CN113392710A - Intelligent recognition method and system for smoking behavior - Google Patents
Intelligent recognition method and system for smoking behavior Download PDFInfo
- Publication number
- CN113392710A CN113392710A CN202110543604.0A CN202110543604A CN113392710A CN 113392710 A CN113392710 A CN 113392710A CN 202110543604 A CN202110543604 A CN 202110543604A CN 113392710 A CN113392710 A CN 113392710A
- Authority
- CN
- China
- Prior art keywords
- module
- unit
- warning
- behavior
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000006399 behavior Effects 0.000 title claims abstract description 112
- 230000000391 smoking effect Effects 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 15
- 239000000779 smoke Substances 0.000 claims abstract description 86
- 238000012544 monitoring process Methods 0.000 claims abstract description 56
- 239000007921 spray Substances 0.000 claims abstract description 23
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 12
- 238000005507 spraying Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000006698 induction Effects 0.000 claims description 4
- 241000208125 Nicotiana Species 0.000 abstract 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 abstract 1
- 238000007689 inspection Methods 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 19
- 230000000694 effects Effects 0.000 description 16
- 235000019504 cigarettes Nutrition 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012706 support-vector machine Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- 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
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
Abstract
本发明涉及智能识别技术，具体涉及一种吸烟行为智能识别方法及系统；通过监控模块实时拍摄视频，并将视频生成图片，而后传送至识别模块进行识别，若存在吸烟行为，将吸烟行为结论传送至警示模块，警示模块生成语音提示信息，并通过扬声器播报；监控模块还感应环境中烟雾浓度和温度，并将感应数据传送至识别模块，识别模块判断出是否发生火灾，而后将火灾行为结论发送至警示模块，警示模块控制喷淋头进行喷水，及时灭火；记录模块存储监控模块、识别模块和警示模块的历史运行数据，便于后期追溯，进而采用图像识别进行判断，再结合传感器监控，避免漏检，促使控烟效果更佳。
The invention relates to intelligent identification technology, in particular to a method and system for intelligent identification of smoking behavior; real-time video is captured by a monitoring module, and a picture is generated from the video, which is then transmitted to an identification module for identification, and if there is smoking behavior, the smoking behavior conclusion is transmitted. To the warning module, the warning module generates voice prompt information and broadcasts it through the loudspeaker; the monitoring module also senses the smoke concentration and temperature in the environment, and transmits the sensing data to the identification module. The identification module judges whether a fire has occurred, and then sends the fire behavior conclusion. To the warning module, the warning module controls the sprinkler to spray water and put out the fire in time; the recording module stores the historical operation data of the monitoring module, the identification module and the warning module, which is convenient for later traceability, and then uses image recognition for judgment, and then combines sensor monitoring to avoid Missing inspections can promote better tobacco control.
Description
Technical Field
The invention relates to the technical field of intelligent identification, in particular to an intelligent identification method and system for smoking behaviors.
Background
Smoking behavior is harmful to the health of smokers and the health of people around, smoking in smoking forbidden areas may cause hidden dangers such as fire due to image safety production.
The existing smoke control technical means mainly use a smoke sensor as a main part, but smoke is controlled by the smoke sensor, so that the problem of serious missed detection exists, when the indoor environment is slightly open, smoke generated by smoking of one or a few people is less, and the smoke sensor cannot detect the smoke and the missed detection results in limited smoke control effect.
Disclosure of Invention
The invention aims to provide an intelligent recognition method and system for smoking behavior, and aims to solve the technical problem that in the prior art, smoke control by a smoke sensor is seriously missed to detect, so that the smoke control effect is limited.
In order to achieve the purpose, the smoking behavior intelligent identification system comprises a monitoring module, an identification module, a warning module and a recording module;
the monitoring module is respectively connected with the identification module and the recording module, the identification module is respectively connected with the warning module and the recording module, and the warning module is connected with the recording module;
the monitoring module is used for shooting videos, preprocessing the videos to generate pictures, sensing the smoke concentration and temperature in the environment, and finally transmitting the pictures and sensing data to the identification module and the recording module;
the identification module is used for acquiring the picture and the induction data, judging whether smoking behaviors exist or not through the picture, judging whether fire disasters occur or not through the induction data, finally generating a behavior conclusion, and transmitting the behavior conclusion to the warning module and the recording module;
the warning module is used for acquiring the behavior conclusion, generating a corresponding smoke control instruction, uploading the smoke control instruction to the recording module, generating corresponding warning information according to the smoke control instruction and sending the warning information to a manager;
the recording module is used for acquiring and storing the data uploaded by the monitoring module, the identification module and the warning module.
The monitoring module shoots a video of a monitored area in real time through a high-definition camera, preprocesses the shot video to generate a picture, transmits the picture to the identification module for identification, judges whether smoking behavior exists or not, transmits a smoking behavior conclusion to the warning module if smoking behavior exists, and generates voice prompt information to warn smoking through the warning module; the monitoring module senses the smoke concentration and temperature in the environment through a smoke sensor and a temperature sensor and transmits sensing data to the identification module, the identification module judges whether a fire disaster occurs or not and then sends a fire disaster behavior conclusion to the warning module, and the warning module controls the device to spray and extinguish the fire; the recording module stores the monitoring module, the identification module and the warning module historical data, and facilitates later-stage tracing.
The monitoring module comprises a camera unit and a picture generation unit, the camera unit is respectively connected with the picture generation unit and the recording module, and the picture generation unit is connected with the identification module;
the camera shooting unit is used for shooting a video and uploading video data to the picture generating unit and the recording module;
the picture generation unit is used for acquiring the video data, preprocessing the video data, generating a picture and uploading the picture to the identification module.
The image pickup unit is composed of a high-definition camera, shoots high-definition images and uploads the high-definition images to the image generation unit, and the image generation unit preprocesses the shot images, generates images similar to smoking actions and uploads the images to the identification module.
The monitoring module comprises a camera unit and a picture generation unit, the camera unit is respectively connected with the picture generation unit and the recording module, and the picture generation unit is connected with the identification module;
the camera shooting unit is used for shooting a video and uploading video data to the picture generating unit and the recording module;
the picture generation unit is used for acquiring the video data, preprocessing the video data, generating a picture and uploading the picture to the identification module.
The sensing unit consists of a smoke sensor and a temperature sensor, senses the smoke concentration and temperature in the environment and transmits data to the identification module.
The identification module comprises an action identification unit and a fire identification unit, the action identification unit is respectively connected with the picture generation unit and the warning module, and the fire identification unit is respectively connected with the sensing unit and the warning module;
the action recognition unit is used for acquiring the picture, identifying the smoking behavior, generating a smoking behavior conclusion and uploading the conclusion to the warning module;
the fire recognition unit is used for acquiring smoke concentration data and temperature data in the environment, identifying fire behaviors, generating fire behavior conclusions and uploading the fire behavior conclusions to the warning module.
The action recognition unit obtains pictures of smoking actions, judges whether smoking actions exist or not through picture processing, uploads a recognition conclusion to the warning module, and the fire recognition unit judges whether fire occurs or not according to the environmental smoke concentration and the environmental temperature and uploads the recognition conclusion to the warning module.
The warning module comprises a voice prompt unit and a spraying unit, the voice prompt unit is connected with the action recognition unit, and the spraying unit is connected with the fire recognition unit;
the voice prompt unit is used for acquiring the smoking behavior conclusion, generating voice prompt information and broadcasting the voice prompt information through a loudspeaker;
and the spraying unit is used for acquiring the fire behavior conclusion, generating a control instruction and controlling the spray header to spray water.
The voice prompt unit obtains a smoking behavior conclusion, generates voice prompt information, broadcasts voice through the loudspeaker to prompt smoking, and the spraying unit obtains a fire behavior conclusion, controls the spraying head to spray water and timely extinguishes fire.
An intelligent recognition method for smoking behaviors comprises the following steps:
shooting a video through a monitoring module, preprocessing the video to generate a picture, sensing the smoke concentration and temperature in the environment, and finally transmitting the picture and sensing data to an identification module and a recording module;
the picture is identified through the identification module, whether smoking behaviors exist or not is judged, whether fire disasters occur or not is judged according to the sensing data, and finally a behavior conclusion is generated and sent to the warning module and the recording module;
the behavior conclusion is obtained through the warning module, a corresponding smoke control instruction is generated to carry out voice prompt or spray fire extinguishing, and the smoke control instruction is uploaded to the recording module;
the recording module acquires and stores data uploaded by the monitoring module, the identification module and the warning module.
Firstly, the monitoring module monitors in real time and uploads monitoring data to the recognition module for recognition, the recognition module recognizes smoking behavior or fire behavior and transmits a recognition conclusion to the warning module, when the warning module receives the smoking behavior conclusion, the speaker is controlled to send out voice prompt for smoke suppression, when the warning module receives the fire behavior conclusion, the spray header is controlled to spray water for fire suppression, and the recording module records and stores the operation data of each module in real time, so that the follow-up is facilitated.
The behavior conclusion is obtained through the warning module, a corresponding smoke control instruction is generated to carry out voice prompt or spray fire extinguishing, and the smoke control instruction is uploaded to the recording module, and the method further comprises the following steps:
and the warning module simultaneously generates corresponding warning information according to the acquired behavior conclusion and sends the warning information to a manager.
The warning module also generates corresponding warning information according to the behavior conclusion and sends the warning information to the manager, so that the manager can conveniently make corresponding measures in time.
According to the intelligent identification method and system for the smoking behavior, videos of a monitoring area are shot in real time through the monitoring module, the videos are preprocessed to generate pictures, then the pictures are transmitted to the identification module to be identified, whether the smoking behavior exists or not is judged, if the smoking behavior exists, a smoking behavior conclusion is transmitted to the warning module, and the warning module generates voice prompt information and broadcasts the voice prompt information through a loudspeaker; the monitoring module senses the smoke concentration and temperature in the environment through a smoke sensor and a temperature sensor and transmits sensing data to the identification module, the identification module judges whether a fire disaster occurs or not and then sends a fire disaster behavior conclusion to the warning module, and the warning module controls the spray header to spray water and extinguish the fire in time; the recording module stores the monitoring module, the identification module and the historical operating data of the warning module, so that the tracking in the later period is facilitated, image recognition is adopted for judgment, and the detection omission is avoided by combining with sensor monitoring, so that the smoke control effect is better.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an intelligent smoking behavior recognition system of the present invention.
Fig. 2 is a schematic structural diagram of the monitoring module of the present invention.
Fig. 3 is a schematic structural diagram of an identification module of the present invention.
Fig. 4 is a schematic structural diagram of the warning module of the present invention.
Fig. 5 is a step diagram of the intelligent smoking behavior recognition method of the present invention.
The system comprises a monitoring module, a 2-recognition module, a 3-warning module, a 4-recording module, a 11-camera unit, a 12-picture generation unit, a 13-sensing unit, a 21-action recognition unit, a 22-fire recognition unit, a 23-face recognition unit, a 31-voice prompt unit, a 32-spraying unit and a 33-communication unit.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the description of the present invention, it is to be understood that, in the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Referring to fig. 1 to 4, the present invention provides an intelligent recognition system for smoking behavior, which includes a monitoring module 1, a recognition module 2, an alarm module 3 and a recording module 4;
the monitoring module 1 is respectively connected with the identification module 2 and the recording module 4, the identification module 2 is respectively connected with the warning module 3 and the recording module 4, and the warning module 3 is connected with the recording module 4;
the monitoring module 1 is used for shooting a video, preprocessing the video to generate a picture, sensing the smoke concentration and temperature in the environment, and finally transmitting the picture and sensing data to the identification module 2 and the recording module 4;
the identification module 2 is configured to obtain the picture and the sensing data, judge whether a smoking behavior exists through the picture, judge whether a fire occurs through the sensing data, finally generate a behavior conclusion, and transmit the behavior conclusion to the warning module 3 and the recording module 4;
the warning module 3 is used for acquiring the behavior conclusion, generating a corresponding smoke control instruction, uploading the smoke control instruction to the recording module 4, generating corresponding warning information according to the smoke control instruction, and sending the warning information to a manager;
the recording module 4 is configured to acquire and store data uploaded by the monitoring module 1, the identification module 2, and the warning module 3.
In the embodiment, firstly, a high-definition camera is installed in a monitoring area, the monitoring module 1 shoots videos of the monitoring area in real time through the high-definition camera, preprocesses the shot videos to generate pictures, then sends the action pictures to the recognition module 2, the recognition module 2 recognizes the action pictures, identifies smoking behaviors, generates smoking behavior conclusions, and simultaneously uploads the smoking behavior conclusions to the warning module 3, the warning module 3 generates a smoke control instruction according to the smoking behavior conclusions, controls a loudspeaker to send out voice prompts to warn smokers to extinguish cigarettes, the monitoring module 1 further obtains smoke concentration and temperature in the environment through a smoke sensor and a temperature sensor installed in the monitoring area, uploads the obtained sensing data to the recognition module 2, and the recognition module 2 obtains the smoke concentration and temperature through a preset range value, judge that the smog concentration is up to standard or the temperature is up to standard, and then reach the conflagration action conclusion, and reach the conclusion warning module 3, warning module 3 generates corresponding accuse cigarette instruction, and the shower head of control intercommunication water source sprays water, plays the effect of in time putting out a fire, warning module 3 still generates corresponding warning information according to the action conclusion of acquireing, conveys to managers, is convenient for managers in time to carry out the accuse cigarette, record module 4 real-time recording and storage monitor module 1, identification module 2 with the historical data of warning module 3 is convenient for the later stage to be traceed back, and then can effectively discern the smoking action, and the accuse cigarette effect is better, can also discern the conflagration action simultaneously, in time puts out a fire, reduces the loss, makes user experience feel better, improves the accuse cigarette effect.
Further, referring to fig. 2, the monitoring module 1 includes a camera unit 11 and a picture generating unit 12, the camera unit 11 is connected to the picture generating unit 12 and the recording module 4, respectively, and the picture generating unit 12 is connected to the identification module 2;
the camera unit 11 is configured to take a video and upload video data to the picture generation unit 12 and the recording module 4;
the picture generating unit 12 is configured to acquire the video data, preprocess the video data, generate a picture, and upload the picture to the identification module 2.
In this embodiment, the camera unit 11 is composed of a plurality of high-definition cameras, is installed in a monitored area, and is configured to take a video of the monitored area, upload the video data to the recording module 4 for storage, and upload the video data to the picture generating unit 12 for further processing; the picture generation unit 12 preprocesses the video, removes noise and gaps in the video by means of median filtering, morphological operation and the like to reduce the influence of environment and illumination, optimizes a binary image, generates a picture through software analysis, and uploads the picture to the recognition module 2, so that a foundation is made for subsequent feature extraction, and the smoke control effect is improved.
Further, referring to fig. 2, the monitoring module 1 further includes a sensing unit 13, and the sensing unit 13 is connected to the identification module 2;
the sensing unit 13 is configured to sense the smoke concentration and temperature in the environment, generate sensing data, and upload the sensing data to the identification module 2.
In this embodiment, the sensing unit 13 is composed of a smoke sensor with a model number of UGP901 and a temperature sensor with a model number of PT100, the smoke sensor senses the smoke concentration in the environment, the temperature sensor senses the temperature in the environment, and uploads the sensing data to the identification module 2 for identification, so as to determine whether a fire disaster occurs or not, and improve the smoke control effect.
Further, referring to fig. 3, the identification module 2 includes an action identification unit 21 and a fire identification unit 22, the action identification unit 21 is connected to the picture generation unit 12 and the warning module 3, respectively, and the fire identification unit 22 is connected to the sensing unit 13 and the warning module 3, respectively;
the action recognition unit 21 is configured to obtain a picture, identify a smoking behavior, generate a smoking behavior conclusion, and upload the smoking behavior conclusion to the warning module 3;
the fire recognition unit 22 is configured to obtain smoke concentration data and temperature data in an environment, identify a fire behavior, generate a fire behavior conclusion, and upload the fire behavior conclusion to the warning module 3.
In this embodiment, the motion recognition unit 21 uses a support vector machine as a classifier, and first intercepts a required smoke and non-smoke sample from an image sequence of indoor smoking smoke recorded in advance, then performs feature extraction and feature fusion operations on the sample, outputs a data set to the support vector machine generation classifier after normalizing an extracted combined feature vector group of the smoking smoke, then performs classification recognition on the obtained picture by using a trained classifier, determines the position of smoke if smoke exists in the picture, further determines whether smoking behavior exists or not, and uploads a smoking behavior conclusion to the warning module 3, so that the detection effect is better; the fire recognition unit 22 receives the smoke concentration and temperature data, compares preset parameters to determine whether the smoke concentration or the temperature exceeds the standard, judges whether a fire occurs, and uploads a fire behavior conclusion to the warning module 3, so that a fire response can be made in time, the using effect is better, and the smoke control effect is improved.
Further, referring to fig. 4, the warning module 3 includes a voice prompt unit 31 and a spraying unit 32, the voice prompt unit 31 is connected to the action recognition unit 21, and the spraying unit 32 is connected to the fire recognition unit 22;
the voice prompt unit 31 is configured to obtain the smoking behavior conclusion, generate voice prompt information, and broadcast the voice prompt information through a speaker;
and the spraying unit 32 is used for acquiring the fire behavior conclusion, generating a control instruction and controlling the spray header to spray water.
In this embodiment, voice prompt unit 31 connects the speaker, after acquireing the smoking action conclusion, generates voice prompt information to send to the speaker, send the voice broadcast information by the speaker, indicate the smoker to forbid the cigarette, spray unit 32 connects the shower head, after acquireing the conflagration action conclusion, controls the shower head and starts, erupts the water source, can put out a fire disaster in time to avoid causing the potential safety hazard, improve the accuse cigarette effect.
Further, referring to fig. 4, the warning module 3 further includes a communication unit 33, and the communication unit 33 is connected to the fire identification unit 22 and the action identification unit 21 respectively;
and the communication unit 33 is used for acquiring the behavior conclusion, generating corresponding warning information and uploading the warning information to a manager.
In the embodiment, the communication module obtains the smoking behavior conclusion and the fire behavior conclusion, generates corresponding warning information, and sends the warning information to the manager through the wireless network, so that the manager can conveniently and timely make a judgment, and control the field condition, thereby being beneficial to safety protection and improving the smoke control effect.
Further, referring to fig. 4, the recognition module 2 further includes a face recognition unit 23, and the face recognition unit 23 is connected to the action recognition unit 21;
the face recognition unit 23 is configured to obtain the smoking behavior conclusion and the corresponding action picture, perform face recognition on the action picture, and identify a smoking person.
In this embodiment, after the face recognition unit 23 obtains the smoking behavior conclusion, the corresponding smoking behavior picture is called in the behavior recognition unit 21, and through face recognition, the smoking person is identified, and when the smoking person enters the monitoring place next time, a warning is given in time to avoid the smoking behavior.
Referring to fig. 5, an intelligent recognition method for smoking behavior includes the following steps:
s101: shooting a video through the monitoring module 1, preprocessing the video to generate a picture, sensing the smoke concentration and temperature in the environment, and finally transmitting the picture and sensing data to the identification module 2 and the recording module 4;
s102: the picture is identified through the identification module 2, whether smoking behaviors exist or not is judged, whether fire disasters occur or not is judged according to the sensing data, and finally a behavior conclusion is generated and sent to the warning module 3 and the recording module 4;
s103: the behavior conclusion is acquired through the warning module 3, a corresponding smoke control instruction is generated to carry out voice prompt or spray fire extinguishing, the smoke control instruction is uploaded to the recording module 4, and corresponding warning information is generated according to the acquired behavior conclusion and is sent to a manager;
s104: the recording module 4 acquires and stores data uploaded by the monitoring module 1, the identification module 2 and the warning module 3.
In this embodiment, first, the monitoring module 1 takes pictures of a monitoring area through a plurality of high definition cameras, pre-processes the taken video, removes noise and gaps in the video by means of median filtering and morphological operations, so as to reduce the influence of environment and illumination, optimizes a binary image, generates a picture through software analysis, transmits the picture to the recognition module 2, the recognition module 2 uses a support vector machine as a classifier, wherein a required smoke and non-smoke sample is intercepted from an image sequence of indoor smoking smoke recorded in advance, then performs feature extraction and feature fusion operations on the sample, outputs a data set to the support vector machine generation classifier after normalizing an extracted joint feature vector group of the smoking smoke, and then classifies and recognizes the acquired picture with a trained classifier, if smoking smoke exists in the picture, determining the position of the smoke, further judging and identifying whether smoking behavior exists, uploading a smoking behavior conclusion to the warning module 3, receiving the smoking behavior conclusion by the warning module 3, generating voice prompt information, broadcasting through a loudspeaker, prompting a smoker to prohibit smoking, avoiding missing detection by adopting image analysis, and having a better smoke control effect; the monitoring module 1 senses the smoke concentration and temperature in a monitoring environment through a smoke sensor and a temperature sensor, and uploads the sensing data to the identification module 2, the identification module 2 is preset with smoke concentration parameters and temperature parameters, the occurrence of fire is judged when the smoke concentration and temperature are sensed to exceed standards, and a fire behavior conclusion is uploaded to the warning module 3, the warning module 3 generates a corresponding control instruction to control a spray header to spray water, so that instant fire extinguishment is realized, meanwhile, the warning module 3 generates corresponding warning information according to the acquired behavior conclusion and transmits the warning information to a manager through a wireless network, so that the manager can control the site in real time, and safety is guaranteed; the recording module 4 records and stores the operation historical data of the monitoring module 1, the identification module 2 and the warning module 3, so that the follow-up is facilitated, effective smoke control is realized, and the smoke control effect is better.
According to the intelligent identification method and system for the smoking behavior, videos of a monitoring area are shot in real time through the monitoring module 1, the videos are preprocessed to generate pictures, then the pictures are transmitted to the identification module 2 to be identified, whether the smoking behavior exists or not is judged, if the smoking behavior exists, a smoking behavior conclusion is transmitted to the warning module 3, and the warning module 3 generates voice prompt information and broadcasts the voice prompt information through a loudspeaker; the monitoring module 1 senses the smoke concentration and temperature in the environment through a smoke sensor and a temperature sensor, and transmits sensing data to the identification module 2, the identification module 2 judges whether a fire disaster occurs or not, and then sends a fire disaster behavior conclusion to the warning module 3, and the warning module 3 controls the spray header to spray water to extinguish the fire in time; the recording module 4 stores the monitoring module 1, the identification module 2 and the historical operating data of the warning module 3, so that the tracking in the later period is facilitated, image recognition is adopted for judgment, and the missing detection is avoided by combining with sensor monitoring, so that the smoke control effect is better.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. An intelligent recognition system for smoking behaviors is characterized by comprising a monitoring module, a recognition module, a warning module and a recording module;
the monitoring module is respectively connected with the identification module and the recording module, the identification module is respectively connected with the warning module and the recording module, and the warning module is connected with the recording module;
the monitoring module is used for shooting videos, preprocessing the videos to generate pictures, sensing the smoke concentration and temperature in the environment, and finally transmitting the pictures and sensing data to the identification module and the recording module;
the identification module is used for acquiring the picture and the induction data, judging whether smoking behaviors exist or not through the picture, judging whether fire disasters occur or not through the induction data, finally generating a behavior conclusion, and transmitting the behavior conclusion to the warning module and the recording module;
the warning module is used for acquiring the behavior conclusion, generating a corresponding smoke control instruction, uploading the smoke control instruction to the recording module, generating corresponding warning information according to the smoke control instruction and sending the warning information to a manager;
the recording module is used for acquiring and storing the data uploaded by the monitoring module, the identification module and the warning module.
2. The intelligent recognition system of smoking behavior of claim 1,
the monitoring module comprises a camera shooting unit and a picture generating unit, the camera shooting unit is respectively connected with the picture generating unit and the recording module, and the picture generating unit is connected with the identification module;
the camera shooting unit is used for shooting a video and uploading video data to the picture generating unit and the recording module;
the picture generation unit is used for acquiring the video data, preprocessing the video data, generating a picture and uploading the picture to the identification module.
3. The intelligent recognition system of smoking behavior of claim 1,
the monitoring module further comprises a sensing unit, and the sensing unit is connected with the identification module;
the sensing unit is used for sensing smoke concentration and temperature in an environment, generating sensing data and uploading the sensing data to the identification module.
4. The intelligent recognition system of smoking behavior of claim 3,
the identification module comprises an action identification unit and a fire identification unit, the action identification unit is respectively connected with the picture generation unit and the warning module, and the fire identification unit is respectively connected with the sensing unit and the warning module;
the action recognition unit is used for acquiring the picture, identifying the smoking behavior, generating a smoking behavior conclusion and uploading the conclusion to the warning module;
the fire recognition unit is used for acquiring smoke concentration data and temperature data in the environment, identifying fire behaviors, generating fire behavior conclusions and uploading the fire behavior conclusions to the warning module.
5. The intelligent recognition system of smoking behavior of claim 4,
the warning module comprises a voice prompt unit and a spraying unit, the voice prompt unit is connected with the action recognition unit, and the spraying unit is connected with the fire recognition unit;
the voice prompt unit is used for acquiring the smoking behavior conclusion, generating voice prompt information and broadcasting the voice prompt information through a loudspeaker;
and the spraying unit is used for acquiring the fire behavior conclusion, generating a control instruction and controlling the spray header to spray water.
6. An intelligent recognition method of smoking behavior, the intelligent recognition system of smoking behavior according to any one of claims 1 to 5, comprising the steps of:
shooting a video through a monitoring module, preprocessing the video to generate a picture, sensing the smoke concentration and temperature in the environment, and finally transmitting the picture and sensing data to an identification module and a recording module;
the picture is identified through the identification module, whether smoking behaviors exist or not is judged, whether fire disasters occur or not is judged according to the sensing data, and finally a behavior conclusion is generated and sent to the warning module and the recording module;
the behavior conclusion is obtained through the warning module, a corresponding smoke control instruction is generated to carry out voice prompt or spray fire extinguishing, and the smoke control instruction is uploaded to the recording module;
and data uploaded by the monitoring module, the identification module and the warning module are acquired and stored through the recording module.
7. The intelligent recognition method for smoking behavior according to claim 6, wherein the warning module obtains the behavior conclusion, generates a corresponding smoke control command for voice prompt or spraying fire extinguishing, and uploads the smoke control command to the recording module, and the method further comprises:
and the warning module generates corresponding warning information according to the acquired behavior conclusion and sends the warning information to a manager.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110543604.0A CN113392710A (en) | 2021-05-19 | 2021-05-19 | Intelligent recognition method and system for smoking behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110543604.0A CN113392710A (en) | 2021-05-19 | 2021-05-19 | Intelligent recognition method and system for smoking behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113392710A true CN113392710A (en) | 2021-09-14 |
Family
ID=77618025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110543604.0A Pending CN113392710A (en) | 2021-05-19 | 2021-05-19 | Intelligent recognition method and system for smoking behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392710A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114821996A (en) * | 2022-01-25 | 2022-07-29 | 深圳市朗鑫智能科技有限公司 | Smoke alarm method, system, electronic equipment and computer storage medium thereof |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530569A (en) * | 2016-10-17 | 2017-03-22 | 北京小米移动软件有限公司 | Method and device for fire monitoring |
| CN107392826A (en) * | 2017-08-04 | 2017-11-24 | 深圳市盛路物联通讯技术有限公司 | A kind of PE management method and system |
| US20190244504A1 (en) * | 2016-10-24 | 2019-08-08 | Hochiki Corporation | Fire monitoring system |
| CN110223487A (en) * | 2019-06-13 | 2019-09-10 | 杭州电子科技大学 | A kind of Smoke Detection and method for warming and system based on cigarette smoking identification |
| CN110329149A (en) * | 2019-07-22 | 2019-10-15 | 天津大学 | The active safety platform of multisensor based on BEI-DOU position system |
| CN110634257A (en) * | 2018-06-25 | 2019-12-31 | 郭娟 | Fire alarm system |
| CN111105586A (en) * | 2019-12-31 | 2020-05-05 | 高慕义 | Intelligent smoke-forbidden water spraying system and identification method |
| 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 |
| CN111862523A (en) * | 2020-07-02 | 2020-10-30 | 重庆思尔达信息科技有限公司 | Wisdom safety supervisory systems |
| CN112036363A (en) * | 2020-09-11 | 2020-12-04 | 新石器慧成(北京)科技有限公司 | Smoking behavior detection method and device |
| 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 |
| CN112489351A (en) * | 2020-11-30 | 2021-03-12 | 北京华正明天信息技术股份有限公司 | School fire early warning method based on picture recognition |
-
2021
- 2021-05-19 CN CN202110543604.0A patent/CN113392710A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530569A (en) * | 2016-10-17 | 2017-03-22 | 北京小米移动软件有限公司 | Method and device for fire monitoring |
| US20190244504A1 (en) * | 2016-10-24 | 2019-08-08 | Hochiki Corporation | Fire monitoring system |
| CN107392826A (en) * | 2017-08-04 | 2017-11-24 | 深圳市盛路物联通讯技术有限公司 | A kind of PE management method and system |
| CN110634257A (en) * | 2018-06-25 | 2019-12-31 | 郭娟 | Fire alarm system |
| CN110223487A (en) * | 2019-06-13 | 2019-09-10 | 杭州电子科技大学 | A kind of Smoke Detection and method for warming and system based on cigarette smoking identification |
| CN110329149A (en) * | 2019-07-22 | 2019-10-15 | 天津大学 | The active safety platform of multisensor based on BEI-DOU position system |
| CN111105586A (en) * | 2019-12-31 | 2020-05-05 | 高慕义 | Intelligent smoke-forbidden water spraying system and identification method |
| 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 |
| CN111862523A (en) * | 2020-07-02 | 2020-10-30 | 重庆思尔达信息科技有限公司 | Wisdom safety supervisory systems |
| CN112036363A (en) * | 2020-09-11 | 2020-12-04 | 新石器慧成(北京)科技有限公司 | Smoking behavior detection method and device |
| 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 |
| CN112489351A (en) * | 2020-11-30 | 2021-03-12 | 北京华正明天信息技术股份有限公司 | School fire early warning method based on picture recognition |
Non-Patent Citations (2)
| Title |
|---|
| SHU WANG等: "A Sauter mean diameter sensor for fire smoke detection", 《SENSORS AND ACTUATORS B: CHEMICAL》, vol. 281, pages 920 - 932, XP085576048, DOI: 10.1016/j.snb.2018.11.021 * |
| 陶益: "于单片机的火灾烟雾温度报警器的设计与制作", 《计算机产品与流通》, pages 126 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114821996A (en) * | 2022-01-25 | 2022-07-29 | 深圳市朗鑫智能科技有限公司 | Smoke alarm method, system, electronic equipment and computer storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10565455B2 (en) | Methods and systems for audiovisual communication | |
| US11785146B2 (en) | Doorbell call center | |
| JP5043940B2 (en) | Video surveillance system and method combining video and audio recognition | |
| CN103150856B (en) | Fire flame video monitoring and early warning system | |
| US20160358436A1 (en) | Video Monitoring System | |
| KR20230004421A (en) | System for detecting abnormal behavior based on artificial intelligence | |
| KR101442669B1 (en) | Method and apparatus for criminal acts distinction using intelligent object sensing | |
| CN109584494A (en) | A kind of hidden fire-fighting danger inspection system based on Internet of Things | |
| CN113392710A (en) | Intelligent recognition method and system for smoking behavior | |
| US10750133B2 (en) | Systems and methods for automatic video recording | |
| CN114534146A (en) | Control method and system for automatically searching for ground based on flame of mobile electric fire-fighting robot | |
| CN111161585A (en) | Fire-fighting interactive experience system and interactive experience control method thereof | |
| CN110507941A (en) | Fire disaster treatment method and system | |
| CN104767969B (en) | Level crossing operation intelligence safety monitoring system and method | |
| CN119007384A (en) | Portable sirens | |
| CN111611966A (en) | Target person detection method, device, equipment and storage medium | |
| CN111757039B (en) | Video call method of wearable device and wearable device | |
| CN110689697A (en) | An artificial intelligence safety monitoring system and method | |
| KR102511093B1 (en) | Smart city elevator crime prevention system | |
| CN104320605B (en) | A kind of intercom system and intercommunication method | |
| CN110048732B (en) | Wearable electronic device and noise elimination method | |
| KR102627402B1 (en) | A IoT smart sprinkler to be capable of Interwork home devices | |
| JP2000032434A (en) | Image-pickup device | |
| TWM491218U (en) | Security host | |
| CN118161805A (en) | Fire-fighting linkage control method, device, equipment and storage medium |
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: 20210914 |