Fire-fighting monitoring method and system

Abstract

The invention provides a fire-fighting monitoring method and a fire-fighting monitoring system. Smog data in a fire-fighting Internet of Things unit environment is collected, and a fire condition in the environment is monitored according to the smog data; acquiring daily operation data of different fire-fighting equipment, and unifying transmission protocols of the operation data of the different fire-fighting equipment; transmitting the operation data to a monitoring center for analysis, packaging the analyzed data, inputting the packaged data into an adapter for event stream conversion to obtain a plurality of first events, and abstracting and monitoring the plurality of first events to obtain a second event; based on the second event, operation data, corresponding to the fire condition, of different fire fighting equipment is obtained, so that the operation condition of the fire fighting equipment in a fire fighting Internet of Things unit is monitored, and the fire fighting monitoring method is good in timeliness and wide in application range.

Description

Technical Field

[0001] The present invention relates to the field of fire protection technology, and in particular to a fire protection monitoring method and system. Background Art

[0002] Firefighting Internet of Things refers to the use of Internet of Things information sensing and communication technologies to link the equipment and facilities in the firefighting system through social fire supervision and management and the firefighting information required by various elements involved in firefighting and rescue by firefighting agencies.

[0003] Fire monitoring mainly includes fire monitoring and fire equipment operation status monitoring. When a fire occurs, the burning of materials will generate parameters such as temperature, smoke, and flame. The current fire monitoring and detection technologies mainly include temperature detection, smoke detection, and flame detection. Temperature detectors have good stability and are easy to replace, but they also have the disadvantages of low sensitivity and slow response. Smoke detectors are easily affected by dust, water vapor, etc., which may lead to false alarms. Flame detectors need to receive radiation from open flames to work, and have obvious lags. Traditional detection technology has certain limitations in fire monitoring. In addition, the current monitoring of the operation status of fire equipment is mainly carried out through regular on-site inspections and maintenance by technical personnel. This monitoring method makes it difficult to detect equipment failures in a timely manner, and there are great safety hazards. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide a fire monitoring method and system to solve the technical problems existing in the prior art.

[0005] The present invention provides a fire monitoring method for monitoring the fire conditions of each fire Internet of Things unit and the operating conditions of fire fighting equipment, including: Collect smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit, and monitor the fire situation in the environment according to the smoke static data and the smoke dynamic data; Constructing a low-power wide-area gateway with a star topology structure, wherein the low-power wide-area gateway is respectively connected to sensors in different firefighting equipment for communication; Based on the low-power wide-area gateway, daily operation data of different fire-fighting equipment is obtained, duplicate bytes in the operation data are removed, and the operation data after the duplicate bytes are removed is formatted to unify the transmission protocol of the operation data of different fire-fighting equipment; The format-converted operation data is transmitted to the monitoring center for parsing, the parsed data is encapsulated and input into the adapter for event stream conversion to obtain a plurality of first events, and the plurality of first events are abstracted and monitored to obtain a second event; Based on the second event, the operating data corresponding to different fire-fighting equipment and the fire conditions are obtained, and the operating status of the fire-fighting equipment in the fire-fighting Internet of Things unit is monitored according to the operating data corresponding to the fire conditions.

[0006] Preferably, the step of collecting smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit, and monitoring the fire condition in the environment according to the smoke static data and the smoke dynamic data includes: Obtaining environmental video images of the firefighting IoT unit within a preset time, extracting activity areas in the environmental video images, and preprocessing the extracted activity areas to screen out a number of suspected smoke areas in the activity areas; Performing smoke feature analysis on the plurality of suspected smoke areas in a time series space, wherein the smoke feature analysis includes at least motion feature analysis, concentration feature analysis, and image change consistency feature analysis; The fire condition in the fire protection Internet of Things unit environment is judged based on the results of the smoke characteristic analysis.

[0007] Preferably, the step of performing smoke feature analysis on the plurality of suspected smoke areas in the time series space comprises: Obtaining the total number of image frames of the suspected smoke areas within a preset time; Divide the motion direction according to the spatial range to obtain a motion direction model, record the motion direction of each frame image corresponding to the suspected smoke area in the motion direction model, and make a first judgment according to the motion direction of the image to complete the motion feature analysis of the smoke; Constructing a smoke concentration equation of the image, solving the smoke concentration equation to obtain a dimming coefficient of a pixel point in each frame of the image, and performing a second judgment based on the dimming coefficient in each frame of the image to complete the smoke concentration feature analysis; The grayscale difference between the two frames of image is obtained and used as the grayscale change of the image. The consistency ratio of the image is calculated based on the grayscale change. A third judgment is performed based on the consistency ratio to complete the consistency analysis of the smoke image change.

[0008] Preferably, the smoke concentration equation is expressed as:

[0009] In the formula, is the grayscale of the current image block, is the grayscale of the background corresponding to the current image block, A is the value of air light, is the smoke penetration rate;

[0010] In the formula, is the attenuation coefficient, is the thickness of the smoke.

[0011] Preferably, the step of removing duplicate bytes from the operating data and converting the format of the operating data after removing the duplicate bytes to unify the transmission protocol of the operating data of different fire fighting equipment includes: Adding redundant codes to the received operating data, performing frequency band sequence expansion on the operating data with the redundant codes added, and performing linear modulation on the operating data after the frequency band sequence expansion, so that the operating data corresponding to different sensors are transmitted using the same frequency; Sending the linearly modulated operation data to a network server based on the UDP / IP protocol, performing address matching based on the terminal node address and the execution address, decrypting the operation data with successful address matching, and removing duplicate bytes in the operation data according to the redundant code; Based on the MQTT protocol, the operation data with duplicate bytes removed is published to the application server. Based on the data parsing service in the application server, the transmission mode of the operation data is standardized to form a unified transmission protocol.

[0012] Preferably, the step of sending the linear modulated operation data to the network server based on the UDP / IP protocol includes: Sending the linearly modulated operation data to the main thread of the network server based on the UDP / IP message protocol, and connecting the received operation data with the slot function in the main thread of the network server; After the slot function is connected with the running data, a corresponding sub-thread is created, in which data splitting processing is performed according to the subject classification of the running data, and the main thread receives the next round of running data at the same time; The data processed by the child threads are stored in a preset table in the form of strings, the data processed by each child thread is encapsulated into a class, and the shared data received by two adjacent child threads are locked and unlocked based on the mutex array.

[0013] Preferably, the steps of transmitting the format-converted operation data to the monitoring center for parsing, encapsulating the parsed data and inputting it into the adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events to obtain a second event include: The format-converted operation data is transmitted to the monitoring center for parsing, the disordered noise data in the operation data is obtained and removed, and the operation data after the disordered noise data is removed is semantically converted; The semantically transformed operation data is encapsulated and inserted into a first event sequence, and an event definition is performed on the operation data inserted into the first event sequence based on an event definition module to obtain a first event; Using the first event as an input stream of a second event engine, merging, filtering and statistically analyzing the first event input to the second event engine to complete abstract processing of the first event; Based on the predefined monitoring rules, the first event after abstract processing is queried, filtered and aggregated to complete the monitoring process of the first event and to mine the second event reflecting the operating status of the fire-fighting equipment in the first event.

[0014] The present invention also proposes a fire monitoring system for monitoring the fire conditions of each fire IoT unit and the operating conditions of fire fighting equipment, including: A collection module, used to collect smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit, and monitor the fire situation in the environment according to the smoke static data and the smoke dynamic data; A building module, used to build a low-power wide-area gateway with a star topology, wherein the low-power wide-area gateway is respectively connected to the sensors in different fire-fighting equipment for communication; A conversion module, used to obtain daily operation data of different fire-fighting equipment based on the low-power wide-area gateway, remove duplicate bytes in the operation data, and convert the format of the operation data after removing the duplicate bytes to unify the transmission protocol of the operation data of different fire-fighting equipment; A parsing module, used for transmitting the format-converted operation data to a monitoring center for parsing, encapsulating the parsed data and inputting the data into an adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events to obtain a second event; A monitoring module is used to obtain operating data corresponding to different fire-fighting equipment and fire conditions based on the second event, and monitor the operating conditions of the fire-fighting equipment in the fire-fighting Internet of Things unit according to the operating data corresponding to the fire conditions.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the fire monitoring method proposed in the present application first monitors the fire conditions in the environment in real time according to the static data and dynamic data of the smoke in the environment, thereby improving the timeliness of fire condition monitoring; obtains the daily operation data of the fire-fighting equipment in real time, and converts the format of the operation data of different fire-fighting equipment to unify the transmission protocol of the operation data in different fire-fighting equipment, thereby improving the efficiency of data transmission; processes the operation data after format conversion based on the dual event method, thereby identifying in real time the operation data corresponding to the fire conditions in the daily operation data of different fire-fighting equipment, and then monitors the operation status of the monitoring fire-fighting equipment; solves the shortcomings of poor timeliness and great safety hazards of manual inspection and maintenance of fire-fighting equipment, and is suitable for large-scale promotion.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the fire monitoring method in Embodiment 1 of the present invention; Figure 2 This is a structural block diagram of a computer in Embodiment 4 of the present invention.

[0018] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0019] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0021] Embodiment 1 See also Figure 1 , which is a fire monitoring method in Embodiment 1 of the present invention, and is used to monitor the fire conditions of each fire IoT unit and the operating conditions of fire fighting equipment; specifically, the fire monitoring method specifically includes steps S10 to S40: S10, collecting smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit, and monitoring the fire situation in the environment according to the smoke static data and the smoke dynamic data; In specific implementation, since conventional smoke detection is mainly triggered after the physical quantity contact is converted into an electrical signal, it is mainly suitable for fire monitoring in small spaces, has strong hysteresis, and is easily affected by interference from water vapor, dust, etc., with the development of image processing technology, this application analyzes the image characteristics of smoke formed by fire to improve the monitoring efficiency when smoldering or the flame is small in the early stage of fire; in the process of smoke generation, the smoke includes dynamic data such as floating and rising, as well as static data such as color. This application combines dynamic data and static data to perform smoke analysis to improve the accuracy of smoke recognition.

[0022] Specifically, the steps of collecting smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit and monitoring the fire condition in the environment according to the smoke static data and the smoke dynamic data include: Obtaining environmental video images of the firefighting IoT unit within a preset time, extracting activity areas in the environmental video images, and preprocessing the extracted activity areas to screen out a number of suspected smoke areas in the activity areas; Performing smoke feature analysis on the plurality of suspected smoke areas in a time series space, wherein the smoke feature analysis includes at least motion feature analysis, concentration feature analysis, and image change consistency feature analysis; The fire condition in the fire protection Internet of Things unit environment is judged based on the results of the smoke characteristic analysis.

[0023] In this embodiment, a multi-Gaussian model can be used to extract active areas in environmental video images. Preprocessing of active area images includes grayscale processing, binarization processing, filtering and denoising processing, etc., to screen out images that may be smoke areas.

[0024] Specifically, the step of performing smoke feature analysis on the plurality of suspected smoke areas in the time series space includes: Obtaining the total number of image frames of the suspected smoke areas within a preset time; Divide the motion direction according to the spatial range to obtain a motion direction model, record the motion direction of each frame image corresponding to the suspected smoke area in the motion direction model, and make a first judgment according to the motion direction of the image to complete the motion feature analysis of the smoke; Constructing a smoke concentration equation of the image, solving the smoke concentration equation to obtain a dimming coefficient of a pixel point in each frame of the image, and performing a second judgment based on the dimming coefficient in each frame of the image to complete the smoke concentration feature analysis; The grayscale difference between the two frames of image is obtained and used as the grayscale change of the image. The consistency ratio of the image is calculated based on the grayscale change. A third judgment is performed based on the consistency ratio to complete the consistency analysis of the smoke image change.

[0025] In this embodiment, firstly, N frames of images of several suspected smoke areas within a preset time t are obtained respectively. Optionally, the images are recorded as ,in, , , Indicates the number of suspected smoke areas, Indicates the total number of image frames within a preset time for each suspected smoke area; when a fire occurs, due to the effect of thermodynamics, the smoke mainly moves upward. If it is affected by wind, it may also spread to the surroundings. Taking the ignition point as the origin, the movement direction is divided into 30° intervals in a 180° space to obtain several movement quadrants. Under normal circumstances, the smoke mainly spreads in the quadrant of 30°-150°. When the suspected smoke area is in the quadrant of 30°-150°, it is predicted to be a smoke image. The first ratio of the number of frames predicted to be a smoke image to the total number of image frames N is calculated, and a first judgment is made based on the first ratio.

[0026] The dimmer coefficient is closely related to the smoke concentration. By constructing the smoke concentration equation of the image, the dimmer coefficients of the pixels in the preprocessed suspected smoke area images are calculated according to the smoke concentration equation, and then the light transmittance of the image is obtained. A light transmittance threshold of 0.85 is taken. When the light transmittance of the suspected smoke area is less than 0.85, it is predicted to be a smoke image. The second ratio of the number of frames predicted to be smoke images to the total number of image frames N is calculated, and a second judgment is made based on the second ratio.

[0027] It can be understood that as the smoke gradually moves away from the fire point, the smoke concentration will gradually decrease and the smoke color will gradually change from dark to light. In order to reduce the impact of different burning colors of different materials, it is necessary to grayscale the image of the suspected smoke area, and perform a difference calculation on the grayscale values ​​of the two suspected smoke area images before and after in the time series space. If the difference is greater than zero, it is predicted to be a smoke image, and the third ratio of the number of frames predicted to be smoke images to the total number of image frames N is calculated. A third judgment is made based on the third ratio. Optionally, in this embodiment, the threshold value of the first ratio is 0.8, the threshold value of the second ratio is 0.8, and the threshold value of the third ratio is 0.85. Finally, based on the comparison results of the three ratios with the corresponding ratio thresholds, it is comprehensively determined whether the suspected smoke area is a smoke image to determine whether a fire has occurred.

[0028] The expression of the smoke concentration equation is:

[0029] In the formula, is the grayscale of the current image block, is the grayscale of the background corresponding to the current image block, A is the value of air light, is the smoke penetration rate;

[0030] In the formula, is the attenuation coefficient, is the thickness of the smoke.

[0031] Furthermore, since the data processing method in most current fire monitoring systems is to connect different monitoring devices to the PC, there are problems such as insufficient system flexibility, lack of correlation between various monitoring devices, and small monitoring range of a single device. In order to improve the monitoring range and acquisition efficiency of smoke video images in the environment, in some optional embodiments, it is necessary to build a corresponding real-time video monitoring system. The fire monitoring method also includes: Arrange a high-point camera and several low-point cameras in the environment of the fire IoT unit, wherein the high-point camera is used to overlook the panoramic image of the monitoring area, and the low-point camera is used to monitor the local area; Coordinate mapping is performed on the high-point camera to mark different positions in the monitoring area with text, and the text marking is used to link and call several of the low-point cameras; Obtain the overall panoramic image of the monitored area through a high-point camera, and identify the overall fire situation in the monitored area based on the panoramic image; After identifying the fire target area of ​​interest, the high-point camera sends a description command to the low-point camera at the corresponding position based on the text annotation. The description command contains relevant information about the media stream data of the high-point camera; After receiving the description command, the low-point camera establishes a session command to the high-point camera, and receives the media stream data of the high-point camera through the RTP protocol to establish the linkage between the high-point camera and the low-point camera.

[0032] In this embodiment, by establishing a linkage between a high-point camera and a low-point camera, the high-point camera is always in working condition to monitor the overall image, while the low-point camera is switched on and off according to the media stream data of the high-point camera to collect video of part of the area according to actual needs, reduce redundant and repeated data collection, and realize high-low linkage. When smoke video data related to the fire is collected, the smoke data can be processed on the corresponding low-point camera, while the high-point camera continues to collect data over a large range.

[0033] Furthermore, in this embodiment, although the high-point camera is always in working state, when there is no fire or moving object, the data collected by the high-point camera is mostly repeated redundant data, and there is not much useful information in the redundant data. This embodiment focuses on the motion feature data related to the fire, which is saved and sent to the corresponding low-point camera. Therefore, in this embodiment, it is also necessary to judge the importance of the video frames in the high-point camera to extract the corresponding important video frames for saving and sending; Specifically, the steps for judging the importance of the video frames from the high-point camera are as follows: Select the video frame objects in the video stream of the high-point camera, and obtain the size and distance attribute information of each object in the video frame; Analyze the visual information of the video frame according to the size and distance attribute information of each object to determine whether a specific event occurs in the video frame; The importance of the video frame is judged according to whether a specific event occurs. When the importance of the video frame is greater than the preset importance, it is determined that there may be a fire in the monitored area. The video frame is saved and sent to the corresponding low-point camera.

[0034] The expression for judging the importance of video frames is:

[0035] In the formula, For the The importance of video, , is the visual information of the video frame, Indicates that the object is stationary. Indicates the object movement, Respectively The size and distance attribute information of the moving object, is the object size judgment threshold, The distance judgment threshold between moving objects;

[0036] In the formula, For the The visual information of the video, is the visual feature transformation function, For the object.

[0037] In this embodiment, when it is determined that the importance of the video frame is greater than or equal to When the video frame is saved, it is sent to the corresponding low-point camera.

[0038] S20, constructing a low-power wide-area gateway with a star topology structure, wherein the low-power wide-area gateway is communicatively connected with sensors in different firefighting equipment respectively; S30, acquiring daily operation data of different fire-fighting equipment based on the low-power wide-area gateway, removing duplicate bytes in the operation data, and converting the format of the operation data after removing the duplicate bytes to unify the transmission protocol of the operation data of different fire-fighting equipment; The steps of removing duplicate bytes from the operation data and converting the format of the operation data after removing the duplicate bytes to unify the transmission protocol of the operation data of different fire fighting equipment include: Adding redundant codes to the received operating data, performing frequency band sequence expansion on the operating data with the redundant codes added, and performing linear modulation on the operating data after the frequency band sequence expansion, so that the operating data corresponding to different sensors are transmitted using the same frequency; Sending the linearly modulated operation data to a network server based on the UDP / IP protocol, performing address matching based on the terminal node address and the execution address, decrypting the operation data with successful address matching, and removing duplicate bytes in the operation data according to the redundant code; Based on the MQTT protocol, the operation data with duplicate bytes removed is published to the application server. Based on the data parsing service in the application server, the transmission mode of the operation data is standardized to form a unified transmission protocol.

[0039] Optionally, in this embodiment, in addition to real-time monitoring of whether a fire occurs, fire monitoring also needs to further monitor the operating status of firefighting equipment, such as monitoring whether the firefighting equipment works in time or triggers an alarm when a fire occurs, and whether the firefighting equipment generates a false alarm when no fire occurs. Specifically, due to the different types of firefighting equipment deployed in firefighting Internet of Things units, there may be large differences between the communication interfaces of different firefighting equipment. In order to realize real-time collection of the operating status of firefighting equipment of networked units, a unified transmission protocol for operating data is required. In this embodiment, a low-power wide-area gateway with a star topology is first constructed to meet the needs of multiple types, long distances, high capacity, and wide coverage in the Internet of Things environment. , the complex requirements of wireless transmission; communicate and connect with different fire-fighting equipment through a low-power wide-area gateway to receive the corresponding operation data, and add redundant codes to the operation data for frequency band sequence expansion and linear modulation, which can not only improve the error detection and correction capabilities in data transmission, but also allow the operation data to be transmitted at the same frequency to improve anti-interference capabilities; all modulated data are managed by a network server, and data parsing based on redundant codes in the network server can remove duplicate bytes in the operation data; the operation data without duplicate bytes is published to the application server, and high-order data parsing is performed in the application server to standardize the transmission mode of the operation data and form a unified transmission protocol.

[0040] Furthermore, the step of sending the linear modulated operation data to the network server based on the UDP / IP protocol includes: Sending the linearly modulated operation data to the main thread of the network server based on the UDP / IP message protocol, and connecting the received operation data with the slot function in the main thread of the network server; After the slot function is connected with the running data, a corresponding sub-thread is created, in which data splitting processing is performed according to the subject classification of the running data, and the main thread receives the next round of running data at the same time; The data processed by the child threads are stored in a preset table in the form of strings, the data processed by each child thread is encapsulated into a class, and the shared data received by two adjacent child threads are locked and unlocked based on the mutex array.

[0041] Optionally, in the present embodiment, since the running data comes from different fire-fighting equipment, multiple data processing tasks can be executed simultaneously in the network server based on multiple sub-threads. Specifically, the running data from different fire-fighting equipment is connected to the slot function in the network server, and the slot function creates corresponding sub-threads for data processing according to the connected running data. At the same time, the main thread receives the next round of running data. In the present embodiment, the running data of the same fire-fighting equipment may be allocated to two adjacent sub-threads due to network congestion or network delay, which may cause the two sub-threads to process the same data, thereby causing the program to run abnormally. In order to protect the shared data allocated to the two sub-threads, in the present embodiment, the shared data is locked and unlocked based on the mutex array to ensure that only one sub-thread processes the shared data at the same time.

[0042] S40, transmitting the format-converted operation data to the monitoring center for parsing, encapsulating the parsed data and inputting it into the adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events to obtain second events; Optionally, in this embodiment, the steps of transmitting the format-converted operation data to the monitoring center for parsing, encapsulating the parsed data and inputting the data into the adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events, and obtaining a second event include: The format-converted operation data is transmitted to the monitoring center for parsing, the disordered noise data in the operation data is obtained and removed, and the operation data after the disordered noise data is removed is semantically converted; The semantically transformed operation data is encapsulated and inserted into a first event sequence, and an event definition is performed on the operation data inserted into the first event sequence based on an event definition module to obtain a first event; Using the first event as an input stream of a second event engine, merging, filtering and statistically analyzing the first event input to the second event engine to complete abstract processing of the first event; Based on the predefined monitoring rules, the first event after abstract processing is queried, filtered and aggregated to complete the monitoring process of the first event and to mine the second event reflecting the operating status of the fire-fighting equipment in the first event.

[0043] Optionally, there are many types of fire-fighting equipment, and the analysis of whether the fire-fighting equipment works in a timely manner, accurately alarms, and whether there are false alarms is relatively complicated. Therefore, in this embodiment, the dual event processing principle is adopted for data analysis to identify the operating data corresponding to the fire situation in the massive operating data; after the massive operating data is input into the adapter for event stream conversion, the first event in the event stream can be considered as a time-point-based, indivisible event. The first event is a description of the system characteristic attributes and operating status changes. The definition of the first event is mainly to perform semantic conversion so that the first event can be processed in the second event engine. A large number of first events can obtain the first event stream through the time series; the first event stream is imported into the second event engine for abstract processing, and the second event engine can obtain higher-level abstract events by continuously abstracting the first event; the pre-defined monitoring rules can be where statements, and the EPS listener can monitor and process the abstract events to monitor the data reflecting the operating status of the fire-fighting equipment in the operating data.

[0044] S50: Based on the second event, the operating data of different fire-fighting equipment corresponding to the fire situation is obtained, and the operating status of the fire-fighting equipment in the fire-fighting Internet of Things unit is monitored according to the operating data corresponding to the fire situation.

[0045] In summary, the fire monitoring method proposed in the present application first monitors the fire conditions in the environment in real time according to the static data and dynamic data of the smoke in the environment, thereby improving the timeliness of fire condition monitoring; obtains the daily operation data of the fire-fighting equipment in real time, and converts the format of the operation data of different fire-fighting equipment to unify the transmission protocol of the operation data in different fire-fighting equipment, thereby improving the efficiency of data transmission; processes the operation data after format conversion based on the dual event method, thereby identifying in real time the operation data corresponding to the fire condition in the daily operation data of different fire-fighting equipment, and then monitors the operation status of the monitoring fire-fighting equipment; solves the shortcomings of poor timeliness and great safety hazards of manual inspection and maintenance of fire-fighting equipment, and is suitable for large-scale promotion.

[0046] Embodiment 2 This embodiment provides a fire monitoring system for monitoring the fire conditions of each fire IoT unit and the operating conditions of fire fighting equipment, including: A collection module, used to collect smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit, and monitor the fire situation in the environment according to the smoke static data and the smoke dynamic data; A building module, used to build a low-power wide-area gateway with a star topology, wherein the low-power wide-area gateway is respectively connected to the sensors in different fire-fighting equipment for communication; A conversion module, used to obtain daily operation data of different fire-fighting equipment based on the low-power wide-area gateway, remove duplicate bytes in the operation data, and convert the format of the operation data after removing the duplicate bytes to unify the transmission protocol of the operation data of different fire-fighting equipment; A parsing module, used for transmitting the format-converted operation data to a monitoring center for parsing, encapsulating the parsed data and inputting the data into an adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events to obtain a second event; A monitoring module is used to obtain operating data corresponding to different fire-fighting equipment and fire conditions based on the second event, and monitor the operating conditions of the fire-fighting equipment in the fire-fighting Internet of Things unit according to the operating data corresponding to the fire conditions.

[0047] Preferably, the step of performing smoke feature analysis on the plurality of suspected smoke areas in the time series space comprises: Obtaining the total number of image frames of the suspected smoke areas within a preset time; Divide the motion direction according to the spatial range to obtain a motion direction model, record the motion direction of each frame image corresponding to the suspected smoke area in the motion direction model, and make a first judgment according to the motion direction of the image to complete the motion feature analysis of the smoke; Constructing a smoke concentration equation of the image, solving the smoke concentration equation to obtain a dimming coefficient of a pixel point in each frame of the image, and performing a second judgment based on the dimming coefficient in each frame of the image to complete the smoke concentration feature analysis; The grayscale difference between the two frames of image is obtained and used as the grayscale change of the image. The consistency ratio of the image is calculated based on the grayscale change. A third judgment is performed based on the consistency ratio to complete the consistency analysis of the smoke image change.

[0048] Preferably, the smoke concentration equation is expressed as:

[0049] In the formula, is the grayscale of the current image block, is the grayscale of the background corresponding to the current image block, A is the value of air light, is the smoke penetration rate;

[0050] In the formula, is the attenuation coefficient, is the thickness of the smoke.

[0051] Preferably, the step of removing duplicate bytes from the operating data and converting the format of the operating data after removing the duplicate bytes to unify the transmission protocol of the operating data of different fire fighting equipment includes: Adding redundant codes to the received operating data, performing frequency band sequence expansion on the operating data with the redundant codes added, and performing linear modulation on the operating data after the frequency band sequence expansion, so that the operating data corresponding to different sensors are transmitted using the same frequency; Sending the linearly modulated operation data to a network server based on the UDP / IP protocol, performing address matching based on the terminal node address and the execution address, decrypting the operation data with successful address matching, and removing duplicate bytes in the operation data according to the redundant code; Based on the MQTT protocol, the operation data with duplicate bytes removed is published to the application server. Based on the data parsing service in the application server, the transmission mode of the operation data is standardized to form a unified transmission protocol.

[0052] Preferably, the step of sending the linear modulated operation data to the network server based on the UDP / IP protocol includes: Sending the linearly modulated operation data to the main thread of the network server based on the UDP / IP message protocol, and connecting the received operation data with the slot function in the main thread of the network server; After the slot function is connected with the running data, a corresponding sub-thread is created, in which data splitting processing is performed according to the subject classification of the running data, and the main thread receives the next round of running data at the same time; The data processed by the child threads are stored in a preset table in the form of strings, the data processed by each child thread is encapsulated into a class, and the shared data received by two adjacent child threads are locked and unlocked based on the mutex array.

[0053] Preferably, the steps of transmitting the format-converted operation data to the monitoring center for parsing, encapsulating the parsed data and inputting it into the adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events to obtain a second event include: The format-converted operation data is transmitted to the monitoring center for parsing, the disordered noise data in the operation data is obtained and removed, and the operation data after the disordered noise data is removed is semantically converted; The semantically transformed operation data is encapsulated and inserted into a first event sequence, and an event definition is performed on the operation data inserted into the first event sequence based on an event definition module to obtain a first event; Using the first event as an input stream of a second event engine, merging, filtering and statistically analyzing the first event input to the second event engine to complete abstract processing of the first event; Based on the predefined monitoring rules, the first event after abstract processing is queried, filtered and aggregated to complete the monitoring process of the first event and to mine the second event reflecting the operating status of the fire-fighting equipment in the first event.

[0054] Furthermore, the monitoring system of this embodiment has the same implementation process as the monitoring method of Embodiment 1, and produces the same effect, which will not be described again here.

[0055] Embodiment 3 A third embodiment of the present invention provides a storage medium on which a computer program is stored. When the program is executed by a processor, the fire monitoring method as described above is implemented.

[0056] Embodiment 4 The present invention also provides a computer, see Figure 2 , shown is a computer in Embodiment 4 of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned fire monitoring method is implemented.

[0057] The memory 10 includes at least one type of storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10 may be an internal storage unit of a computer, such as a hard disk of the computer. In other embodiments, the memory 10 may also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Further, the memory 10 may also include both an internal storage unit of the computer and an external storage device. The memory 10 may be used not only to store application software and various types of data installed in the computer, but also to temporarily store data that has been output or is to be output.

[0058] Among them, in some embodiments, the processor 20 can be an electronic control unit (Electronic Control Unit, abbreviated as ECU, also known as a vehicle computer), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run the program code stored in the memory 10 or process data, such as executing access restriction programs, etc.

[0059] It should be pointed out that Figure 2 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0060] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0061] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0062] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0063] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0064] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A fire monitoring method for monitoring the fire conditions of each fire Internet of Things unit and the operating conditions of fire fighting equipment, characterized in that: include; Collect smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit, and monitor the fire situation in the environment according to the smoke static data and the smoke dynamic data; Constructing a low-power wide-area gateway with a star topology structure, wherein the low-power wide-area gateway is respectively connected to sensors in different firefighting equipment for communication; Based on the low-power wide-area gateway, daily operation data of different fire-fighting equipment is obtained, duplicate bytes in the operation data are removed, and the operation data after the duplicate bytes are removed is formatted to unify the transmission protocol of the operation data of different fire-fighting equipment; The format-converted operation data is transmitted to the monitoring center for parsing, the parsed data is encapsulated and input into the adapter for event stream conversion to obtain a plurality of first events, and the plurality of first events are abstracted and monitored to obtain a second event; Based on the second event, the operating data corresponding to different fire-fighting equipment and the fire conditions are obtained, and the operating status of the fire-fighting equipment in the fire-fighting Internet of Things unit is monitored according to the operating data corresponding to the fire conditions.

2. The fire monitoring method according to claim 1, characterized in that: The steps of collecting smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit and monitoring the fire situation in the environment according to the smoke static data and the smoke dynamic data include: Obtaining environmental video images of the firefighting IoT unit within a preset time, extracting activity areas in the environmental video images, and preprocessing the extracted activity areas to screen out a number of suspected smoke areas in the activity areas; Performing smoke feature analysis on the plurality of suspected smoke areas in a time series space, wherein the smoke feature analysis includes at least motion feature analysis, concentration feature analysis, and image change consistency feature analysis; The fire condition in the fire protection Internet of Things unit environment is judged based on the results of the smoke characteristic analysis.

3. The fire monitoring method according to claim 2, characterized in that: The step of performing smoke feature analysis on the plurality of suspected smoke areas in the time series space comprises: Obtaining the total number of image frames of the suspected smoke areas within a preset time; Divide the motion direction according to the spatial range to obtain a motion direction model, record the motion direction of each frame image corresponding to the suspected smoke area in the motion direction model, and make a first judgment according to the motion direction of the image to complete the motion feature analysis of the smoke; Constructing a smoke concentration equation of the image, solving the smoke concentration equation to obtain a dimming coefficient of a pixel point in each frame of the image, and performing a second judgment based on the dimming coefficient in each frame of the image to complete the smoke concentration feature analysis; The grayscale difference between the two frames of image is obtained and used as the grayscale change of the image. The consistency ratio of the image is calculated based on the grayscale change. A third judgment is performed based on the consistency ratio to complete the consistency analysis of the smoke image change.

4. The fire monitoring method according to claim 3, characterized in that: The expression of the smoke concentration equation is: In the formula, is the grayscale of the current image block, is the grayscale of the background corresponding to the current image block, A is the value of air light, is the smoke penetration rate; In the formula, is the attenuation coefficient, is the thickness of the smoke.

5. The fire monitoring method according to claim 1, characterized in that: The steps of removing duplicate bytes from the operation data and converting the format of the operation data after removing the duplicate bytes to unify the transmission protocol of the operation data of different fire fighting equipment include: Adding redundant codes to the received operating data, performing frequency band sequence expansion on the operating data with the redundant codes added, and performing linear modulation on the operating data after the frequency band sequence expansion, so that the operating data corresponding to different sensors are transmitted using the same frequency; Sending the linearly modulated operation data to a network server based on the UDP / IP protocol, performing address matching based on the terminal node address and the execution address, decrypting the operation data with successful address matching, and removing duplicate bytes in the operation data according to the redundant code; Based on the MQTT protocol, the operation data with duplicate bytes removed is published to the application server. Based on the data parsing service in the application server, the transmission mode of the operation data is standardized to form a unified transmission protocol.

6. The fire monitoring method according to claim 5, characterized in that: The step of sending the linear modulated operation data to the network server based on the UDP / IP protocol includes: Sending the linearly modulated operation data to the main thread of the network server based on the UDP / IP message protocol, and connecting the received operation data with the slot function in the main thread of the network server; After the slot function is connected with the running data, a corresponding sub-thread is created, in which data splitting processing is performed according to the subject classification of the running data, and the main thread receives the next round of running data at the same time; The data processed by the child threads are stored in a preset table in the form of strings, the data processed by each child thread is encapsulated into a class, and the shared data received by two adjacent child threads are locked and unlocked based on the mutex array.

7. The fire monitoring method according to claim 1, characterized in that: The steps of transmitting the format-converted operation data to the monitoring center for parsing, encapsulating the parsed data and inputting it into the adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events to obtain a second event include: The format-converted operation data is transmitted to the monitoring center for parsing, the disordered noise data in the operation data is obtained and removed, and the operation data after the disordered noise data is removed is semantically converted; The semantically transformed operation data is encapsulated and inserted into a first event sequence, and an event definition is performed on the operation data inserted into the first event sequence based on an event definition module to obtain a first event; Using the first event as an input stream of a second event engine, merging, filtering and statistically analyzing the first event input to the second event engine to complete abstract processing of the first event; Based on the predefined monitoring rules, the first event after abstract processing is queried, filtered and aggregated to complete the monitoring process of the first event and to mine the second event reflecting the operating status of the fire-fighting equipment in the first event.

8. A fire monitoring system for monitoring the fire conditions of each fire IoT unit and the operating conditions of fire fighting equipment, characterized in that: include: A collection module, used to collect smoke static data and smoke dynamic data in the environment of the fire protection Internet of Things unit, and monitor the fire situation in the environment according to the smoke static data and the smoke dynamic data; A building module, used to build a low-power wide-area gateway with a star topology, wherein the low-power wide-area gateway is respectively connected to the sensors in different fire-fighting equipment for communication; A conversion module, used to obtain daily operation data of different fire-fighting equipment based on the low-power wide-area gateway, remove duplicate bytes in the operation data, and convert the format of the operation data after removing the duplicate bytes to unify the transmission protocol of the operation data of different fire-fighting equipment; A parsing module, used for transmitting the format-converted operation data to a monitoring center for parsing, encapsulating the parsed data and inputting the data into an adapter for event stream conversion to obtain a plurality of first events, abstracting and monitoring the plurality of first events to obtain a second event; A monitoring module is used to obtain operating data corresponding to different fire-fighting equipment and fire conditions based on the second event, and monitor the operating conditions of the fire-fighting equipment in the fire-fighting Internet of Things unit according to the operating data corresponding to the fire conditions.

Images