CN113380000A - Fire alarm controller alarm condition processing operation monitoring method based on video - Google Patents
Fire alarm controller alarm condition processing operation monitoring method based on video Download PDFInfo
- Publication number
- CN113380000A CN113380000A CN202110483199.8A CN202110483199A CN113380000A CN 113380000 A CN113380000 A CN 113380000A CN 202110483199 A CN202110483199 A CN 202110483199A CN 113380000 A CN113380000 A CN 113380000A
- Authority
- CN
- China
- Prior art keywords
- alarm
- information
- indicator light
- state
- fire alarm
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 title claims abstract description 20
- 238000013135 deep learning Methods 0.000 claims abstract description 4
- 230000001960 triggered effect Effects 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 2
- 230000003213 activating effect Effects 0.000 claims 1
- 238000011112 process operation Methods 0.000 claims 1
- 238000012015 optical character recognition Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007599 discharging 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
- 238000011084 recovery Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
- G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
Abstract
The invention relates to a fire alarm controller alarm condition processing operation monitoring method based on video, which comprises the following steps: step one, establishing an operation rule according to an alarm occurrence type; secondly, acquiring a video of the region of interest through a camera; extracting display information of a screen and an indicator lamp in the video through a deep learning algorithm, judging whether a fire alarm controller is in an alarm state, if so, executing the next step, and if not, continuing monitoring; analyzing the extracted display information, identifying the alarm type and the alarm details, and calling a corresponding operation rule; identifying operation information of the operator on duty and confirming whether the operation is effective or not; step six, matching the operation information with the called operation rule, and judging whether the operation rule is in compliance; and step seven, reporting the alarm type, the alarm details, the operation information of the attendant, the compliance information and the alarm information of the fire alarm controller to a server.
Description
Technical Field
The invention relates to a video monitoring technology, in particular to a fire alarm controller alarm condition processing operation monitoring method based on video.
Background
The fire alarm controller (as shown in fig. 1) is a professional fire fighting device, can be connected with various sensors and fire extinguishing equipment, and is used for timely and effectively collecting fire information when a fire occurs, and helping an operator on duty to rapidly control the fire extinguishing equipment to start to extinguish a fire or remotely eliminate misinformation information. Because the function of the fire alarm controller is very important, the fire alarm controller generally needs to be operated by professional personnel and can be put on duty after professional training. If a fire occurs, the operation is wrong, and serious loss is caused.
The conventional fire alarm controller can only record and analyze information reported by related equipment generally, and has no way of judging whether the operation of an attendant accords with regulations or not, so that some conventional methods can install a camera in an attendant room for monitoring and then restore an event by replaying a monitoring video.
The invention is therefore set forth in this light.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a video-based fire alarm controller alarm condition processing operation monitoring method, which can realize the automatic detection of whether the operation of an operator on duty is in compliance or not, thereby reducing the pressure of recovering subsequent events and sending a prompt to related personnel in time when the operation is not in compliance.
In order to realize the purpose, the invention adopts the following technical scheme:
a fire alarm controller alarm processing operation monitoring method based on video comprises the following steps:
step one, establishing a corresponding operation rule according to an alarm occurrence type, and storing the operation rule in a rule base;
monitoring an interested area through a camera, and acquiring a video of the interested area in real time, wherein the interested area at least covers a screen of a fire alarm controller, an indicator light area and an operation area of the fire alarm controller;
extracting display information of a screen and an indicator lamp of the fire alarm controller through a deep learning algorithm according to the acquired video, judging whether the fire alarm controller is in an alarm state or not according to the extracted display information, executing the next step if the fire alarm controller is in the alarm state, and continuing monitoring if the fire alarm controller is not in the alarm state;
analyzing the display information of the extraction screen and the indicator light, identifying specific alarm types and alarm details, and calling corresponding operation rules in a rule base;
acquiring a video within a preset time period after the warning condition occurs, identifying the operation information of the operator on duty through a target detection algorithm, and determining whether the operation of the operator on duty is effective or not by combining the change states of a screen and an indicator lamp;
step six, matching the effective operation information of the operator on duty with the called operation rule, if the operation information is in accordance with the called operation rule, judging that the operation is in compliance, and if the operation information is not in compliance, judging that the operation is not in compliance;
and step seven, reporting the alarm type, the alarm details, the operation information of the person on duty and the compliance information to a server, and pushing reminding information to a supervisor or a background manager in time when the non-compliance information exists in the reported information.
Further, the sixth step also includes that when the judgment result is that the device is not in compliance, the sound-light alarm device or other prompting devices are started to send out a prompt to the person on duty.
Further, in the first step,
the alarm types are at least divided into: first alarm information alarm, fire alarm information alarm, fault information alarm, start information alarm, feedback information alarm, shield information alarm and alarm information alarm;
the operation rule includes at least the following information: the fire alarm controller comprises an alarm type, a button list which is allowed to be clicked and corresponds to the alarm type, a screen display state and an indicator light display state after the button is triggered, whether the operation state of the fire alarm controller is allowed to be switched or not, and alarm time limit processing time.
Further, in the third step, the method for extracting the screen display information of the fire alarm controller and judging the alarm state comprises the following steps:
a1, performing OCR processing on the screen image to obtain characters/symbols displayed on the screen and corresponding position information;
a2, using the specific position of the screen with some specific characters/coincidence, or only using some specific characters/coincidence as the characteristic, judging whether the fire alarm controller is in alarm state;
in the third step, the method for extracting the display information of the indicator light and judging the alarm state comprises the following steps:
b1, acquiring the state and position information of the indicator light through an effect-det algorithm, wherein the state of the indicator light comprises three states of on, off and flashing of the indicator light;
b2, acquiring the unique identification code of the indicator light according to the position information of the indicator light;
and b3, comparing the unique identification code of the indicator light and the state of the indicator light with the normal state, and judging whether the fire alarm controller is in an alarm state.
Further, in the third step, the method for extracting the screen display information of the fire alarm controller and judging the alarm state comprises the following steps:
a1, performing OCR processing on the screen image to obtain characters/symbols displayed on the screen and corresponding position information;
a2, using the specific position of the screen with some specific characters/coincidence, or only using some specific characters/coincidence as the characteristic, judging whether the fire alarm controller is in alarm state;
in the third step, the method for extracting the display information of the indicator light and judging the alarm state comprises the following steps:
b1, acquiring the state and position information of the indicator light through an effect-det algorithm, wherein the state of the indicator light comprises three states of on, off and flashing of the indicator light;
b2, performing OCR algorithm processing on the indicator light region to obtain character information of the corresponding indicator light, and acquiring the unique identification code of the indicator light according to the character information;
and b3, comparing the unique identification code of the indicator light and the state of the indicator light with the normal state, and judging whether the fire alarm controller is in an alarm state.
Further, in the fourth step, the method for analyzing the display information of the screen of the fire alarm controller includes:
judging the type of the target line by using a regular expression according to the characters/symbols extracted in the step a1, and extracting information according to the type of the target line to obtain an alarm type and alarm details; the alarm details include at least: alarm serial number, alarm time, alarm equipment ID and alarm equipment installation place;
in the fourth step, the method for analyzing the display information of the indicator light comprises the following steps:
and matching with a pre-stored alarm type according to the state of the indicator lamp and the unique identification code to obtain the matched alarm type.
Further, in the fifth step, the operation information of the attendant includes information of operating keys of the attendant and information of changing the operation state of the fire alarm controller.
Further, the fifth step comprises the following steps:
d1, acquiring a video within a preset time period after the warning condition occurs;
d2, detecting the operation mode of the fire alarm controller in the video by using an effective-det algorithm, and recording, wherein the operation mode comprises an automatic mode and a manual mode;
d3, detecting whether the display state of the screen or the indicator light of the fire alarm controller changes, if not, recording as not operating, if so, executing the next step;
d4, when the screen or the indicator light of the fire alarm controller changes, detecting whether a finger appears in the current image by using an efficient-det algorithm, and if the finger is not detected, recording that the operation is not performed; if the finger is detected, executing the next step;
and d5, calculating keys covered by the fingers, if the fingers only cover one key, judging the key to be a triggered key, and if the fingers cover a plurality of keys, combining a screen or an indicator light to display information to discharge an interference key to obtain the triggered key.
Further, the sixth step includes the steps of:
step f1, judging whether the key triggered by the attendant is in the allowed key list, if so, executing the next step, and if not, judging that the attendant is not in compliance;
and f2, judging whether the time for the attendant to trigger the key is within a specified time range, if so, judging compliance, and if not, judging non-compliance.
After the technical scheme of the invention is adopted, the following beneficial effects are brought:
the invention can record the equipment police condition and the operation of the on-duty personnel on the equipment at the same time after being implemented, automatically judge whether the operation of the on-duty personnel is illegal by combining the operation rule, and conveniently restore and pursue the incident in the future.
Drawings
FIG. 1: an operation interface diagram of a fire alarm controller of a certain type;
FIG. 2: a flow diagram of the present invention;
FIG. 3: the invention identifies the schematic diagram of the operation information of the operator on duty;
wherein: 1. fire alarm controller 2, screen 3, pilot lamp area 4, operating area 5, finger 6, minimum rectangle frame.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Example one
Referring to fig. 2 and 3, a method for monitoring an alarm processing operation of a video-based fire alarm controller includes the steps of:
step one, establishing a corresponding operation rule according to the alarm occurrence type, and storing the operation rule in a rule base.
Specifically, the alarm types are various, and may generally include: the fire alarm system comprises an initial alarm information alarm, a fire alarm information alarm, a fault information alarm, a starting information alarm, a feedback information alarm, a shielding information alarm and a fire alarm information alarm, wherein corresponding alarm types are different for different fire alarm controllers 1, and the specific alarm types can be adjusted for different fire alarm controllers 1. The operation rule includes at least the following information: the alarm type, the key list which corresponds to the alarm type and is allowed to be clicked, the screen display state and the indicator light display state after the key is triggered, whether the operation state of the fire alarm controller 1 is allowed to be switched or not, and the alarm time limit processing time. Each alarm type at least corresponds to one set of operation rules, when the alarm occurs, the operation of the operator on duty only accords with the operation rules, and otherwise, the operation is not in compliance.
And secondly, monitoring the region of interest through a camera, and acquiring a video of the region of interest in real time. The region of interest covers at least the screen 2 of the fire alarm controller 1, the indicator light region 3 and the operating region 4 of the fire alarm controller 1. Specifically, the camera is installed in a position right facing the fire alarm controller 1, and the camera adopts a high-definition camera and can at least ensure that information such as characters and figures on the fire alarm controller 1 can be clearly shot.
And step three, extracting display information of a screen 2 and an indicator lamp of the fire alarm controller 1 through a deep learning algorithm according to the acquired video, judging whether the fire alarm controller 1 is in an alarm state or not according to the extracted display information, executing the next step if the fire alarm controller 1 is in the alarm state, and continuing monitoring if the fire alarm controller 1 is not in the alarm state.
Specifically, the method for extracting the display information of the screen 2 of the fire alarm controller 1 and judging the alarm state comprises the following steps:
step a1, performing OCR (Optical Character Recognition) processing on the screen 2 image to obtain the characters/symbols displayed on the screen 2 and the corresponding position information, because the display information on the screen 2 of the fire alarm controller 1 is relatively simple, the characters/symbols information can be extracted quickly through OCR Recognition.
Step a2, using the specific position of the screen 2 with some specific characters/coincidence, or only using some specific characters/coincidence as the characteristic, to judge whether the fire alarm controller 1 is in the alarm state, if the fire alarm occurs, the specific position of the screen 2 of the fire alarm controller 1 will have a fire symbol, when the OCR recognizes that the fire symbol appears on the screen 2, the fire alarm controller can be judged to be in the alarm state, or by comparing with the characters/symbols extracted in the normal state, the fire alarm controller can be judged to be in the alarm state.
Specifically, the method for extracting the display information of the indicator light and judging the alarm state comprises the following steps:
and b1, acquiring the state and the position information of the indicator light through an efficacy-det algorithm, wherein the state of the indicator light comprises three states of on, off and flashing of the indicator light. The effective-det algorithm was developed by the Google brain team, and the details can be found in the paper Effect det: Scalable and Effect Object Detection. According to the invention, the identification of the indicator light with higher precision can be realized by calling the effective-det algorithm and training the model.
The method for judging the flicker of the indicator lamp comprises the following steps: and judging whether the state of the indicator light is switched more than twice within a preset time range (which can be set to be 3 seconds), if so, returning to flicker, and otherwise, returning to the current state of the indicator light.
B2, acquiring the unique identification code of the indicator light according to the position information of the indicator light; because the position of each indicator light is determined, the unique identification code of each indicator light can be directly acquired through coordinate comparison according to the positions of the indicator lights.
And b3, comparing the unique identification code of the indicator light with the state of the indicator light, and judging whether the fire alarm controller 1 is in an alarm state.
In the process of judging the alarm state by using the display information of the screen 2 or the indicator light, the fire alarm controller 1 can be judged to be in the alarm state at the moment as long as the screen 2 or the indicator light is detected to be in the alarm state arbitrarily.
And step four, analyzing the display information of the extraction screen 2 and the indicator light, identifying specific alarm types and alarm details, and calling corresponding operation rules in the rule base.
Specifically, the method for analyzing the display information on the screen 2 of the fire alarm controller 1 includes:
according to the characters/symbols extracted in the step a1, the type of the target line is judged by using the regular expression, and information extraction is carried out according to the type of the target line to obtain an alarm type and alarm details, because a screen 2 of the fire alarm controller 1 can display a plurality of lines of character information, and the alarm type and the alarm details can be directly displayed in a character form, each line of information displayed on the screen 2 is matched through the regular expression, if the line of information can be matched, the line of content is extracted to obtain the alarm type and the alarm details, if the line of information can not be matched, the next line of information is continuously matched, and the alarm details at least comprise: alarm serial number, alarm time, alarm device ID and alarm device installation place.
Specifically, the method for analyzing the display information of the indicator light comprises the following steps:
according to the state of the indicator light and the unique identification code, the indicator light is matched with the pre-stored alarm type to obtain the matched alarm type, and the display state of the indicator light can be associated with the alarm type, so that the specific alarm type can be judged after the state of the indicator light and the unique identification code are obtained.
And fifthly, acquiring a video within a preset time period after the warning condition occurs, identifying the operation information of the operator on duty through a target detection algorithm, and determining whether the operation of the operator on duty is effective or not by combining the change states of the screen 2 and the indicator lamp. The operation information of the attendant comprises information of operating keys of the attendant and information of changing the running state of the fire alarm controller 1.
Specifically, the step five comprises the following detailed steps:
and d1, acquiring the video within a preset time period after the warning condition occurs, wherein the preset time can be 10 minutes or 15 minutes or can be flexibly set according to the requirement.
And d2, detecting the operation modes of the fire alarm controller 1 in the video by using an effective-det algorithm, and recording, wherein the operation modes comprise an automatic mode and a manual mode. Generally, under normal conditions, the fire alarm controller 1 operates in a manual mode, the fire alarm gives an alarm, and after the false alarm of the sensor is eliminated manually, the fire alarm controller 1 is switched from the manual mode to an automatic mode, or the fire extinguishing equipment is started manually.
And d3, detecting whether the display state of the screen 2 or the indicator light is changed, if not, recording that the screen is not operated, and if so, executing the next step, wherein the change of the screen 2 is detected by an OCR algorithm, and the change of the indicator light is detected by an effective-det algorithm.
D4, when the screen 2 or the indicator light of the fire alarm controller 1 changes, detecting whether a finger 5 appears in the current image by using an efficient-det algorithm, and if the finger 5 is not detected, recording that the operation is not performed; if the finger 5 is detected, the next step is performed.
And d5, calculating the keys covered by the finger 5, if the finger 5 only covers one key, judging that the key is the triggered key, and if the finger 5 covers a plurality of keys, combining the screen 2 or the indicator light to display information to discharge the interference key to obtain the triggered key.
Specifically, the method for calculating the key covered by the finger 5 includes the steps of detecting the edge of the finger 5 through an effective-det algorithm, then using a minimum rectangular frame 6 to select a first joint of the finger 5, simultaneously calculating the coordinate and area information of the minimum rectangular frame 6, then calculating all keys falling within the range of the minimum rectangular frame 6 according to the coordinate, area and position information of the keys of the minimum rectangular frame 6, and finally discharging interference keys according to the display state of the screen 2 or the lighting state of an indicator lamp after the keys are triggered to obtain the triggered keys.
Step six, matching the effective operation information of the operator on duty with the called operation rule, if the operation information is in accordance with the called operation rule, judging that the operation is in compliance, if the operation information is not in compliance, judging that the operation is not in compliance,
specifically, the step six comprises the following detailed steps:
step f1, judging whether the key triggered by the attendant is in the allowed key list, if so, executing the next step, and if not, judging that the attendant is not in compliance;
and f2, judging whether the time for the attendant to trigger the key is within a specified time range, if so, judging compliance, and if not, judging non-compliance.
Through the two steps of judging processes, the information whether the operation of the operator on duty is in compliance can be obtained.
And step seven, reporting the alarm type, the alarm details, the operation information of the person on duty and the compliance information to a server, and pushing reminding information to a supervisor or a background manager in time when the non-compliance information exists in the reported information.
Preferably, the sixth step further includes, when the judgment result is that the person is not in compliance, starting an audible and visual alarm device or other prompting devices to send a prompt to the person on duty.
Example two
The difference between this embodiment and the first embodiment is that the manner of obtaining the unique identifier code of the indicator light in the third step is different, and specifically, in the third step, the method for extracting the display information of the indicator light and determining the alarm state includes:
and b1, acquiring the state and the position information of the indicator light through an efficacy-det algorithm, wherein the state of the indicator light comprises three states of on, off and flashing of the indicator light.
And b2, performing OCR algorithm processing on the indicator light region to obtain character information of the corresponding indicator light, and acquiring the unique identification code of the indicator light according to the character information. Because the characters are generally marked around the indicator light, the character information of the indicator light can be extracted through an OCR algorithm, and because the characters marked on the indicator light with different functions are different, the unique identification code of the indicator light can be obtained by utilizing the extracted characters.
And b3, comparing the unique identification code of the indicator light with the state of the indicator light, and judging whether the fire alarm controller 1 is in an alarm state.
The fire alarm controller can automatically monitor whether the fire alarm controller 1 is in compliance when the person on duty operates, and can send out prompt when the person on duty detects that the fire alarm controller 1 is not in compliance, so that hidden dangers can be eliminated as soon as possible, and a basis is provided for future event recovery and responsibility tracing of related personnel.
The foregoing is directed to embodiments of the present invention, and it is understood that various changes and modifications may be made by those skilled in the art without departing from the spirit and scope of the invention.
Claims (9)
1. A fire alarm controller alarm processing operation monitoring method based on video is characterized by comprising the following steps:
step one, establishing a corresponding operation rule according to an alarm occurrence type, and storing the operation rule in a rule base;
monitoring an interested area through a camera, and acquiring a video of the interested area in real time, wherein the interested area at least covers a screen of a fire alarm controller, an indicator light area and an operation area of the fire alarm controller;
extracting display information of a screen and an indicator lamp of the fire alarm controller through a deep learning algorithm according to the acquired video, judging whether the fire alarm controller is in an alarm state or not according to the extracted display information, executing the next step if the fire alarm controller is in the alarm state, and continuing monitoring if the fire alarm controller is not in the alarm state;
analyzing the display information of the extraction screen and the indicator light, identifying specific alarm types and alarm details, and calling corresponding operation rules in a rule base;
acquiring a video within a preset time period after the warning condition occurs, identifying the operation information of the operator on duty through a target detection algorithm, and determining whether the operation of the operator on duty is effective or not by combining the change states of a screen and an indicator lamp;
step six, matching the effective operation information of the operator on duty with the called operation rule, if the operation information is in accordance with the called operation rule, judging that the operation is in compliance, and if the operation information is not in compliance, judging that the operation is not in compliance;
and step seven, reporting the alarm type, the alarm details, the operation information of the person on duty and the compliance information to a server, and pushing reminding information to a supervisor or a background manager in time when the non-compliance information exists in the reported information.
2. The method as claimed in claim 1, wherein the sixth step further comprises activating an audible and visual alarm or other prompting device to prompt the person on duty when the determination result is that the fire alarm controller is not in compliance.
3. The method for monitoring fire alarm controller alert process operations based on video of claim 1, wherein in the first step,
the alarm types are at least divided into: first alarm information alarm, fire alarm information alarm, fault information alarm, start information alarm, feedback information alarm, shield information alarm and alarm information alarm;
the operation rule includes at least the following information: the fire alarm controller comprises an alarm type, a button list which is allowed to be clicked and corresponds to the alarm type, a screen display state and an indicator light display state after the button is triggered, whether the operation state of the fire alarm controller is allowed to be switched or not, and alarm time limit processing time.
4. The video-based fire alarm controller alarm handling operation monitoring method of claim 1,
in the third step, the method for extracting the screen display information of the fire alarm controller and judging the alarm state comprises the following steps:
a1, performing OCR processing on the screen image to obtain characters/symbols displayed on the screen and corresponding position information;
a2, using the specific position of the screen with some specific characters/coincidence, or only using some specific characters/coincidence as the characteristic, judging whether the fire alarm controller is in alarm state;
in the third step, the method for extracting the display information of the indicator light and judging the alarm state comprises the following steps:
b1, acquiring the state and position information of the indicator light through an effect-det algorithm, wherein the state of the indicator light comprises three states of on, off and flashing of the indicator light;
b2, acquiring the unique identification code of the indicator light according to the position information of the indicator light;
and b3, comparing the unique identification code of the indicator light and the state of the indicator light with the normal state, and judging whether the fire alarm controller is in an alarm state.
5. The video-based fire alarm controller alarm handling operation monitoring method of claim 1,
in the third step, the method for extracting the screen display information of the fire alarm controller and judging the alarm state comprises the following steps:
a1, performing OCR processing on the screen image to obtain characters/symbols displayed on the screen and corresponding position information;
a2, using the specific position of the screen with some specific characters/coincidence, or only using some specific characters/coincidence as the characteristic, judging whether the fire alarm controller is in alarm state;
in the third step, the method for extracting the display information of the indicator light and judging the alarm state comprises the following steps:
b1, acquiring the state and position information of the indicator light through an effect-det algorithm, wherein the state of the indicator light comprises three states of on, off and flashing of the indicator light;
b2, performing OCR algorithm processing on the indicator light region to obtain character information of the corresponding indicator light, and acquiring the unique identification code of the indicator light according to the character information;
and b3, comparing the unique identification code of the indicator light and the state of the indicator light with the normal state, and judging whether the fire alarm controller is in an alarm state.
6. The video-based fire alarm controller alarm processing operation monitoring method according to claim 4 or 5,
in the fourth step, the method for analyzing the display information of the screen of the fire alarm controller comprises the following steps:
judging the type of the target line by using a regular expression according to the characters/symbols extracted in the step a1, and extracting information according to the type of the target line to obtain an alarm type and alarm details; the alarm details include at least: alarm serial number, alarm time, alarm equipment ID and alarm equipment installation place;
in the fourth step, the method for analyzing the display information of the indicator light comprises the following steps:
and matching with a pre-stored alarm type according to the state of the indicator lamp and the unique identification code to obtain the matched alarm type.
7. The method as claimed in claim 1, wherein the operation information of the attendant in the step five includes information on an operation button of the attendant and information on a state of changing the operation of the fire alarm controller.
8. The method of claim 7, wherein the step five includes the steps of:
d1, acquiring a video within a preset time period after the warning condition occurs;
d2, detecting the operation mode of the fire alarm controller in the video by using an effective-det algorithm, and recording, wherein the operation mode comprises an automatic mode and a manual mode;
d3, detecting whether the display state of the screen or the indicator light of the fire alarm controller changes, if not, recording as not operating, if so, executing the next step;
d4, when the screen or the indicator light of the fire alarm controller changes, detecting whether a finger appears in the current image by using an efficient-det algorithm, and if the finger is not detected, recording that the operation is not performed; if the finger is detected, executing the next step;
and d5, calculating keys covered by the fingers, if the fingers only cover one key, judging the key to be a triggered key, and if the fingers cover a plurality of keys, combining a screen or an indicator light to display information to discharge an interference key to obtain the triggered key.
9. The method for monitoring an alarm handling operation of a video-based fire alarm controller according to claim 1, wherein the sixth step includes the steps of:
step f1, judging whether the key triggered by the attendant is in the allowed key list, if so, executing the next step, and if not, judging that the attendant is not in compliance;
and f2, judging whether the time for the attendant to trigger the key is within a specified time range, if so, judging compliance, and if not, judging non-compliance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110483199.8A CN113380000B (en) | 2021-04-30 | 2021-04-30 | Video-based fire alarm processing operation monitoring method for fire alarm controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110483199.8A CN113380000B (en) | 2021-04-30 | 2021-04-30 | Video-based fire alarm processing operation monitoring method for fire alarm controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113380000A true CN113380000A (en) | 2021-09-10 |
| CN113380000B CN113380000B (en) | 2022-12-16 |
Family
ID=77570383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110483199.8A Active CN113380000B (en) | 2021-04-30 | 2021-04-30 | Video-based fire alarm processing operation monitoring method for fire alarm controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113380000B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537166A (en) * | 2021-09-15 | 2021-10-22 | 北京科技大学 | Alarm method, alarm device and storage medium |
| CN114501185A (en) * | 2022-01-27 | 2022-05-13 | 浙江华消科技有限公司 | Control method and device for fire acousto-optic alarm and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1185436A (en) * | 1997-09-09 | 1999-03-30 | Yokogawa Electric Corp | Distributed controller |
| CN102157049A (en) * | 2011-04-28 | 2011-08-17 | 公安部沈阳消防研究所 | Intelligent image identification based remote monitoring transmission system of operating conditions of fire alarm controller |
| US20120173227A1 (en) * | 2011-01-04 | 2012-07-05 | Olaworks, Inc. | Method, terminal, and computer-readable recording medium for supporting collection of object included in the image |
| CN105786316A (en) * | 2016-02-26 | 2016-07-20 | 湖北汽车工业学院 | Computer recognition method for evaluating software operating level |
| CN108960554A (en) * | 2018-02-09 | 2018-12-07 | 珠海优特电力科技股份有限公司 | It is a kind of to run and maintenance safety control device, system and method |
| CN109165151A (en) * | 2018-07-05 | 2019-01-08 | 北京西普阳光教育科技股份有限公司 | The evaluation method and device of computer based image conversion interface alternation operation |
| CN111385536A (en) * | 2020-03-05 | 2020-07-07 | 绍兴凌科智能技术有限公司 | Workshop monitoring method and system based on acousto-optic signal identification |
| CN111857470A (en) * | 2020-07-15 | 2020-10-30 | 杭州真鹏科技有限公司 | Unattended control method and device for production equipment and controller |
| CN112188263A (en) * | 2020-09-10 | 2021-01-05 | 珠海格力电器股份有限公司 | Bullet screen information control method and playing equipment |
| CN112629105A (en) * | 2019-09-24 | 2021-04-09 | 青岛海尔电冰箱有限公司 | Virtual control panel operation identification method and refrigerator |
-
2021
- 2021-04-30 CN CN202110483199.8A patent/CN113380000B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1185436A (en) * | 1997-09-09 | 1999-03-30 | Yokogawa Electric Corp | Distributed controller |
| US20120173227A1 (en) * | 2011-01-04 | 2012-07-05 | Olaworks, Inc. | Method, terminal, and computer-readable recording medium for supporting collection of object included in the image |
| CN102157049A (en) * | 2011-04-28 | 2011-08-17 | 公安部沈阳消防研究所 | Intelligent image identification based remote monitoring transmission system of operating conditions of fire alarm controller |
| CN105786316A (en) * | 2016-02-26 | 2016-07-20 | 湖北汽车工业学院 | Computer recognition method for evaluating software operating level |
| CN108960554A (en) * | 2018-02-09 | 2018-12-07 | 珠海优特电力科技股份有限公司 | It is a kind of to run and maintenance safety control device, system and method |
| CN109165151A (en) * | 2018-07-05 | 2019-01-08 | 北京西普阳光教育科技股份有限公司 | The evaluation method and device of computer based image conversion interface alternation operation |
| CN112629105A (en) * | 2019-09-24 | 2021-04-09 | 青岛海尔电冰箱有限公司 | Virtual control panel operation identification method and refrigerator |
| CN111385536A (en) * | 2020-03-05 | 2020-07-07 | 绍兴凌科智能技术有限公司 | Workshop monitoring method and system based on acousto-optic signal identification |
| CN111857470A (en) * | 2020-07-15 | 2020-10-30 | 杭州真鹏科技有限公司 | Unattended control method and device for production equipment and controller |
| CN112188263A (en) * | 2020-09-10 | 2021-01-05 | 珠海格力电器股份有限公司 | Bullet screen information control method and playing equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537166A (en) * | 2021-09-15 | 2021-10-22 | 北京科技大学 | Alarm method, alarm device and storage medium |
| CN114501185A (en) * | 2022-01-27 | 2022-05-13 | 浙江华消科技有限公司 | Control method and device for fire acousto-optic alarm and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113380000B (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7359237B2 (en) | Video processing system, video processing method, and video processing program | |
| CN113380000B (en) | Video-based fire alarm processing operation monitoring method for fire alarm controller | |
| CN108389359B (en) | Deep learning-based urban fire alarm method | |
| CN109271881B (en) | Safety management and control method and device for personnel in transformer substation and server | |
| CN107437318B (en) | Visible light intelligent recognition algorithm | |
| CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
| CN104091354A (en) | Fire detection method based on video images and fire detection device thereof | |
| CN111932709A (en) | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification | |
| CN110853268A (en) | Method for realizing intrusion detection vulnerability real-time scanning based on analysis of mass data of pipe gallery system | |
| CN108831097A (en) | Flame smog identifying system and method | |
| CN114937237A (en) | Construction site safety monitoring method and system based on AI intelligent identification | |
| CN115100813A (en) | Intelligent community system based on digital twins | |
| CN114550082A (en) | Easy-to-use efficient AI (Artificial Intelligence) recognition algorithm | |
| CN113554364A (en) | Disaster emergency management method, device, equipment and computer storage medium | |
| CN112542022A (en) | Automatic inspection system for intelligent production | |
| CN104721996A (en) | Auto-centering fire-fighting apparatus and method based on flame image recognition | |
| CN110928305A (en) | Patrol method and system for railway passenger station patrol robot | |
| CN112419091B (en) | Intelligent video safety control method for field operation of power distribution network driven by knowledge graph | |
| CN206058456U (en) | It is a kind of for fire identification can monitor in real time image processing system | |
| CN116449679A (en) | Intelligent hospital security linkage control method and system based on digital twinning | |
| CN113936293A (en) | Video information-based off-duty personnel detection method, control device and storage medium | |
| CN111881733B (en) | Method and system for judging and guiding worker operation step standard visual identification | |
| CN114281656A (en) | Intelligent central control system | |
| CN110543830B (en) | Motion detection method, motion detection device, and storage medium | |
| CN204684512U (en) | Based on flame image identification automatic centering fire plant |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 266103 Haier Industrial Park, 1 Haier Road, Laoshan District, Shandong, Qingdao Applicant after: Hainayun IOT Technology Co.,Ltd. Applicant after: Qingdao Aidian Technology Co.,Ltd. Address before: 266103 Haier Industrial Park, 1 Haier Road, Laoshan District, Shandong, Qingdao Applicant before: Qingdao hainayun Technology Holding Co.,Ltd. Applicant before: Qingdao Aidian Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221115 Address after: 266101 Haier Industrial Park, 1 Haier Road, Laoshan District, Shandong, Qingdao Applicant after: Hainayun IOT Technology Co.,Ltd. Applicant after: Qingdao Aidian Technology Co.,Ltd. Applicant after: Qingdao hainayun Intelligent System Co.,Ltd. Address before: 266103 Haier Industrial Park, 1 Haier Road, Laoshan District, Shandong, Qingdao Applicant before: Hainayun IOT Technology Co.,Ltd. Applicant before: Qingdao Aidian Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240103 Address after: 266101 Haier Industrial Park, 1 Haier Road, Laoshan District, Shandong, Qingdao Patentee after: Hainayun IOT Technology Co.,Ltd. Patentee after: Qingdao hainayun Intelligent System Co.,Ltd. Address before: 266101 Haier Industrial Park, 1 Haier Road, Laoshan District, Shandong, Qingdao Patentee before: Hainayun IOT Technology Co.,Ltd. Patentee before: Qingdao Aidian Technology Co.,Ltd. Patentee before: Qingdao hainayun Intelligent System Co.,Ltd. |