CN117152906B - Video image fire alarm system based on artificial intelligence - Google Patents
Video image fire alarm system based on artificial intelligence Download PDFInfo
- Publication number
- CN117152906B CN117152906B CN202311434961.9A CN202311434961A CN117152906B CN 117152906 B CN117152906 B CN 117152906B CN 202311434961 A CN202311434961 A CN 202311434961A CN 117152906 B CN117152906 B CN 117152906B
- Authority
- CN
- China
- Prior art keywords
- fire
- data
- flame
- information
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 239000000779 smoke Substances 0.000 claims abstract description 81
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 25
- 238000002485 combustion reaction Methods 0.000 claims description 40
- 239000003550 marker Substances 0.000 claims description 29
- 230000001360 synchronised effect Effects 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 10
- 239000003086 colorant Substances 0.000 claims description 5
- 239000002360 explosive Substances 0.000 claims description 5
- 238000000034 method Methods 0.000 claims description 5
- 238000013075 data extraction Methods 0.000 claims 1
- 101100408454 Arabidopsis thaliana PLC6 gene Proteins 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/36—Indoor scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of fire alarm systems, in particular to a video image fire alarm system based on artificial intelligence, which comprises a control host. According to the invention, floor monitoring is arranged in each floor of the building, the interior of the building can be monitored, video information collected by the floor monitoring is stored and backed up by the storage end, and meanwhile, the video information is transmitted to the industrial computer, a fire identification module arranged in the industrial computer carries out fire identification on a fire starting position appearing in the floor by utilizing video processing, scene identification, smoke identification and flame identification, and then fire judgment is carried out; through setting up fire alarm platform, establish the conflagration information sharing between a plurality of buildings, the user and resident of corresponding building, fire department, reduce the conflagration loss.
Description
Technical Field
The invention relates to the technical field of fire alarm systems, in particular to a video image fire alarm system based on artificial intelligence.
Background
In order to timely early warn when a fire disaster occurs, fire fighting devices and fire fighting alarm devices are usually arranged in the building to early warn, and common fire fighting alarm devices comprise smoke alarm equipment, flame detection equipment and the like, but the judgment means of the equipment on whether the flame is the fire disaster is single, so that misjudgment is easy to cause;
in addition, the existing fire alarm device can only realize regional (in-floor) alarm, and when a fire disaster occurs, the fire alarm needs to be manually contacted, so that the time of fire rescue is influenced.
Building monitoring is a common safety monitoring means for buildings, and the existing building monitoring can only carry out picture monitoring and can not carry out early warning on flame burning, so that a video image fire alarm system based on artificial intelligence is provided for the problems.
Disclosure of Invention
The invention aims to provide a video image fire alarm system based on artificial intelligence so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a video image fire alarm system based on artificial intelligence, comprising:
and (3) an acquisition end: the method comprises the steps that an acquisition end acquires a video of the interior of a building;
and (3) a control host: the system comprises a storage end, an industrial computer, a PLC and a gateway, wherein the storage end receives a monitoring video from an acquisition end, stores and backs up the monitoring video, the industrial computer synchronizes the monitoring video stored in the storage end, and synchronizes the information generated after the processing to the PLC and a fire alarm platform, and a fire identification module is arranged in the industrial computer;
the fire disaster recognition module comprises video processing, scene recognition, smoke recognition, flame recognition and fire disaster judgment, and is in communication connection with the artificial intelligent learning platform, wherein:
the artificial intelligent learning platform comprises a fire scene database, a miscut statistics and man-machine intercommunication module, wherein the fire scene database comprises combustion data, artificial activity data, flame data and smoke data;
after receiving video information from a storage end, video processing intermittently extracts video pictures of a plurality of time nodes, then extracts marker data, wherein the marker data comprises a combustion object picture, a portrait picture, a smoke picture and a flame picture, and after being sequenced according to the time node sequence, the marker data are combined and sent to scene recognition, smoke recognition and flame recognition, and after receiving the marker data of the plurality of time nodes, the scene recognition, the smoke recognition and the flame recognition are compared with the combustion object data, the human activity data, the flame data and the smoke data pre-stored in a fire scene database, and the comparison result is sent to fire judgment;
judging whether the scene where the marker data is located is fire or not according to the similarity condition of the marker data and the fire scene database, and synchronously triggering alarm and generating fire data when the scene is judged to be fire;
fire alarm platform: including high in the clouds database, fire region analysis, relate to list and confirm, early warning information send, fire alarm platform establishes communication with the gateway of control host computer and is connected, wherein:
the cloud database comprises building information registration, resident and user information registration;
after fire area analysis receives fire data sent by a corresponding building control host, the fire area analysis is compared with building information registration of a cloud database, and after building information is determined, the information is synchronized to a related list for determination;
the related list determines that the resident and user information of the corresponding building in the registration of the resident and user information is called according to the building information, and the summarized fire data of the resident and user information is sent to the early warning information for sending;
after receiving information and fire disaster data from residents and users related to list determination, the early warning information is sent to the corresponding residents and users in the resident and user information synchronously after the early warning information is generated by the fire disaster data, and meanwhile, the fire disaster information is edited and synchronously sent to fire departments and properties of corresponding buildings.
As a preferable scheme, after the fire disaster identification module generates fire disaster data, the fire disaster identification module is synchronized to a fire disaster alarm platform through a gateway by an industrial computer, meanwhile, the data information for triggering alarm generated by the industrial computer is synchronized to a PLC, the PLC controls an alarm terminal to alarm, and the alarm terminal alarms for floors arranged in a building floor.
As a preferred scheme, after receiving the picture from the video processing, the scene recognition extracts the information of the scene, the person and the combustion object in the picture successively, compares the information with the data prestored in the fire scene database, judges whether inflammable and explosive objects, person actions and combustion objects exist around the scene and the combustion point of flame combustion, generates a data table after collecting the information, and transmits the data table to the smoke recognition and the flame recognition respectively with the picture from the video processing.
As a preferable scheme, after receiving a data table from scene recognition and a picture subjected to video processing, smoke recognition continuously extracts images of smoke in a plurality of pictures, performs color and volume analysis, compares the images with smoke information pre-stored in a fire scene database, generates continuous data for the smoke, gathers the data table, and sends the data to fire judgment.
As a preferable scheme, after receiving a data table from scene recognition and frames subjected to video processing, flame recognition continuously extracts images of flames in a plurality of frames, analyzes colors, volumes and flame shapes, compares the images with flame information pre-stored in a fire scene database, generates continuous flame data, gathers the continuous flame data in the data table, and sends the continuous flame data to fire judgment.
As a preferable scheme, after the fire disaster judgment receives a data table summarizing flame and smoke data, summarizing and counting is carried out according to the comparison result of each item of data, wherein the flame and the smoke are analyzed according to a time line, difference value calculation is carried out according to the data change of the flame and the smoke in sequence, the change condition of the flame and the smoke is judged, if each item of data has a growing trend, the fire disaster is judged, and fire disaster data is generated while an alarm is triggered.
When the data of scenes, smoke and flames lack comparison objects in a fire scene database, synchronizing the pictures processed by video into misleakage statistics, synchronizing the pictures into a fire department by using a man-machine intercommunication module, manually judging by the fire department, uploading judging data to the man-machine intercommunication module after the fire department completes manual judgment, and updating the data of the fire scene database by using the man-machine intercommunication module.
As a preferable scheme, the property and the fire alarm platform are in communication connection, and the property gathers positioning information of the building, building structure, resident and user information to a cloud database.
According to the technical scheme provided by the invention, the video image fire alarm system based on artificial intelligence has the beneficial effects that:
1. the floor monitoring is arranged in each floor of the building, the inside of the building can be monitored, video information collected by the floor monitoring is stored and backed up by the storage end, meanwhile, the video information is transmitted to the industrial computer, a fire identification module arranged in the industrial computer carries out fire identification on a fire position appearing in the floor by utilizing video processing, scene identification, smoke identification and flame identification, and then fire judgment is carried out;
2. by arranging the fire alarm platform, synchronous supervision of a plurality of building control hosts can be realized, fire information sharing among a plurality of buildings, users corresponding to the buildings, households and fire departments is established, and fire loss is reduced.
Drawings
FIG. 1 is a schematic diagram of the overall structure of a video image fire alarm system based on artificial intelligence of the invention;
FIG. 2 is a schematic diagram of a fire disaster recognition module and an artificial intelligence learning platform according to the present invention;
FIG. 3 is a schematic diagram of a control host according to the present invention.
In the figure: 1. a chassis; 2. a mounting frame; 3. an industrial computer; 4. a gateway; 5. a hard disk; 6. a PLC; 7. alarming on floors; 8. floor monitoring.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In order to better understand the above technical solutions, the following detailed description will be given with reference to the accompanying drawings and the specific embodiments.
As shown in fig. 1-3, an embodiment of the present invention provides an artificial intelligence-based video image fire alarm system, including:
and (3) an acquisition end: the method comprises the steps that an acquisition end acquires a video of the interior of a building;
and (3) a control host: the system comprises a storage end, an industrial computer, a PLC and a gateway, wherein the storage end receives a monitoring video from a collection end and stores and backs up the monitoring video, the monitoring video stored in the industrial computer synchronous storage end is processed, and information generated after the processing is synchronously sent to the PLC and a fire alarm platform, the industrial computer is internally provided with a fire identification module, and the fire identification module comprises the following components:
in order to judge whether flame combustion is fire or not, the fire identification module comprises video processing, scene identification, smoke identification, flame identification and fire judgment, the fire identification module is in communication connection with an artificial intelligent learning platform, the artificial intelligent learning platform comprises a fire scene database, an error statistics and man-machine intercommunication module, the fire scene database comprises combustion matter data, artificial activity data, flame data and smoke data, and the combustion matter data, the artificial activity data, the flame data and the smoke data provide comparison data for scene identification, smoke identification and flame identification;
after receiving video information from a storage end, video processing intermittently extracts video pictures of a plurality of time nodes, then extracts marker data, wherein the marker data comprises a combustion object picture, a portrait picture, a smoke picture and a flame picture, and after being sequenced according to the time node sequence, the marker data are combined and sent to scene recognition, smoke recognition and flame recognition, and after receiving the marker data of the plurality of time nodes, the scene recognition, the smoke recognition and the flame recognition are compared with the combustion object data, the human activity data, the flame data and the smoke data pre-stored in a fire scene database, and the comparison result is sent to fire judgment;
judging whether the scene where the marker data is located is fire or not according to the similarity condition of the marker data and the fire scene database, and synchronously triggering alarm and generating fire data when the scene is judged to be fire;
further, after scene recognition receives a picture from video processing, scene, character and combustion object information in the picture are sequentially extracted and compared with data prestored in a fire scene database, whether inflammable and explosive objects, character actions and combustion object conditions exist around a scene and a combustion point of flame combustion or not is judged, a data table is generated after information is summarized, and the data table and the picture from video processing are transmitted to smoke recognition and flame recognition respectively; after receiving a data table from scene recognition and pictures subjected to video processing, continuously extracting images of smoke in a plurality of pictures, analyzing color and volume, comparing the images with smoke information pre-stored in a fire scene database, generating continuous data aiming at the smoke, summarizing the data table, and sending the data table to fire judgment; after receiving a data table from scene recognition and frames subjected to video processing, continuously extracting images of flames in a plurality of frames, analyzing colors, volumes and flame shapes, comparing the images with flame information prestored in a fire scene database, generating continuous flame-oriented data, summarizing the continuous flame-oriented data into the data table, and sending the continuous flame-oriented data to fire judgment; after the fire disaster judgment receives the data table summarizing the flame and smoke data, summarizing and counting according to the comparison result of each item of data, analyzing the flame and the smoke according to a time line, calculating the difference value according to the data change of the flame and the smoke in sequence, judging the change condition of the flame and the smoke, if each item of data has a growing trend, judging the fire disaster, triggering an alarm and generating fire disaster data;
fire alarm platform: including high in the clouds database, fire region analysis, relate to list and confirm, early warning information send, fire alarm platform establishes communication with the gateway of control host computer and is connected, wherein:
the cloud database comprises building information registration, resident and user information registration;
after fire area analysis receives fire data sent by a corresponding building control host, the fire area analysis is compared with building information registration of a cloud database, and after building information is determined, the information is synchronized to a related list for determination;
the related list determines that the resident and user information of the corresponding building in the registration of the resident and user information is called according to the building information, and the summarized fire data of the resident and user information is sent to the early warning information for sending;
after receiving resident information, user information and fire data which are determined by a list, extracting contact information of the resident and the user in the resident information and the user information, generating early warning information by the fire warning information, synchronously sending the early warning information to corresponding resident and user in the resident information and the user information, simultaneously editing fire information and synchronously sending the fire information to fire departments and properties of corresponding buildings, monitoring the inside of the buildings by arranging floor monitoring in each floor layer of the buildings, storing and backing up video information collected by floor monitoring by a storage end, simultaneously, transmitting the video information to an industrial computer, carrying out fire identification on fire positions which appear in the floors by a fire identification module arranged in the industrial computer, and carrying out fire judgment after detecting fire by utilizing video processing, scene identification, smoke identification and flame identification.
Further, the storage terminal is connected with a monitoring PC terminal of the building for conventional building monitoring.
In this embodiment, in order to realize quick alarm, after the fire disaster identification module generates fire disaster data, the industrial computer is synchronized to the fire disaster alarm platform through the gateway, and simultaneously, the industrial computer generates data information triggering alarm and is synchronized to the PLC, and the PLC controls the alarm terminal to alarm, and the alarm terminal is the floor alarm arranged in the building floor.
In this embodiment, in order to avoid that the fire scene database has no contrast data required for scene recognition, smoke recognition and flame recognition, when the scene recognition, smoke recognition and flame recognition occur, and when the data of the scene, smoke and flame lack contrast objects in the fire scene database, the video processing picture is synchronized to the miscut statistics, the miscut statistics utilizes the man-machine intercommunication module to synchronize the picture to the fire department, the fire department carries out manual judgment, the fire department uploads the judgment data to the man-machine intercommunication module after completing the manual judgment, and the man-machine intercommunication module carries out data update on the fire scene database.
In this embodiment, the property and the fire alarm platform establish communication connection, and the property gathers the positioning information of the building, the structure of the building, and the resident and user information into the cloud database.
Embodiments of the present invention will be described in further detail below with reference to the attached drawings:
referring to fig. 1-3, the method includes:
and (3) an acquisition end: the method comprises the steps that a collecting end collects videos inside a building, wherein the collecting end is a floor monitoring 8 arranged in each floor of the building;
and (3) a control host: including the storage end, industrial computer 3, PLC6 and gateway 4, wherein, the storage end is hard disk 5, industrial computer 3, PLC6 and gateway 4 all set up in control host's quick-witted incasement 1, and install fixedly through mounting bracket 2, the storage end is received and is kept the backup from the surveillance video of gathering the end, the surveillance video that holds in the synchronous storage end of industrial computer is handled, and the information that will produce after handling is synchronous for PLC6 and fire alarm platform, wherein, the built-in fire identification module of industrial computer, wherein:
in order to judge whether flame combustion is fire or not, the fire identification module comprises video processing, scene identification, smoke identification, flame identification and fire judgment, the fire identification module is in communication connection with an artificial intelligent learning platform, the artificial intelligent learning platform comprises a fire scene database, an error statistics and man-machine intercommunication module, the fire scene database comprises combustion matter data, artificial activity data, flame data and smoke data, and the combustion matter data, the artificial activity data, the flame data and the smoke data provide comparison data for scene identification, smoke identification and flame identification;
after receiving video information from a storage end, video processing intermittently extracts video pictures of a plurality of time nodes, then extracts marker data, wherein the marker data comprises a combustion object picture, a portrait picture, a smoke picture and a flame picture, and after being sequenced according to the time node sequence, the marker data are combined and sent to scene recognition, smoke recognition and flame recognition, and after receiving the marker data of the plurality of time nodes, the scene recognition, the smoke recognition and the flame recognition are compared with the combustion object data, the human activity data, the flame data and the smoke data pre-stored in a fire scene database, and the comparison result is sent to fire judgment;
judging whether the scene where the marker data is located is fire or not according to the similarity condition of the marker data and the fire scene database, and synchronously triggering alarm and generating fire data when the scene is judged to be fire;
further, after scene recognition receives a picture from video processing, scene, character and combustion object information in the picture are sequentially extracted and compared with data prestored in a fire scene database, whether inflammable and explosive objects, character actions and combustion object conditions exist around a scene and a combustion point of flame combustion or not is judged, a data table is generated after information is summarized, and the data table and the picture from video processing are transmitted to smoke recognition and flame recognition respectively; after receiving a data table from scene recognition and pictures subjected to video processing, continuously extracting images of smoke in a plurality of pictures, analyzing color and volume, comparing the images with smoke information pre-stored in a fire scene database, generating continuous data aiming at the smoke, summarizing the data table, and sending the data table to fire judgment; after receiving a data table from scene recognition and frames subjected to video processing, continuously extracting images of flames in a plurality of frames, analyzing colors, volumes and flame shapes, comparing the images with flame information prestored in a fire scene database, generating continuous flame-oriented data, summarizing the continuous flame-oriented data into the data table, and sending the continuous flame-oriented data to fire judgment; after the fire disaster judgment receives the data table summarizing the flame and smoke data, summarizing and counting according to the comparison result of each item of data, analyzing the flame and the smoke according to a time line, calculating the difference value according to the data change of the flame and the smoke in sequence, judging the change condition of the flame and the smoke, if each item of data has a growing trend, judging the fire disaster, triggering an alarm and generating fire disaster data;
fire alarm platform: including high in the clouds database, fire region analysis, relate to list and confirm, early warning information send, fire alarm platform establishes communication with the gateway of control host computer and is connected, wherein:
the cloud database comprises building information registration, resident and user information registration;
after fire area analysis receives fire data sent by a corresponding building control host, the fire area analysis is compared with building information registration of a cloud database, and after building information is determined, the information is synchronized to a related list for determination;
the related list determines that the resident and user information of the corresponding building in the registration of the resident and user information is called according to the building information, and the summarized fire data of the resident and user information is sent to the early warning information for sending;
after receiving information and fire disaster data from residents and users related to list determination, the early warning information is sent to the corresponding residents and users in the resident and user information synchronously after the early warning information is generated by the fire disaster data, and meanwhile, the fire disaster information is edited and synchronously sent to fire departments and properties of corresponding buildings.
In this embodiment, the alarm terminal includes floor alarm 7 disposed in each floor, and the floor alarm 7 is controlled to be turned on and off by the PLC 6.
The following explains the using steps of the video image fire alarm system based on artificial intelligence:
step one: building account numbers are established on a cloud database by building properties of the building, and building modeling graphs, building position information, building fire-fighting facility conditions, resident or tenant distribution conditions, contact modes and the like are input;
step two: starting floor monitoring to perform uninterrupted video acquisition on the building, storing video data to a hard disk, and synchronizing the video data to an industrial computer;
step three: after receiving the video information, a fire disaster identification module in the industrial computer intermittently extracts video pictures of a plurality of time nodes, and then extracts marker data, wherein the marker data comprises a combustion object picture, a portrait picture, a smoke picture and a flame picture, and the marker data are sequenced according to the time node sequence and then are combined and sent to scene identification, smoke identification and flame identification;
step four: the fire disaster identification judgment, after the scene identification receives the picture from the video processing, extracting the scene, character and combustion object information in the picture successively, comparing the scene with the data prestored in a fire disaster scene database, judging whether inflammable and explosive objects, character actions and combustion object conditions exist around the scene and the combustion point of flame combustion, generating a data table after collecting the information, and transmitting the data table to the smoke identification and the flame identification respectively with the picture from the video processing; after receiving a data table from scene recognition and pictures subjected to video processing, continuously extracting images of smoke in a plurality of pictures, analyzing color and volume, comparing the images with smoke information pre-stored in a fire scene database, generating continuous data aiming at the smoke, summarizing the data table, and sending the data table to fire judgment; after receiving a data table from scene recognition and frames subjected to video processing, continuously extracting images of flames in a plurality of frames, analyzing colors, volumes and flame shapes, comparing the images with flame information prestored in a fire scene database, generating continuous flame-oriented data, summarizing the continuous flame-oriented data into the data table, and sending the continuous flame-oriented data to fire judgment; after the fire disaster judgment receives the data table summarizing the flame and smoke data, summarizing and counting according to the comparison result of each item of data, analyzing the flame and the smoke according to a time line, wherein the time line is used for extracting the video according to video processing, the extracting interval is controlled to be 5-10s, the difference value calculation is carried out according to the data change of the flame and the smoke in the sequence time, the change condition of the flame and the smoke is judged, if each item of data has a growing trend, the fire disaster is judged, and the fire disaster data is generated while the alarm is triggered;
step five: triggering an alarm, triggering the alarm to be sent to a PLC when the fire identification module judges that the combustion is fire, controlling an alarm end to alarm by the PLC, and synchronizing alarm information to a property;
step six: when the fire disaster identification module judges that the combustion is a fire disaster, the generated fire disaster data is synchronized to a fire disaster alarm platform through a gateway, a fire disaster area analysis and design list of the fire disaster alarm platform determines that building modeling graphics, building position information, building fire protection facility conditions, resident or tenant distribution conditions and contact modes of corresponding buildings are extracted from a cloud database, and fire disaster information is sent to residents or tenants and fire departments by means of early warning information transmission, so that judgment and early warning of the fire disaster of the buildings are realized.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. A video image fire alarm system based on artificial intelligence is characterized in that: comprising the following steps:
and (3) an acquisition end: the acquisition terminal acquires the video inside the building;
and (3) a control host: the system comprises a storage end, an industrial computer, a PLC and a gateway, wherein the storage end receives a monitoring video from an acquisition end, stores and backs up the monitoring video, the industrial computer synchronizes the monitoring video stored in the storage end, and synchronizes the information generated after the processing to the PLC and a fire alarm platform, and a fire identification module is arranged in the industrial computer;
the fire disaster recognition module comprises video processing, scene recognition, smoke recognition, flame recognition and fire disaster judgment, and is in communication connection with the artificial intelligence learning platform, wherein:
the artificial intelligence learning platform comprises a fire scene database, a misleakage statistics and man-machine intercommunication module, wherein the fire scene database comprises combustion data, artificial activity data, flame data and smoke data;
the method comprises the steps that after video information from a storage end is received through video processing, video images of a plurality of time nodes are intermittently extracted, then marker data extraction is carried out, wherein the marker data comprise a combustion object image, a portrait image, a smoke image and a flame image, and after the marker data are sequenced according to the time nodes, the marker data are combined and sent to scene recognition, smoke recognition and flame recognition, and after the marker data of the plurality of time nodes are received through the scene recognition, the smoke recognition and the flame recognition, the marker data are compared with the combustion object data, the manual activity data, the flame data and the smoke data which are prestored in a fire scene database, and a comparison result is sent to fire judgment;
the fire disaster judgment judges whether the scene where the marker data is located is fire disaster or not according to the similarity condition of the marker data and the fire disaster scene database, and when the scene is judged to be fire disaster, the fire disaster judgment system synchronously triggers alarm and generates fire disaster data;
fire alarm platform: including high in the clouds database, fire region analysis, relate to list and confirm, early warning information send, fire alarm platform establishes communication with the gateway of control host computer and is connected, wherein:
the cloud database comprises building information registration, resident and user information registration;
the fire area analysis compares fire data sent by a corresponding building control host with building information registration of a cloud database after receiving the fire data, and synchronizes the information to a related list after determining the building information;
the related list determines resident and user information of a corresponding building in the registration of resident and user information according to building information, and sends summarized fire data of the resident and user information to early warning information;
after receiving information and fire disaster data from residents and users related to list determination, the early warning information sending device extracts contact ways of the residents and users in the resident and user information, generates early warning information from the fire disaster data, synchronously sends the early warning information to corresponding residents and users in the resident and user information, and simultaneously edits the fire disaster information and synchronously sends the fire disaster information to fire departments and property of corresponding buildings;
after receiving the picture from the video processing, the scene recognition extracts the scene, character and combustion object information in the picture successively, compares the scene, character and combustion object information with the data prestored in the fire scene database, judges whether inflammable and explosive objects, character actions and combustion object conditions exist around the scene and the combustion point of flame combustion, generates a data table after collecting the information, and transmits the data table to smoke recognition and flame recognition respectively with the picture from the video processing;
after receiving a data table from scene recognition and pictures subjected to video processing, continuously extracting images of smoke in a plurality of pictures, analyzing color and volume, comparing the images with smoke information prestored in a fire scene database, generating continuous data aiming at the smoke, summarizing the data table, and sending the data table to fire judgment;
after receiving the data sheet from scene recognition and the frames subjected to video processing, the flame recognition continuously extracts images of flames in a plurality of frames, analyzes colors, volumes and flame shapes, compares the images with flame information prestored in a fire scene database, generates continuous flame-oriented data, gathers the continuous flame-oriented data into the data sheet, and sends the continuous flame-oriented data to fire judgment;
after the fire disaster judgment receives the data table summarizing the flame and smoke data, summarizing and counting according to the comparison result of each item of data, analyzing the flame and the smoke according to a time line, calculating the difference value according to the data change of the flame and the smoke in sequence, judging the change condition of the flame and the smoke, if each item of data has a growing trend, judging the fire disaster, triggering an alarm and generating fire disaster data;
when the scene recognition, the smoke recognition and the flame recognition occur and the data of the scene, the smoke and the flame lack of comparison objects in the fire scene database, synchronizing the picture processed by the video into the misleakage statistics, synchronizing the picture into the fire department by using the man-machine intercommunication module, manually judging by the fire department, uploading the judgment data to the man-machine intercommunication module after the fire department completes the manual judgment, and updating the data of the fire scene database by using the man-machine intercommunication module.
2. The artificial intelligence based video image fire alarm system of claim 1, wherein: after the fire disaster identification module generates fire disaster data, the fire disaster identification module is synchronized to a fire disaster alarm platform through a gateway by an industrial computer, meanwhile, the industrial computer generates data information for triggering alarm and is synchronized to a PLC, the PLC controls an alarm terminal to alarm, and the alarm terminal alarms for floors arranged in floors of a building.
3. The artificial intelligence based video image fire alarm system of claim 1, wherein: the property establishes communication connection with the fire alarm platform, and the property gathers positioning information of the building, building structure, resident and user information to a cloud database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311434961.9A CN117152906B (en) | 2023-11-01 | 2023-11-01 | Video image fire alarm system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311434961.9A CN117152906B (en) | 2023-11-01 | 2023-11-01 | Video image fire alarm system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117152906A CN117152906A (en) | 2023-12-01 |
| CN117152906B true CN117152906B (en) | 2024-01-23 |
Family
ID=88901220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311434961.9A Active CN117152906B (en) | 2023-11-01 | 2023-11-01 | Video image fire alarm system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152906B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408846A (en) * | 2016-11-29 | 2017-02-15 | 周川 | Image fire hazard detection method based on video monitoring platform |
| CN206004702U (en) * | 2016-07-29 | 2017-03-08 | 云南英科瑞电力电子有限公司 | Based on internet cloud communication and the multiple terminals security against fire intelligent monitor system of cloud storage technology |
| CN108492517A (en) * | 2018-03-06 | 2018-09-04 | 深圳智达机械技术有限公司 | A kind of fire monitoring system for building |
| CN109144019A (en) * | 2018-10-29 | 2019-01-04 | 电子科技大学中山学院 | Based on big data wisdom building monitored control system |
| CN109493561A (en) * | 2018-11-19 | 2019-03-19 | 杭州湛川智能技术有限公司 | A kind of fire monitoring system based on image procossing |
| CN111639620A (en) * | 2020-06-08 | 2020-09-08 | 深圳航天智慧城市系统技术研究院有限公司 | Fire disaster analysis method and system based on visible light image recognition |
| CN112312437A (en) * | 2020-11-12 | 2021-02-02 | 福建阿古电务数据科技有限公司 | Internet of things wireless double-link self-adaptive communication system and method |
| KR20210128277A (en) * | 2020-04-16 | 2021-10-26 | 양우태 | Real-time smart fire fighting sensing and monitoring system |
| CN114882664A (en) * | 2022-04-20 | 2022-08-09 | 苏州金朵云数字科技有限公司 | Visual building alarm system based on digital sand table |
| CN115035483A (en) * | 2022-08-10 | 2022-09-09 | 广东广宇科技发展有限公司 | Indoor fire safety hidden danger monitoring method and system, electronic equipment and storage medium |
| CN115620477A (en) * | 2022-10-26 | 2023-01-17 | 安徽谊钢消防工程有限公司 | Fire engineering construction is with real-time fire prevention monitoring data transmission system |
| JP3243299U (en) * | 2022-06-28 | 2023-08-18 | 穩態光電科技股▲ふん▼有限公司 | fire early alarm |
-
2023
- 2023-11-01 CN CN202311434961.9A patent/CN117152906B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206004702U (en) * | 2016-07-29 | 2017-03-08 | 云南英科瑞电力电子有限公司 | Based on internet cloud communication and the multiple terminals security against fire intelligent monitor system of cloud storage technology |
| CN106408846A (en) * | 2016-11-29 | 2017-02-15 | 周川 | Image fire hazard detection method based on video monitoring platform |
| CN108492517A (en) * | 2018-03-06 | 2018-09-04 | 深圳智达机械技术有限公司 | A kind of fire monitoring system for building |
| CN109144019A (en) * | 2018-10-29 | 2019-01-04 | 电子科技大学中山学院 | Based on big data wisdom building monitored control system |
| CN109493561A (en) * | 2018-11-19 | 2019-03-19 | 杭州湛川智能技术有限公司 | A kind of fire monitoring system based on image procossing |
| KR20210128277A (en) * | 2020-04-16 | 2021-10-26 | 양우태 | Real-time smart fire fighting sensing and monitoring system |
| CN111639620A (en) * | 2020-06-08 | 2020-09-08 | 深圳航天智慧城市系统技术研究院有限公司 | Fire disaster analysis method and system based on visible light image recognition |
| CN112312437A (en) * | 2020-11-12 | 2021-02-02 | 福建阿古电务数据科技有限公司 | Internet of things wireless double-link self-adaptive communication system and method |
| CN114882664A (en) * | 2022-04-20 | 2022-08-09 | 苏州金朵云数字科技有限公司 | Visual building alarm system based on digital sand table |
| JP3243299U (en) * | 2022-06-28 | 2023-08-18 | 穩態光電科技股▲ふん▼有限公司 | fire early alarm |
| CN115035483A (en) * | 2022-08-10 | 2022-09-09 | 广东广宇科技发展有限公司 | Indoor fire safety hidden danger monitoring method and system, electronic equipment and storage medium |
| CN115620477A (en) * | 2022-10-26 | 2023-01-17 | 安徽谊钢消防工程有限公司 | Fire engineering construction is with real-time fire prevention monitoring data transmission system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117152906A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240185705A1 (en) | Augmented reality of a building | |
| CN101334924B (en) | Fire detection system and fire detection method thereof | |
| CN105913600B (en) | A kind of building intelligent fire alarm system | |
| CN104881943B (en) | A kind of nuclear power station visual image fire protection alarm system and method | |
| CN206045239U (en) | Linkage type intelligent cloud fire-fighting system | |
| CN207993197U (en) | A kind of chemical industry smoke and fire intelligent video analytic system | |
| CN113542411B (en) | Fire control thing networking integrated management platform | |
| CN110517441A (en) | Based on the frame-embedded smog of deep learning and flame video alarming system and method | |
| CN212782246U (en) | Smoke and fire recognition system based on artificial intelligence | |
| CN110853287A (en) | Flame real-time monitoring system and method based on Internet of things distributed architecture | |
| CN112396796A (en) | Automatic fire hazard identification early warning monitoring system based on computer vision | |
| CN201091014Y (en) | Fire detecting device | |
| CN110148288A (en) | Intelligent fire early warning system and method for early warning | |
| CN112037462A (en) | Intelligent evacuation system and control method thereof | |
| CN111681386A (en) | Fire control early warning system based on big data | |
| CN111669488A (en) | Video monitoring and fire alarm linkage system and method thereof | |
| CN117152906B (en) | Video image fire alarm system based on artificial intelligence | |
| CN114882664A (en) | Visual building alarm system based on digital sand table | |
| WO2016060312A1 (en) | Indoor position recognition-based security management device and method | |
| KR20210041337A (en) | Control system and control device for patrol and moving out, and operation method thereof | |
| CN205405842U (en) | Intelligence alarm system based on cloud platform | |
| CN206340127U (en) | Radio-type intelligent cloud fire-fighting system | |
| CN209232092U (en) | A kind of building fire-fighting system based on Internet of Things | |
| CN105575074A (en) | Intelligent alarm system based on cloud platform | |
| CN116403384A (en) | Remote artificial intelligent fire-fighting early warning system based on Internet of things technology |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |