CN114998822A - Fire detection method, device, equipment and storage medium - Google Patents
Fire detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114998822A CN114998822A CN202210452499.4A CN202210452499A CN114998822A CN 114998822 A CN114998822 A CN 114998822A CN 202210452499 A CN202210452499 A CN 202210452499A CN 114998822 A CN114998822 A CN 114998822A
- Authority
- CN
- China
- Prior art keywords
- fire
- marking
- target
- frame image
- determining
- 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.)
- Withdrawn
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 20
- 239000000779 smoke Substances 0.000 claims description 40
- 238000002372 labelling Methods 0.000 claims description 36
- 238000004891 communication Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 206010000369 Accident Diseases 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G08B5/00—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied
- G08B5/22—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied using electric transmission; using electromagnetic transmission
- G08B5/36—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied using electric transmission; using electromagnetic transmission using visible light sources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Electromagnetism (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention relates to the technical field of warehouse security, in particular to a fire detection method, a fire detection device, fire detection equipment and a storage medium, and discloses a method for acquiring a target frame image acquired by a target camera; carrying out fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result; according to the invention, the fire recognition is carried out on the image acquired by the camera through the preset fire recognition model, so that the fire detection result can be obtained, and the technical problems of high cost and low efficiency of fire detection are solved.
Description
Technical Field
The invention relates to the technical field of warehouse security, in particular to a fire detection method, a fire detection device, fire detection equipment and a storage medium.
Background
In recent years, the news that a fire causes a great deal of casualties and losses is endless, and a great deal of losses and resource waste are caused, for example: in the warehouse for accumulating materials, a fire disaster can cause a large amount of loss of the accumulated materials in the warehouse, and people can not find the fire condition in time just when the fire disaster happens, so that the fire condition is spread to cause serious consequences.
In the prior art, the fire is generally detected by an infrared camera or a smoke alarm, but the infrared camera has higher cost and low sensitivity, the smoke alarm has simpler triggering rule, is easy to give false alarm, and has lower prediction efficiency on the fire.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a fire detection method, a fire detection device, fire detection equipment and a fire detection storage medium, and aims to solve the technical problems of high cost and low efficiency of fire detection in the prior art.
To achieve the above object, the present invention provides a fire detection method, comprising the steps of:
acquiring a target frame image acquired by a target camera;
carrying out fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result;
and sending the fire recognition result to a client for displaying.
Optionally, the performing fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result includes:
performing fire annotation on the target frame image through a preset fire annotation model to obtain a fire annotation result;
and determining fire marking frame information according to the fire marking result, and determining a fire identification result according to the fire marking frame information.
Optionally, the determining the fire labeling box information according to the fire labeling result, and determining the fire recognition result according to the fire labeling box information includes:
extracting the information of the marking frame in the fire marking result, and determining the fire state according to the information of the marking frame;
acquiring the area of a fire marking frame, and determining the fire passing area according to the area of the fire marking frame;
and recording the fire state and the fire passing area as a fire recognition result.
Optionally, the extracting the information of the label box in the fire label result, and determining the fire state according to the information of the label box includes:
extracting smoke marking frame information and naked flame marking frame information in the fire marking result;
respectively extracting the number of smoke marking frames in the smoke marking frame information and the number of open fire marking frames in the open fire marking frame information;
and determining the fire condition state based on the number of the smoke marking frames and the number of the open fire marking frames.
Optionally, the obtaining of the area of the fire marking box and the determining of the fire passing area according to the area of the fire marking box include:
obtaining the scaling of the target camera;
determining the central position of the target frame image, and establishing a coordinate system based on the central position;
determining the coordinate parameter of the fire marking frame according to the coordinate system, and determining the area of the fire marking frame according to the coordinate parameter of the fire marking frame;
and determining the fire passing area based on the area of the fire marking box and the scaling.
Optionally, after the sending the fire recognition result to the client for displaying, the method further includes:
if the fire exists, establishing a target fire file;
acquiring acquisition time corresponding to the target frame image, and correspondingly storing the target frame image and the acquisition time to a target fire situation file;
and when a file calling instruction is received, sending the target fire file to a client for display.
Optionally, the acquiring time corresponding to the target frame image, and storing the target frame image and the acquiring time in correspondence to a target fire profile, further includes:
after the preset time interval, acquiring a frame image of the target camera, and carrying out fire detection on the frame image;
when the detection result is that no fire exists, the current time is obtained;
determining the duration of the fire according to the current time and the acquisition time;
and updating the target fire profile according to the fire duration and the frame image.
In addition, to achieve the above object, the present invention also provides a fire detection apparatus including:
the image acquisition module is used for acquiring a target frame image acquired by a target camera;
the fire recognition module is used for carrying out fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result;
and the result display module is used for sending the fire recognition result to the client for display.
Further, to achieve the above object, the present invention also proposes a fire detection apparatus including: a memory, a processor and a fire detection program stored on the memory and executable on the processor, the fire detection program being configured to implement the steps of the fire detection method as described above.
Furthermore, to achieve the above object, the present invention also proposes a storage medium having stored thereon a fire detection program which, when executed by a processor, implements the steps of the fire detection method as described above.
The invention discloses a method for acquiring a target frame image acquired by a target camera; carrying out fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result; compared with the prior art that whether the fire exists or not is detected through an infrared camera or a smoke alarm, the fire detection method and the fire detection system can obtain the fire detection result by carrying out fire recognition on the image acquired by the camera through a preset fire recognition model, and solve the technical problems of high cost and low efficiency of fire detection.
Drawings
FIG. 1 is a schematic diagram of a fire detection system for a hardware environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of the fire detection method of the present invention;
FIG. 3 is a schematic flow chart of a fire detection method according to a second embodiment of the present invention;
FIG. 4 is a schematic flow chart of a fire detection method according to a third embodiment of the present invention;
fig. 5 is a block diagram showing the construction of a first embodiment of the fire detecting device of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a fire detection device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the fire detection apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
It will be appreciated by those skilled in the art that the configuration shown in fig. 1 does not constitute a limitation of the fire detection apparatus and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a fire detection program.
In the fire detection apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the fire detection apparatus of the present invention may be provided in the fire detection apparatus which calls the fire detection program stored in the memory 1005 through the processor 1001 and performs the fire detection method provided by the embodiment of the present invention.
An embodiment of the present invention provides a fire detection method, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a fire detection method according to the present invention.
In this embodiment, the fire detection method includes the steps of:
step S10: and acquiring a target frame image acquired by a target camera.
It should be noted that the main executing body of the method of the embodiment may be a fire detection device, wherein the fire detection device may be a device having data processing and data transmission, for example: the present embodiment is not limited to this, and in the present embodiment and the following embodiments, a control computer will be taken as an example for description.
It should be noted that the target camera is used for collecting fire video data, wherein the target camera may be kept networked so that the collected fire video data may be transmitted in a network communication manner, and may also be in other communication manners, for example: bluetooth, etc., which the present embodiment does not specifically limit.
It can be understood that, since the video data is collected by the camera, when the subsequent fire detection is performed, the frame image in the video data needs to be collected, so that the fire recognition model can perform the fire detection on the frame image, and therefore, the frame image in the video data can be split to obtain the target frame image.
Further, in order to acquire the target frame image, the step S10 includes:
acquiring video data acquired by a target camera;
and converting the frame image of the video data by a preset frame image conversion tool to obtain a target frame image.
It should be understood that the preset frame image conversion tool may be a Python library that converts a video stream into frame images, or may be other frame image conversion tools having the same or similar functions, which is not limited in this embodiment.
In the concrete implementation, a warehouse fire is taken as an example for explanation, after a camera in the warehouse collects a video, the video stream is transmitted to a control computer, so that a frame image conversion tool in the control computer generates a frame image according to the video stream, wherein because the warehouse is often not too large, or a plurality of cameras coexist simultaneously, and the area monitored by each camera is limited, a camera with a particularly high resolution does not need to be emphasized, and if a plurality of cameras exist simultaneously, a plurality of corresponding video streams can be simultaneously subjected to frame image conversion in a multi-thread manner.
Step S20: and carrying out fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result.
It should be noted that the preset fire recognition model is used for performing fire recognition on the target frame image to determine whether a fire exists in the target frame image, where the preset fire recognition model may be a target detection algorithm trained by a user in advance, for example: fast RCNN or YOLO series algorithms, etc., which are not limited in this embodiment.
It is easy to understand that target detection needs to select or construct a target detection network model in advance, select a related data set for training the network model, generate a corresponding model file, and then predict by using the model file.
Further, in order to obtain a preset fire recognition model, before the step S20, the method further includes:
acquiring a frame image sample and a fire recognition result sample;
and carrying out model training on the frame image sample and the fire recognition result sample through an initial neural network model to obtain a preset fire recognition model.
In a specific implementation, the fire recognition result may include: the condition of a fire state and the area of crossing a fire, wherein the condition of a fire state can be the condition of a fire size that detects out, divide into the condition of a fire state according to the condition of a fire size: the areas of fire passing can be detected and areas of fire occurring in the absence of fire, smoke, small fire, large fire, etc.
Step S30: and sending the fire recognition result to a client for displaying.
It should be noted that the client may be a mobile phone, a computer, a display screen, or other client devices, taking the warehouse as an example, and when detecting a fire in a frame image collected by a camera in the warehouse, the client may send a fire detection result to the display screen of the monitoring room to remind the user of the fire in the warehouse.
The embodiment discloses obtaining a target frame image collected by a target camera; carrying out fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result; it will to send the condition of a fire recognition result to the customer end and show, this embodiment carries out the condition of a fire discernment through the image with the camera collection through predetermineeing the condition of a fire recognition model, and wherein, predetermine the condition of a fire recognition model and can be trained network model for whether there is the condition of a fire in the image of judgement collection, thereby obtain the condition of a fire testing result, solved to with the condition of a fire detection cost higher and the lower technical problem of efficiency.
Referring to fig. 3, fig. 3 is a schematic flow chart of a fire detection method according to a second embodiment of the present invention.
Based on the first embodiment, in this embodiment, the step S20 includes:
step S201: and carrying out fire annotation on the target frame image through a preset fire annotation model to obtain a fire annotation result.
It should be noted that the preset fire labeling model is used for performing a standard on a part containing smoke or open fire in the target frame image to obtain a fire labeling result, wherein for a real object containing smoke or open fire in the target frame image, a frame selection mode is used for labeling to obtain a fire labeling frame.
Step S202: and determining fire marking frame information according to the fire marking result, and determining a fire identification result according to the fire marking frame information.
It should be understood that the fire label box information includes: the number of the fire marking frames and the area of the fire marking frames are divided into the number of smoke marking frames and the number of open fire marking frames; the area of the fire marking box is divided into the area of the smoke marking box and the area of the open fire marking box.
Further, in order to determine the fire state and the fire area, the fire labeling box may be divided into a smoke labeling box and an open fire labeling box during labeling, and the step S202 includes:
extracting the information of the marking frame in the fire marking result, and determining the fire state according to the information of the marking frame;
acquiring the area of a fire marking frame, and determining the fire passing area according to the area of the fire marking frame;
and recording the fire state and the fire passing area as a fire recognition result.
It is easy to understand that in case of fire, open fire and smoke may occur, and the proportion of open fire to smoke may generally represent the fire status, wherein the fire status is divided into: no fire, smoke, small fire, big fire, etc.
Further, in order to determine the fire condition state according to the smoke labeling box information and the open fire labeling box information, the method for extracting the labeling box information in the fire condition labeling result and determining the fire condition state according to the labeling box information includes:
extracting smoke marking frame information and open fire marking frame information in the fire marking result;
respectively extracting the number of smoke marking frames in the smoke marking frame information and the number of open fire marking frames in the open fire marking frame information;
and determining the fire condition state based on the number of the smoke marking frames and the number of the open fire marking frames.
It is worth to be noted that if the fire detection result corresponding to the target frame image is that no smoke mark frame or open fire mark frame exists, the current fire state is that no fire is on; if the fire detection result corresponding to the target frame image is that the smoke marking frame exists but the open fire marking frame does not exist, the current fire state is smoke; if the fire detection result corresponding to the target frame image indicates that the smoke mark frames and the open fire mark frames exist and the number of the smoke mark frames is greater than that of the open fire mark frames, the current fire state is a small fire, and if the fire detection result corresponding to the target frame image indicates that the smoke mark frames and the open fire mark frames exist and the number of the smoke mark frames is less than that of the open fire mark frames or only the open fire mark frames exist and the number of the open fire mark frames is greater than a preset threshold, the current fire state is a small fire, wherein the preset threshold can be 5, which is not specifically limited in this embodiment.
The fire detection result further includes a fire area, that is, the swept area of the current fire, and in order to obtain the fire area, the fire area may be estimated by the area of the label box in the target frame image.
Further, in order to obtain the fire area, the area of the fire marking box is obtained, and the fire area is determined according to the area of the fire marking box, including:
obtaining the scaling of the target camera;
determining the central position of the target frame image, and establishing a coordinate system based on the central position;
determining the coordinate parameter of the fire marking frame according to the coordinate system, and determining the area of the fire marking frame according to the coordinate parameter of the fire standard frame;
and determining the fire passing area based on the area of the fire marking box and the scaling.
It should be noted that the scaling of the target camera refers to a distance scale of the camera when the target camera shoots, and the actual fire passing area can be calculated through the area of the mark frame and the distance scale.
In a specific implementation, a coordinate system is established by taking the central position of the target frame image as an origin, that is, each vertex coordinate of the smoke labeling frame and the naked flame labeling frame can be obtained in the coordinate system, and the area of the labeling frame can be calculated according to the vertex coordinates, for example: the coordinates of the upper left corner and the coordinates of the lower right corner of the marking frame are (x1, y1) and (x2, y2) respectively, the area of the marking frame is | (x2-x1) | (y2-y1) |, and the actual fire passing area can be obtained by combining a distance scale of the head of the water system, and the formula for obtaining the actual fire passing area is as follows:
S＝|(x2-x1)*(y2-y1)|*m
wherein S is the fire passing area, x1 and y1 are respectively the horizontal and vertical coordinates of the top left corner vertex of the labeling frame, x2 and y2 are respectively the horizontal and vertical coordinates of the bottom right corner vertex of the labeling frame, and m is the distance scale of the camera, namely the zoom scale.
It is easy to understand that, when a coordinate system is established, the origin of coordinates may also be determined by a user, and the area of the labeling box may also be determined by the coordinates of the lower left corner of the labeling box and the coordinates of the upper right corner of the labeling box, which is not specifically limited in this embodiment.
The second embodiment discloses that the fire condition marking is carried out on the target frame image through a preset fire condition marking model to obtain a fire condition marking result; according to the fire labeling result, the information of the fire labeling frame is determined, and according to the information of the fire labeling frame, the fire identification result is determined.
Referring to fig. 4, fig. 4 is a schematic flow chart of a fire detection method according to a third embodiment of the present invention.
Based on the second embodiment, in this embodiment, after step S30, the method further includes:
step S40: if the fire exists, a target fire file is established.
It should be noted that the target fire profile refers to a set created by correspondingly storing the image data, the duration of the fire, the fire record and the like acquired from the fire, and is used for determining the cause of the fire and tracing the need according to the fire profile.
Step S50: acquiring the acquisition time corresponding to the target frame image, and correspondingly storing the target frame image and the acquisition time to a target fire situation archive.
It should be understood that the acquisition time refers to the time corresponding to the target frame image, and since the camera acquires video data, the acquisition time corresponding to each frame image can be reserved in the process of frame image conversion.
Further, in order to determine the duration of the fire, after the step S50, the method further includes:
after the preset time interval, acquiring a frame image of the target camera, and carrying out fire detection on the frame image;
when the detection result is that no fire exists, acquiring the current time;
determining the duration of the fire condition according to the current time and the acquisition time;
and updating the target fire profile according to the fire duration and the frame image.
In specific implementation, when a first image frame with smoke or fire appears, the target image frame is stored, the image frame is stored again at preset time intervals, and the operation is continuously carried out for multiple times until the fire is over, so that each moment in the fire period is stored, and the fire accident analysis is carried out subsequently.
It will be appreciated that the preset time may be set and modified by the user, for example: 10s, this embodiment is not particularly limited thereto.
It should be noted that the duration of the fire refers to the difference between the acquisition time corresponding to the frame image in which the fire is detected for the first time and the current time in which the fire is detected for the last time, and when the first image frame with smoke or fire appears, the time t1 is recorded, when a plurality of consecutive images do not have smoke or fire, the fire is considered to be extinguished, the fire is over, the time t2 is recorded, and the duration of the fire t is t2-t1, for example: the acquisition time corresponding to the target frame image of the first detected fire is 12 o 'clock, the current time of the last detected fire is 13 o' clock, and the duration of the fire is 1 h.
Step S60: and when a file calling instruction is received, sending the target fire file to a client for display.
It should be noted that the file retrieving instruction refers to an operation instruction input by a user, and is used for checking image data acquired by fire so as to analyze a fire accident.
In specific implementation, the stored fire image data and the data such as the duration of the fire, the fire state, the fire passing area and the like are sent to a display screen according to a file calling instruction input by a user, so that the user can analyze the cause of the fire accident according to the data.
The third embodiment discloses that if a fire exists, a target fire file is established; acquiring acquisition time corresponding to the target frame image, and correspondingly storing the target frame image and the acquisition time to a target fire situation file; when receiving archives and transferring the instruction, will target fire situation archives send to the customer end and show, and this embodiment is through whether there is the fire situation in the detection image, and then calculates the fire situation duration to the image correspondence storage that will have the fire situation, the convenient follow-up fire incident reason analysis that carries on has improved the rate of accuracy that the user traced to the source and has saved the time of tracing to the source.
Furthermore, an embodiment of the present invention further provides a storage medium, on which a fire detection program is stored, and the fire detection program, when executed by a processor, implements the steps of the fire detection method as described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
Referring to fig. 5, fig. 5 is a block diagram illustrating a first embodiment of a fire detection apparatus according to the present invention.
As shown in fig. 5, a fire detection apparatus according to an embodiment of the present invention includes:
and the image acquisition module 10 is configured to acquire a target frame image acquired by a target camera.
And the fire recognition module 20 is configured to perform fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result.
And the result display module 30 is used for sending the fire recognition result to the client for display.
The embodiment discloses obtaining a target frame image collected by a target camera; carrying out fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result; it will to send the condition of a fire recognition result to the customer end and show, this embodiment carries out the condition of a fire discernment through the image with the camera collection through predetermineeing the condition of a fire recognition model, and wherein, predetermine the condition of a fire recognition model and can be trained network model for whether there is the condition of a fire in the image of judgement collection, thereby obtain the condition of a fire testing result, solved to with the condition of a fire detection cost higher and the lower technical problem of efficiency.
In an embodiment, the fire identification module 20 is further configured to label the fire of the target frame image through a preset fire labeling model to obtain a fire labeling result; and determining fire marking frame information according to the fire marking result, and determining a fire identification result according to the fire marking frame information.
In an embodiment, the fire recognition module 20 is further configured to extract the labeling box information in the fire labeling result, and determine the fire state according to the labeling box information; acquiring the area of a fire marking frame, and determining the fire passing area according to the area of the fire marking frame; and recording the fire state and the fire passing area as a fire recognition result.
In an embodiment, the fire identification module 20 is further configured to extract smoke labeling box information and open fire labeling box information in the fire labeling result; respectively extracting the number of smoke marking frames in the smoke marking frame information and the number of open fire marking frames in the open fire marking frame information; and determining the fire condition state based on the number of the smoke marking frames and the number of the open fire marking frames.
In an embodiment, the fire recognition module 20 is further configured to obtain a scaling of the target camera; determining the central position of the target frame image, and establishing a coordinate system based on the central position; determining the coordinate parameter of the fire marking frame according to the coordinate system, and determining the area of the fire marking frame according to the coordinate parameter of the fire marking frame; and determining the fire passing area based on the area of the fire marking box and the scaling ratio.
In an embodiment, the result displaying module 30 is further configured to establish a target fire profile if a fire exists; acquiring acquisition time corresponding to the target frame image, and correspondingly storing the target frame image and the acquisition time to a target fire situation file; and when a file calling instruction is received, sending the target fire file to a client for display.
In an embodiment, the result display module 30 is further configured to obtain frame images of the target camera at preset time intervals, and perform fire detection on the frame images; when the detection result is that no fire exists, acquiring the current time; determining the duration of the fire according to the current time and the acquisition time; and updating the target fire profile according to the fire duration and the frame image.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment can be referred to the fire detection method provided by any embodiment of the present invention, and are not described herein again.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or a part contributing to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A fire detection method, characterized by comprising:
acquiring a target frame image acquired by a target camera;
performing fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result;
and sending the fire condition recognition result to a client for displaying.
2. The fire detection method according to claim 1, wherein the performing fire recognition on the target frame image through a preset fire recognition model to obtain a fire recognition result comprises:
performing fire annotation on the target frame image through a preset fire annotation model to obtain a fire annotation result;
and determining fire marking frame information according to the fire marking result, and determining a fire identification result according to the fire marking frame information.
3. The fire detection method according to claim 2, wherein the determining of the fire tagging box information according to the fire tagging result and the determining of the fire recognition result according to the fire tagging box information comprise:
extracting the information of the marking frame in the fire marking result, and determining the fire state according to the information of the marking frame;
acquiring the area of a fire marking frame, and determining the fire passing area according to the area of the fire marking frame;
and recording the fire state and the fire passing area as a fire recognition result.
4. The fire detection method according to claim 3, wherein the extracting of the label box information in the fire labeling result and the determining of the fire status according to the label box information comprises:
extracting smoke marking frame information and open fire marking frame information in the fire marking result;
respectively extracting the number of smoke marking frames in the smoke marking frame information and the number of open fire marking frames in the open fire marking frame information;
and determining the fire condition state based on the number of the smoke marking frames and the number of the open fire marking frames.
5. The fire detection method of claim 3, wherein the obtaining of the area of the fire label box and the determining of the fire passing area based on the area of the fire label box comprises:
obtaining the scaling of the target camera;
determining the central position of the target frame image, and establishing a coordinate system based on the central position;
determining the coordinate parameter of the fire marking frame according to the coordinate system, and determining the area of the fire marking frame according to the coordinate parameter of the fire marking frame;
and determining the fire passing area based on the area of the fire marking box and the scaling.
6. The fire detection method according to any one of claims 1 to 5, wherein after sending the fire recognition result to a client for display, the method further comprises:
if the fire exists, establishing a target fire condition file;
acquiring acquisition time corresponding to the target frame image, and correspondingly storing the target frame image and the acquisition time to a target fire situation file;
and when a file calling instruction is received, sending the target fire file to a client for display.
7. The fire detection method according to claim 6, wherein after acquiring the acquisition time corresponding to the target frame image and storing the target frame image and the acquisition time corresponding to the target fire profile, the method further comprises:
after the preset time interval, acquiring a frame image of the target camera, and carrying out fire detection on the frame image;
when the detection result is that no fire exists, acquiring the current time;
determining the duration of the fire according to the current time and the acquisition time;
and updating the target fire profile according to the fire duration and the frame image.
8. A fire detection device, characterized in that the fire detection device comprises:
the image acquisition module is used for acquiring a target frame image acquired by a target camera;
the fire recognition module is used for recognizing the fire of the target frame image through a preset fire recognition model to obtain a fire recognition result;
and the result display module is used for sending the fire recognition result to the client for display.
9. A fire detection apparatus, characterized in that the fire detection apparatus comprises: a memory, a processor, and a fire detection program stored on the memory and executable on the processor, the fire detection program configured to implement the fire detection method of any one of claims 1 to 7.
10. A storage medium having stored thereon a fire detection program which, when executed by a processor, implements a fire detection method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210452499.4A CN114998822A (en) | 2022-04-27 | 2022-04-27 | Fire detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210452499.4A CN114998822A (en) | 2022-04-27 | 2022-04-27 | Fire detection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114998822A true CN114998822A (en) | 2022-09-02 |
Family
ID=83026211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210452499.4A Withdrawn CN114998822A (en) | 2022-04-27 | 2022-04-27 | Fire detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114998822A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115690695A (en) * | 2022-12-29 | 2023-02-03 | 杭州浩联智能科技有限公司 | Construction site fire auxiliary disposal method, system and storage medium |
-
2022
- 2022-04-27 CN CN202210452499.4A patent/CN114998822A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115690695A (en) * | 2022-12-29 | 2023-02-03 | 杭州浩联智能科技有限公司 | Construction site fire auxiliary disposal method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10812761B2 (en) | Complex hardware-based system for video surveillance tracking | |
| CN105302701B (en) | Method, device and equipment for testing reaction time of terminal user interface | |
| JP5751321B2 (en) | Information processing apparatus and information processing program | |
| CN112508109B (en) | Training method and device for image recognition model | |
| CN113096158A (en) | Moving object identification method and device, electronic equipment and readable storage medium | |
| CN114998822A (en) | Fire detection method, device, equipment and storage medium | |
| CN111881320A (en) | Video query method, device, equipment and readable storage medium | |
| CN112419639A (en) | Video information acquisition method and device | |
| CN110505438B (en) | Queuing data acquisition method and camera | |
| US9607210B2 (en) | Video surveillance system and method for fraud detection | |
| JP2009239507A (en) | Monitoring system | |
| CN112528825A (en) | Station passenger recruitment service method based on image recognition | |
| CN114463779A (en) | Smoking identification method, device, equipment and storage medium | |
| CN115190277B (en) | Safety monitoring method, device and equipment for construction area and storage medium | |
| JP6399096B2 (en) | Information processing apparatus, display method, and computer program | |
| CN112419638B (en) | Method and device for acquiring alarm video | |
| WO2022044637A1 (en) | Image processing device, image processing method, and program | |
| CN115424405A (en) | Smoke and fire monitoring and alarming method, device, equipment and storage medium | |
| CN109284730B (en) | Method and device applied to screening data and monitoring system | |
| KR20210096754A (en) | Safety management method and system using image learning model for digital Safety, Health, Environment industry specialization | |
| WO2024105767A1 (en) | Information processing program, information processing method, and information processing device | |
| CN114724080B (en) | Building site intelligent safety identification method and device based on security video monitoring | |
| CN115294649B (en) | Method, apparatus, storage medium and processor for identifying behavior using mobile device | |
| WO2024105766A1 (en) | Information processing program, information processing method, and information processing device | |
| CN112949619B (en) | Guest room sanitation monitoring method, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220902 |
|
| WW01 | Invention patent application withdrawn after publication |