奇节电科技有限公司 | Method for monitoring smoking in workshop on the basis of image analysis |
| CN105225428A (en) * | 2015-09-14 | 2016-01-06 | 国家电网公司 | A kind of indoor smoke detection alarm method and system |
| CN106991417A (en) * | 2017-04-25 | 2017-07-28 | 华南理工大学 | A kind of visual projection's interactive system and exchange method based on pattern-recognition |
| CN107358630A (en) * | 2017-07-10 | 2017-11-17 | 长春工程学院 | A kind of ccd image processing localization method and removable welding fume extractor |
| CN108577364A (en) * | 2018-05-30 | 2018-09-28 | 红塔烟草(集团)有限责任公司 | A kind of Portable tobacco cigarette displaying diostribution device |
-
2018
- 2018-12-19 CN CN201811556670.6A patent/CN109711307A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519605A (en) * | 2012-01-12 | 2012-06-27 | 安徽大学 | Smoking detection system and device based on infrared thermal image |
| CN104053564A (en) * | 2012-01-17 | 2014-09-17 | 皇家飞利浦有限公司 | Heating system for heating living being |
| CN104978829A (en) * | 2015-06-24 | 2015-10-14 | 国家电网公司 | Indoor smoking monitoring control method and system |
| CN105120215A (en) * | 2015-08-19 | 2015-12-02 | 苏州市新瑞奇节电科技有限公司 | Method for monitoring smoking in workshop on the basis of image analysis |
| CN105225428A (en) * | 2015-09-14 | 2016-01-06 | 国家电网公司 | A kind of indoor smoke detection alarm method and system |
| CN106991417A (en) * | 2017-04-25 | 2017-07-28 | 华南理工大学 | A kind of visual projection's interactive system and exchange method based on pattern-recognition |
| CN107358630A (en) * | 2017-07-10 | 2017-11-17 | 长春工程学院 | A kind of ccd image processing localization method and removable welding fume extractor |
| CN108577364A (en) * | 2018-05-30 | 2018-09-28 | 红塔烟草(集团)有限责任公司 | A kind of Portable tobacco cigarette displaying diostribution device |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490090A (en) * | 2019-07-29 | 2019-11-22 | 恒大智慧科技有限公司 | Smoking detection method, system and its storage medium based on intelligence community |
| CN110503005A (en) * | 2019-07-29 | 2019-11-26 | 恒大智慧科技有限公司 | Smoking detection method, system and its storage medium based on intelligence community |
| CN110490098A (en) * | 2019-07-31 | 2019-11-22 | 恒大智慧科技有限公司 | Smoking behavior automatic testing method, equipment and the readable storage medium storing program for executing of community user |
| CN111326225A (en) * | 2020-02-17 | 2020-06-23 | 深圳市白美科技有限公司 | Smoking health management and supervision platform |
| CN111553275A (en) * | 2020-04-28 | 2020-08-18 | 厦门博海中天信息科技有限公司 | Smoking monitoring method, module, device and medium based on AI and thermal imaging |
| CN113761980A (en) * | 2020-06-04 | 2021-12-07 | 杭州海康威视系统技术有限公司 | Smoking detection method and device, electronic equipment and machine-readable storage medium |
| CN113761980B (en) * | 2020-06-04 | 2024-03-01 | 杭州海康威视系统技术有限公司 | Smoking detection method, smoking detection device, electronic equipment and machine-readable storage medium |
| CN111797757A (en) * | 2020-06-30 | 2020-10-20 | 图为信息科技(深圳)有限公司 | Smoking behavior monitoring method and system |
| CN112200092A (en) * | 2020-10-13 | 2021-01-08 | 深圳龙岗智能视听研究院 | Intelligent smoking detection method based on variable-focus movement of dome camera |
| CN113343859A (en) * | 2021-06-10 | 2021-09-03 | 浙江大华技术股份有限公司 | Smoking behavior detection method and device, storage medium and electronic device |
| CN113505715A (en) * | 2021-07-16 | 2021-10-15 | 厦门柏事特信息科技有限公司 | Vehicle window parabolic detection method based on real-time video |
| CN113505715B (en) * | 2021-07-16 | 2024-03-22 | 厦门柏事特信息科技有限公司 | A vehicle window parabola detection method based on real-time video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711307A (en) | A kind of smoking evidence collecting method based on recognition of face | |
| US12014571B2 (en) | Method and apparatus with liveness verification | |
| US9922238B2 (en) | Apparatuses, systems, and methods for confirming identity | |
| US9858474B2 (en) | Object tracking and best shot detection system | |
| CN104217201B (en) | Method for evaluating image quality, method for generating a file, computer program product, user interface, data file and electronic device | |
| JP5287333B2 (en) | Age estimation device | |
| US7218759B1 (en) | Face detection in digital images | |
| CN103294994B (en) | For the device of face is recognized based on environmental suitability | |
| CN106169071B (en) | An attendance method and system based on dynamic face and badge recognition | |
| CN109101871A (en) | A kind of living body detection device based on depth and Near Infrared Information, detection method and its application | |
| US20090135188A1 (en) | Method and system of live detection based on physiological motion on human face | |
| TW201401186A (en) | System and method for identifying human face | |
| CN102262727A (en) | Method for monitoring face image quality at client acquisition terminal in real time | |
| KR20190089387A (en) | Liveness test method and apparatus | |
| WO2016084072A1 (en) | Anti-spoofing system and methods useful in conjunction therewith | |
| CN110390229B (en) | Face picture screening method and device, electronic equipment and storage medium | |
| US11080557B2 (en) | Image authentication apparatus, method, and storage medium using registered image | |
| JP2000259814A (en) | Image processor and method therefor | |
| CN104091176A (en) | Technology for applying figure and head portrait comparison to videos | |
| CN108734067A (en) | A kind of authentication method, system and camera that the testimony of a witness compares | |
| JP2010122746A (en) | Image monitoring device | |
| WO2021217764A1 (en) | Human face liveness detection method based on polarization imaging | |
| JP2011150497A (en) | Person identification device, person identification method, and software program thereof | |
| JP2012185769A (en) | Authentication device, authentication method, authentication program, and storage medium | |
| Waris et al. | Analysis of textural features for face biometric anti-spoofing |
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 |
Application publication date: 20190503 |
|
| RJ01 | Rejection of invention patent application after publication |