Fireworks warning method, device, electronic equipment and system

Abstract

The present application discloses a method, device, electronic device and system for early warning of fireworks, which relates to the field of image processing technology and is at least used to improve the problem that it is difficult to accurately and effectively detect and early warning fires for ancient buildings, etc. The method comprises: in the case that there is a fireworks area in the target detection area, obtaining the target features of the fireworks area; the target features include the distribution state of the flame feature points in the fireworks area, and / or the target object detection information; the target object detection information is used to indicate whether there is a target object in the fireworks area and the posture of the target object when the target object exists; the target object is used to place burning objects; when the target features meet the preset early warning conditions, outputting early warning information corresponding to the fireworks area.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a fireworks warning method, device, electronic equipment and system. Background Art

[0002] As an important part of cultural heritage, ancient buildings have rich material and spiritual values. However, ancient buildings are built a long time ago and have weak fire resistance, so accurate and effective fire detection and early warning are needed.

[0003] In the related art, whether to issue a fire warning is generally determined based on the distance between the identified fireworks and unique objects such as candles in ancient buildings. That is, when the distance between the fireworks and unique objects is small, no fire warning is issued, and when the distance between the fireworks and unique objects is large, a fire warning is issued. This method is prone to false alarms or missed alarms, and it is difficult to accurately and effectively detect and warn fires in ancient buildings. Summary of the invention

[0004] The embodiments of the present application provide a fire and smoke warning method, device, electronic equipment and system for improving the problem of difficulty in accurately and effectively performing fire detection and warning on ancient buildings.

[0005] To achieve the above objectives, the present application provides the following technical solutions:

[0006] In a first aspect, a method for early warning of fireworks is provided, comprising: obtaining target features of the fireworks area when there is a fireworks area in a target detection area. The target features include the distribution state of flame feature points in the fireworks area, and / or target object detection information. The target object detection information is used to indicate whether there is a target object in the fireworks area and the posture of the target object when the target object exists. The target object is used to place a burning object. When the target feature meets a preset early warning condition, early warning information corresponding to the fireworks area is output.

[0007] In the technical solution of the present application, considering that a normal fire point may be set in the target detection area, the electronic device can obtain the target features of the fireworks area when there is a fireworks area in the target detection area. The target features can reflect the distribution state of the flame feature points in the fireworks area, and / or whether there is a target object in the fireworks area and the posture of the target object when there is a target object. In this way, the electronic device can perform fine-grained recognition based on the target features of the fireworks area. Furthermore, the electronic device can output warning information corresponding to the fireworks area when accurately identifying that the target features meet the preset warning conditions, thereby improving the accuracy of warning for the fireworks area.

[0008] Compared with making early warning decisions based on the distance between the identified fireworks and fire points and the unique objects, it is easy to cause missed alarms when the distance between the identified fireworks and fire points and the unique objects is close but the fireworks and fire points are not normal fire points, and to cause false alarms when the distance between the identified fireworks and fire points and the unique objects is far but the fireworks and fire points are normal fire points. The present application can accurately identify based on the fine-grained features of the fireworks and fire areas, avoid false alarms for normal fire points that are far away from the unique objects, and avoid missed alarms for abnormal fire points that are close to the unique objects, thereby realizing accurate and effective fire detection and early warning for ancient buildings.

[0009] In a possible embodiment, the distribution state of the flame feature points in the fireworks area includes a dispersed state or a clustered state. The posture of the target object includes standing upright or falling down.

[0010] In a possible embodiment, when the target feature meets the preset warning condition, the method of outputting the warning information corresponding to the fireworks area specifically includes: if the distribution state is a clustered state, outputting the warning information. If the target object detection information indicates that there is no target object in the fireworks area, or the posture of the target object is tilted, outputting the warning information.

[0011] In a possible embodiment, when the target feature meets the preset warning conditions, the method of outputting warning information corresponding to the fireworks area specifically includes: if the distribution state is a dispersed state, and there is no target object in the fireworks area or the target object is in a tilted posture, then outputting warning information.

[0012] In a possible embodiment, the target feature also includes: human body recognition information corresponding to the fireworks area. The human body recognition information is used to indicate whether there is a target human body in the target detection area. The distance between the position of the target human body and the fireworks area is less than a preset distance. When the target feature meets the preset warning condition, the method of outputting the warning information corresponding to the fireworks area specifically includes: if the target object detection information is used to indicate that there is no target object in the fireworks area, and the human body recognition information indicates that there is no target human body, or the target object detection information is used to indicate that the posture of the target object is tilted, and the human body recognition information indicates that there is no target human body, then the warning information is output.

[0013] In a possible embodiment, the target feature also includes the area of ​​the fireworks area in the captured image corresponding to the target detection area. The method for obtaining the target feature of the fireworks area specifically includes: obtaining the area of ​​the fireworks area in the captured image. According to the area being greater than a preset area threshold, obtaining the distribution state of the flame feature points in the fireworks area. According to the area being less than or equal to the preset area threshold, obtaining the target object detection information.

[0014] In a possible embodiment, the target feature also includes a risk level of the detection area where the fireworks area is located. The risk level includes a first level or a second level. Fireworks with an area larger than a preset area threshold are not allowed to appear in the first level detection area. Fireworks with an area larger than a preset area threshold are allowed to appear in the second level detection area. When the target feature meets the preset warning condition, the method of outputting warning information corresponding to the fireworks area specifically includes: if the risk level of the detection area where the fireworks area is located is the first level, and the area of ​​the fireworks area is larger than the preset area threshold, then outputting warning information.

[0015] In a second aspect, a fire and smoke warning device is provided, comprising: an acquisition unit and an output unit.

[0016] The acquisition unit is used to acquire the target features of the fireworks area when there is a fireworks area in the target detection area. The target features include the distribution state of the flame feature points in the fireworks area and / or the target object detection information. The target object detection information is used to indicate whether there is a target object in the fireworks area and the posture of the target object when the target object exists. The target object is used to place the burning object.

[0017] The output unit is used to output warning information corresponding to the fireworks area when the target characteristics meet the preset warning conditions.

[0018] In a possible embodiment, the distribution state of the flame feature points in the fireworks area includes a dispersed state or a clustered state. The posture of the target object includes standing upright or falling down.

[0019] In a possible embodiment, the output unit is specifically configured to: output warning information if the distribution state is a gathering state; and output warning information if the target object detection information indicates that there is no target object in the fireworks area, or the target object is in a falling posture.

[0020] In a possible embodiment, the output unit is specifically configured to: output warning information if the distribution state is a dispersed state, and there is no target object in the fireworks area or the target object is in a tilted posture.

[0021] In a possible embodiment, the target feature further includes: human body recognition information corresponding to the fireworks area. The human body recognition information is used to indicate whether there is a target human body in the target detection area. The distance between the position of the target human body and the fireworks area is less than a preset distance. The output unit is specifically used to: if the target object detection information is used to indicate that there is no target object in the fireworks area, and the human body recognition information indicates that there is no target human body, or if the target object detection information is used to indicate that the posture of the target object is tilted, and the human body recognition information indicates that there is no target human body, then output a warning message.

[0022] In a possible embodiment, the target feature further includes the area of ​​the fireworks area in the captured image corresponding to the target detection area. The acquisition unit is specifically used to: acquire the area of ​​the fireworks area in the captured image. According to the area being greater than a preset area threshold, the distribution state of the flame feature points in the fireworks area is acquired. According to the area being less than or equal to the preset area threshold, the target object detection information is acquired.

[0023] In a possible embodiment, the target feature also includes a risk level of the detection area where the fireworks area is located. The risk level includes a first level or a second level. Fireworks with an area larger than a preset area threshold are not allowed to appear in the first level detection area. Fireworks with an area larger than a preset area threshold are allowed to appear in the second level detection area. The output unit is specifically used to: if the risk level of the detection area where the fireworks area is located is the first level, and the area of ​​the fireworks area is larger than the preset area threshold, then output warning information.

[0024] In a third aspect, an electronic device is provided, comprising: a processor and a memory. The processor is connected to the memory, the memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions stored in the memory, thereby implementing any one of the methods provided in the first aspect.

[0025] In a fourth aspect, a readable storage medium is provided, comprising computer execution instructions. When the computer execution instructions are executed on an electronic device, the electronic device executes any one of the methods provided in the first aspect.

[0026] In a fifth aspect, a computer program product is provided, comprising computer execution instructions, which, when executed on an electronic device, causes the electronic device to execute any one of the methods provided in the first aspect.

[0027] In a sixth aspect, a fire and smoke warning system is provided, comprising: an electronic device and a camera device. The electronic device is used to execute any one of the fire and smoke warning methods provided in the first aspect. The camera device is used to collect image information.

[0028] The technical effects brought about by any implementation method in the second to sixth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of a fire scene provided in an embodiment of the present application;

[0030] Figure 2 A schematic diagram of a scene of flammable items provided in an embodiment of the present application;

[0031] Figure 3 A schematic diagram of the structure of a fire and smoke warning system provided in an embodiment of the present application;

[0032] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0033] Figure 5 A flowchart of a fire and smoke warning method provided in an embodiment of the present application;

[0034] Figure 6 A schematic diagram of a fireworks area provided in an embodiment of the present application;

[0035] Figure 7 A schematic diagram of another fireworks area provided in an embodiment of the present application;

[0036] Figure 8 A flowchart of another fire and smoke warning method provided in an embodiment of the present application;

[0037] Fig. 9 A schematic diagram of another fireworks area provided in an embodiment of the present application;

[0038] Fig.10 A schematic structural diagram of a fire and smoke warning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0040] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0041] First, a brief introduction to the application scenarios involved in this application is given.

[0042] As an important part of cultural heritage, ancient buildings have rich material and spiritual values. However, ancient buildings are built a long time ago and have weak fire resistance, so fire accidents occur frequently. Moreover, with the rapid development of tourism, the frequency of fires in ancient buildings is also increasing. Therefore, it is necessary to accurately and effectively detect and warn fires in ancient buildings.

[0043] In the related art, generally, by reading the video stream in the ancient building scene, the foreground image area of ​​the video image frame in the video stream is obtained by the inter-frame difference method, and the foreground cumulative image is calculated and the foreground cumulative image is divided into multiple image blocks, so as to further perform fireworks recognition based on the image blocks. In addition, in the related art, it is determined whether to issue a fire warning based on the distance between the identified fireworks point and the candle lamp and other unique objects in the ancient building. That is, when the distance between the fireworks point and the unique object is small, no fire warning is issued, and when the distance between the fireworks point and the unique object is large, a fire warning is issued.

[0044] However, there are many real fire points in these ancient buildings. For example, oil lamps or candle lamps used for various purposes such as expressing respect, lighting guidance, praying and blessing. Figure 1 The following is a schematic diagram of a fire scene provided by an embodiment of the present application. Figure 1 In the style shown in (a) or (b), a large number of oil lamps or candle lamps are arranged in a group.

[0045] In addition, there are many flammable items in these ancient buildings. Figure 2 The figure shows a scene schematic diagram of a flammable article provided in an embodiment of the present application. Figure 2 (a) and (b) show different styles of cloth decorations.

[0046] In addition, ancient buildings use fire and electricity frequently, have many electrical lines, and are old and outdated, and use electricity in an irregular manner.

[0047] Therefore, the fire detection and warning methods based on the above-mentioned related technologies are prone to false alarms or missed alarms, making it difficult to accurately and effectively perform fire detection and warning for ancient buildings.

[0048] In order to solve the above problems, an embodiment of the present application provides a fireworks warning method. In the fireworks warning method, considering that a normal fire point may be set in the target detection area, the electronic device can obtain the target features of the fireworks area when there is a fireworks area in the target detection area. The target features can reflect the distribution state of the flame feature points in the fireworks area, and / or whether there is a target object in the fireworks area and the posture of the target object when there is a target object. In this way, the electronic device can perform fine-grained recognition based on the target features of the fireworks area. Furthermore, the electronic device can output warning information corresponding to the fireworks area when accurately identifying that the target features meet the preset warning conditions, thereby improving the accuracy of warning the fireworks area.

[0049] Compared with making early warning decisions based on the distance between the identified fireworks and fire points and the unique objects, it is easy to cause missed alarms when the distance between the identified fireworks and fire points and the unique objects is close but the fireworks and fire points are not normal fire points, and to cause false alarms when the distance between the identified fireworks and fire points and the unique objects is far but the fireworks and fire points are normal fire points. The present application can accurately identify based on the fine-grained features of the fireworks and fire areas, avoid false alarms for normal fire points that are far away from the unique objects, and avoid missed alarms for abnormal fire points that are close to the unique objects, thereby realizing accurate and effective fire detection and early warning for ancient buildings.

[0050] Next, the implementation environment (implementation architecture) involved in this application is briefly introduced.

[0051] The above-mentioned fire and smoke warning method provided in the embodiment of the present application can be applied to electronic equipment in a fire and smoke warning system. Figure 3 , which is a schematic diagram of a fire and smoke warning system provided by an embodiment of the present application. The fire and smoke warning system may include an electronic device 101 and a camera device 102. The electronic device 101 may be connected to the camera device 102 via a wired network or a wireless network.

[0052] In practical applications, there may be multiple electronic devices 101 and multiple camera devices 102. For ease of understanding, the present embodiment of the application is described by taking the case where there is only one electronic device 101 and one camera device 102.

[0053] The electronic device 101 can be used to manage the camera device 102 and to provide fire and smoke warnings based on the image information captured by the camera device 102 .

[0054] Optionally, the electronic device 101 may be a terminal, a server, or other device used for fire and smoke warning. Figure 3 The figure only shows an example of a device form of the electronic device 101 and is not intended to limit the device form of the electronic device 101 .

[0055] The terminal may be an access terminal, a terminal unit, a user terminal (TE), a mobile device, a tablet computer (pad), a handheld device with wireless communication function, a computing device, or other processing device connected to a wireless modem. The present application embodiment does not limit this.

[0056] The server can be a single physical or logical server, or it can be a server cluster. A server cluster can realize various functions of the server by two or more physical or logical servers sharing different responsibilities and cooperating with each other. Optionally, a server cluster can also be referred to as a computing device cluster. In some implementations, the server cluster can also be a distributed cluster. This application does not limit the form of the electronic device 101.

[0057] The camera device 102 may be used to capture image information of the deployed detection area and send the captured image information to the electronic device 101 .

[0058] Optionally, the video camera 102 may be a camera, a ball camera or other types of video cameras. The camera has functions such as high-definition shooting and precise focusing. The ball camera may support free rotation and flexible zooming to achieve all-round real-time observation. Figure 3 The figure is merely an example of a device form of the camera device 102 , and is not intended to limit the device form of the camera device 102 .

[0059] In terms of hardware implementation, the above electronic devices can be implemented as follows: Figure 4 The hardware structure shown is implemented. Figure 4 FIG. 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device can be used to implement the functions of the above electronic device.

[0060] Figure 4 The electronic device shown may include: a processor 201 , a memory 202 , a communication interface 203 , and a bus 204 . The processor 201 , the memory 202 , and the communication interface 203 may be connected via the bus 204 .

[0061] The processor 201 is the control center of the electronic device, and may be a general-purpose central processing unit (CPU) or other general-purpose processors, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0062] As an example, the processor 201 may include one or more CPUs, such as Figure 4 CPU 0 and CPU 1 are shown in .

[0063] The memory 202 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0064] In a possible implementation, the memory 202 may exist independently of the processor 201. The memory 202 may be connected to the processor 201 via a bus 204 and used to store data, instructions, or program codes. When the processor 201 calls and executes the instructions or program codes stored in the memory 202, the fireworks warning method provided in the embodiment of the present application can be implemented.

[0065] In another possible implementation, the memory 202 may also be integrated with the processor 201 .

[0066] The communication interface 203 is used for connecting the electronic device to other robots or central dispatching equipment through a communication network, which may be Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc. The communication interface 203 may include a receiving unit for receiving data and a sending unit for sending data.

[0067] The bus 204 may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0068] It should be pointed out that Figure 4 The structure shown in the figure does not constitute a limitation on the electronic device, except Figure 4In addition to the components shown, the electronic device may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0069] For ease of understanding, the fire and smoke warning method provided by the present application is specifically introduced below with reference to the accompanying drawings.

[0070] like Figure 5 FIG. 1 is a flow chart of a method for early warning of fireworks provided in an embodiment of the present application. The method includes: S301-S302.

[0071] S301: When there is a fireworks area in the target detection area, obtain target features of the fireworks area.

[0072] The target detection area may be any area within the fire and smoke warning range, which may include indoor and outdoor areas of a building, to effectively cover the area where the building is located.

[0073] The fireworks area is an area where smoke and / or fire points exist. The target features of the fireworks area include the distribution state of the flame feature points in the fireworks area and / or the target object detection information.

[0074] The flame feature point in the fireworks area is the fire point burning in the fireworks area. When there are multiple fire points that are not in contact with each other in the fireworks area, it can be identified that there are multiple flame feature points.

[0075] The distribution state of the flame feature points in the fireworks area includes a dispersed state or a clustered state. Figure 6 Shown is a schematic diagram of a fireworks area provided in an embodiment of the present application. Figure 6 In the dashed box shown in (a), the distribution state of the flame feature points in the fireworks area can be identified as a dispersed state. Figure 6 In the dashed box shown in (b), the flame feature points in the fireworks area are large and irregular, and their distribution state can be identified as a clustered state.

[0076] The target object is used to place burning objects, i.e., combustible materials with normal fire points such as candles and oil lamps. The target object detection information is used to indicate whether there is a target object in the fireworks area, and the posture of the target object when there is a target object. The posture of the target object can include standing upright or falling down.

[0077] Furthermore, multiple detection areas can be set within the fire and smoke warning range, and a camera device can be set corresponding to each detection area. The electronic device can obtain the captured image or video data of each detection area in real time through the camera device to facilitate fire and smoke recognition and warning.

[0078] For example, a pre-trained fireworks point detection model based on a deep neural network may be configured in the electronic device. The fireworks point detection model is used to identify smoke and fire points in an image, and each smoke or fire point in the image can be marked by a bar-shaped recognition frame or the like. After the electronic device obtains a snapshot image of any detection area, it can efficiently identify and process the snapshot image through the fireworks point detection model. If smoke and fire points are not identified in the snapshot image, the electronic device can determine that any detection area is normal. If one or more smoke and / or fire points are identified in the snapshot image, the electronic device can determine that any detection area is a target detection area, and determine that each marked smoke area or fire point area is a fireworks area. That is, a fireworks area can be a smoke recognition frame in the snapshot image, or a fire point recognition frame in the snapshot image.

[0079] Furthermore, the electronic device may obtain the target features of the fireworks area when determining that there is a fireworks area in the target detection area. For example, the electronic device may identify the flame feature points in the fireworks area based on the captured image or video data, and further determine the distribution state of the flame feature points in the fireworks area based on the spatial relationship between different flame feature points. For another example, the electronic device may identify whether there is a target object in the fireworks area based on the captured image or video data. If there is a target object in the fireworks area, the electronic device may further determine the posture of the target object. Subsequently, the electronic device may accurately determine whether there is an abnormality in the fireworks area based on the target features of the fireworks area.

[0080] S302: When the target feature meets the preset warning condition, output warning information corresponding to the fireworks area.

[0081] Among them, the warning information is used to indicate that the fireworks area in the target detection area is of abnormal type. The abnormal type of fireworks area is an abnormal fireworks point that needs to be handled by staff in a timely manner. The normal type of fireworks area is a normal fire point that is allowed to exist in the target detection area.

[0082] Optionally, the preset warning condition can be used to limit the distribution state of the flame feature points corresponding to the abnormal type of fireworks area, and / or to limit the posture of the target object corresponding to the abnormal type of fireworks area. Based on this, after the electronic device obtains the target feature of the fireworks area, it can determine whether the target feature of the fireworks area meets the preset warning condition. If the target feature of the fireworks area meets the preset warning condition, it can be indicated that the fireworks area in the target detection area is of an abnormal type. Then the electronic device can output warning information corresponding to the fireworks area. If the target feature of the fireworks area does not meet the preset warning condition, it can be indicated that the fireworks area in the target detection area is of a normal type. Then the electronic device may not output warning information.

[0083] In one embodiment, in the above S302, that is, when the electronic device outputs warning information corresponding to the fireworks area when the target characteristics meet the preset warning conditions, the embodiment of the present application provides an optional implementation method, including: S3021-S3022.

[0084] S3021: If the distribution state is an aggregated state, output warning information.

[0085] Combination Figure 6 , considering that the target detection area is usually Figure 6 In the manner shown in (a) in the figure, multiple normal fire points are arranged neatly and dispersedly. If it is recognized that the flame feature points in the fireworks area are in a large and irregular aggregation state, the electronic device can determine that the target features of the fireworks area meet the preset warning conditions and output the warning information corresponding to the fireworks area so that the staff can handle it in time.

[0086] S3022: If the target object detection information indicates that there is no target object in the fireworks area, or the target object is in a tilted posture, output a warning message.

[0087] Considering that normal fire points such as oil lamps or candle lamps set in the target detection area correspond to lamp bodies or candlesticks, and under normal circumstances, the posture of the lamp body or candlestick is upright. If it is recognized that there is no target object in the fireworks area, it can be indicated that the flame feature points in the fireworks area are likely not normal fire points such as oil lamps or candle lamps. If it is recognized that there is a target object in the fireworks area, and the posture of the target object is tilted, it can be indicated that the flame feature points in the fireworks area are normal fire points that are abnormally tilted. In these two cases, the electronic device can determine that the target characteristics of the fireworks area meet the preset warning conditions, and output the warning information corresponding to the fireworks area, so that the staff can handle it in time.

[0088] In one embodiment, in the above S302, that is, when the electronic device outputs warning information corresponding to the fireworks area when the target characteristics meet the preset warning conditions, the embodiment of the present application provides another optional implementation method, including: S3023.

[0089] S3023: If the distribution state is a dispersed state, and there is no target object in the fireworks area or the target object is in a tilted posture, output a warning message.

[0090] If it is identified that the distribution state of the flame feature points in the fireworks area is a dispersed state, the electronic device can further identify the target object detection information in the fireworks area to further eliminate the fire risk.

[0091] If there is no target object in the fireworks area, it can be indicated that the flame feature points in the fireworks area are likely to be scattered abnormal fireworks points. Alternatively, if there are one or more target objects in the fireworks area with a tilted posture, it can be indicated that the flame feature points in the fireworks area are normal fire points that are abnormally tilted. The electronic device can then determine that the target features of the fireworks area meet the preset warning conditions and output warning information. In this way, the electronic device can accurately identify whether the fireworks area is an abnormal type through the distribution state and target object detection information to avoid false alarms.

[0092] In one embodiment, the target feature of the fireworks area may further include: human body recognition information corresponding to the fireworks area. The human body recognition information is used to indicate whether there is a target human body in the target detection area. The distance between the position of the target human body and the fireworks area is less than a preset distance. That is, the target human body is a human body whose distance relative to the fireworks area is less than a preset distance. Based on this, in the above S302, that is, when the electronic device outputs warning information corresponding to the fireworks area when the target feature meets the preset warning conditions, the embodiment of the present application provides another optional implementation method, including: S3024.

[0093] S3024: If the target object detection information indicates that there is no target object in the fireworks area and the human body recognition information indicates that there is no target human body, or the target object detection information indicates that the target object is in a fallen posture and the human body recognition information indicates that there is no target human body, then output a warning message.

[0094] Considering that a person may walk in the detection area holding an oil lamp or candle, etc. In this case, the electronic device may not be able to accurately identify the target object due to the human hand blocking the target object. To further reduce false alarms, the electronic device can perform human body recognition processing on the captured image when it is determined that the target feature indicates that the fireworks area meets the preset warning conditions.

[0095] If the human body is not recognized, or the distance between the recognized human body and the fireworks area is greater than or equal to the preset distance, the electronic device can determine that the human body recognition information is used to indicate that there is no target human body in the target detection area, and output a warning message. If the electronic device recognizes the human body, and determines that the distance between the human body and the fireworks area is less than the preset distance, it determines that the human body recognition information is used to indicate that there is a target human body in the target detection area. In this case, it may be that a person is walking in the detection area holding an oil lamp or a candle lamp. In order to avoid false alarms, the electronic device may not output a warning message.

[0096] Alternatively, considering that the person may have been handling an unusual type of fireworks. To further reduce false alarms, the electronic device may obtain the human body recognition information when determining that the target object detection information is used to indicate that the posture of the target object is falling.

[0097] If the human body is not recognized, or the distance between the recognized human body and the fireworks area is greater than or equal to the preset distance, it means that the person is not dealing with abnormal types of fireworks. The electronic device can determine that the human body recognition information is used to indicate that there is no target human body in the target detection area, and output a warning message. If the electronic device recognizes the human body, and determines that the distance between the human body and the fireworks area is less than the preset distance, it determines that the human body recognition information is used to indicate that there is a target human body in the target detection area. In this case, it may be that the person is already dealing with abnormal types of fireworks. In order to avoid false alarms, the electronic device may not output a warning message.

[0098] In one embodiment, the target features of the fireworks area also include: the shape of the flame feature point in the fireworks area. The shape of the flame feature point is the geometric shape formed by the combustion boundary of the fire point. In addition, a preset shape can be pre-set in the electronic device. The preset shape is the shape of a normal fire point such as an oil lamp or a candle lamp when it burns normally. Based on this, the electronic device can also make a judgment based on the comparison result of the shape of the flame feature point in the fireworks area and the preset shape.

[0099] For example, consider that a person may be holding an oil lamp or a candle lamp and walking in the detection area. In this case, the electronic device may not be able to accurately identify the target object because the target object is blocked by the human hand. To further reduce false alarms, the electronic device can identify the shape of the flame feature point in the fireworks area. If the shape of the flame feature point in the fireworks area is not a preset shape, the electronic device determines that the target feature of the fireworks area meets the preset warning condition and outputs a warning message. If the shape of the flame feature point in the fireworks area is a preset shape, it may be that a person is holding an oil lamp or a candle lamp and walking in the detection area. The electronic device does not output a warning message to avoid false alarms.

[0100] In one embodiment, the target feature of the fireworks area also includes: the area of ​​the fireworks area in the snapshot image corresponding to the target detection area. The area of ​​the fireworks area in the snapshot image corresponding to the target detection area can be the area of ​​the identification box of the fireworks area in the snapshot image corresponding to the target detection area. Based on this, in the above S301, that is, when the electronic device obtains the target feature of the fireworks area, the embodiment of the present application provides an optional implementation method, including: S3011-S3013.

[0101] S3011: Obtain the area of ​​the fireworks region in the captured image.

[0102] Considering that when the area of ​​the fireworks area is large, there are more flame feature points in the fireworks area, and there may be occlusions between the target objects of each flame feature point, the distribution state of the flame feature points in the fireworks area can more accurately reflect whether there is an abnormality in the fireworks area. When the area of ​​the fireworks area is small, there are fewer flame feature points in the fireworks area, such as a fireworks area including one or two flame feature points. In this case, the posture of the target object in the fireworks area can more accurately reflect whether there is an abnormality in the fireworks area.

[0103] Based on this, the electronic device can first obtain the area of ​​the fireworks area in the captured image to determine the distribution state of the flame feature points or the target object detection information in the fireworks area, so as to efficiently obtain the target features that are more matched with the fireworks area, and identify whether there is an abnormality in the fireworks area based on the target features that are more matched with the fireworks area, thereby improving the accuracy and efficiency of the early warning.

[0104] S3012: According to the area being greater than a preset area threshold, the distribution state of the flame feature points in the fireworks area is obtained.

[0105] Among them, the preset area threshold can be flexibly set based on the size of the target object without restriction.

[0106] If the area of ​​the fireworks area in the captured image is larger than the preset area threshold, it can indicate that the number of flame feature points in the fireworks area may be large. The electronic device can then obtain the distribution state of the flame feature points in the fireworks area to accurately identify whether there is an abnormality in the fireworks area.

[0107] S3013: Acquire target object detection information based on the area being less than or equal to a preset area threshold.

[0108] If the area of ​​the fireworks area in the captured image is less than or equal to the preset area threshold, it can indicate that the number of flame feature points in the fireworks area may be small. The electronic device can then obtain target object detection information to accurately identify whether there is an abnormality in the fireworks area.

[0109] In one embodiment, the target feature of the fireworks area further includes: the risk level of the detection area where the fireworks area is located. The risk level includes a first level or a second level. Fireworks with an area larger than a preset area threshold are not allowed to appear in the first level detection area. Fireworks with an area larger than a preset area threshold are allowed to appear in the second level detection area.

[0110] Based on this, in the above S302, that is, when the electronic device outputs warning information corresponding to the fireworks area when the target characteristics meet the preset warning conditions, the embodiment of the present application provides another optional implementation method, including: S3025.

[0111] S3025: If the risk level of the detection area where the fireworks area is located is the first level, and the area of ​​the fireworks area is greater than the preset area threshold, output warning information.

[0112] Considering that there may be one or more normal fire points such as oil lamps or candle lamps in the detection area under normal circumstances. At the same time, considering that there are generally flammable objects such as cloth decorations and wire line aggregation in the building, the building can be further divided into multiple areas with different risk levels.

[0113] For example, the first level area may be a detection area where flammable materials or electric wires are gathered. Such areas usually do not have normal fire points, and when normal fire points are set, the number is small, such as one or two, and the area of ​​the fireworks area in the corresponding captured image is not allowed to be larger than the preset area threshold.

[0114] For another example, the second level area may be a detection area where normal fire points exist. This type of area allows the setting of normal fire points, and the number of normal fire points can be large, and the area of ​​the fireworks area in the corresponding captured image can be greater than the preset area threshold.

[0115] In this case, areas with different risk levels have different sensitivities to fire and smoke warnings. That is, areas at the first level have high sensitivity to fire and smoke warnings. Areas at the second level have low sensitivity to fire and smoke warnings. In other words, under normal circumstances, there will not be large fire and smoke areas in the first level area. If a large fire and smoke area is identified in the first level area, an early warning needs to be issued in time to avoid the problem of missing reports leading to larger fires. Under normal circumstances, a large or small number of normal fire points are allowed to exist in the second level area. When a fire and smoke area is identified in the second level area, it is necessary to further identify the distribution status and / or target object of the flame feature points in the fire and smoke area to avoid the problem of frequent early warnings for normal fire and smoke areas due to false alarms.

[0116] Based on this, when the electronic device obtains the target features of the fireworks area, it can obtain the risk level information of the target detection area to determine the risk level of the target detection area where the fireworks area is located. If the risk level of the target detection area is the first level and the area of ​​the fireworks area is greater than the preset area threshold, the electronic device can output warning information to issue a warning in time to avoid causing a large fire. If the risk level of the target detection area is the second level, the electronic device can further identify based on other features of the fireworks area to avoid false alarms.

[0117] In this way, considering that different items may be placed in different areas, causing different risks of fire, the electronic equipment can adapt to the different characteristics of areas with different risk levels, and perform different feature recognition logic on the fireworks areas in areas with different risk levels, so as to achieve refined recognition and accurate warning of the fireworks warning range.

[0118] In one embodiment, before the above S301, that is, before the electronic device obtains the target features of the fireworks area, the fireworks warning method provided by the embodiment of the present application further includes: S401.

[0119] S401: Determine whether the region overlap is less than a preset overlap threshold.

[0120] The area overlap is the overlap between the fireworks area in the captured image and the warning shielding area corresponding to the target detection area.

[0121] The warning shielding area is a pre-set area in the captured image of the target detection area where no fire and smoke warning is required. Figure 7 FIG. 1 is a schematic diagram of another type of fire and smoke area provided in an embodiment of the present application. The early warning shielding area may be an area where people often move around and where multiple oil lamps or candle lamps are deployed for a long time. Such areas generally do not have a fire risk and do not require fire and smoke warnings.

[0122] After the electronic device recognizes that there is at least one fireworks area in the captured image of the target detection area, it can determine whether there is a corresponding early warning shielding area in the target detection area. If there is no corresponding early warning shielding area in the target detection area, the electronic device executes S301. If there is a corresponding early warning shielding area in the target detection area, the electronic device can determine the overlap between the fireworks area in the captured image and the early warning shielding area corresponding to the target detection area, that is, the area overlap.

[0123] If the area overlap is less than the preset overlap threshold, it can be indicated that the fireworks area is not in the early warning shielding area, and the electronic device executes S301. If the area overlap is greater than or equal to the preset overlap threshold, it can be indicated that the fireworks area is in the early warning shielding area, which can indicate that the fireworks area is a normal fire point deployment area and no further identification is required, then the electronic device no longer executes S301, ends the identification process of the fireworks area, and avoids false alarms for normal fire point deployment areas.

[0124] In the above embodiments of the present application, considering that there are many real fire points within the fire warning range of ancient buildings, the risk of causing fire is relatively high. For fires caused by the tipping over of oil lamps or candle lamps or the ignition of cloth decorations, the electronic device can identify the multi-dimensional features of the fire area in the captured image, and accurately identify the fire area in combination with the preset shielding area.

[0125] In one embodiment, Figure 8 , which is a flow chart of another fire and smoke warning method provided in an embodiment of the present application. Figure 8 The fire and smoke warning method shown includes: S501-S518.

[0126] S501: Obtain a captured image.

[0127] S502: Identify the fireworks area.

[0128] S503: Determine whether a fireworks area is identified.

[0129] If the fireworks area is identified, the electronic device executes S504. If the fireworks area is not identified, the electronic device ignores the captured image and starts to obtain captured images of other areas again.

[0130] S504: Determine whether there is a fireworks area in the target detection area.

[0131] S505: Obtain risk level information of the target detection area.

[0132] S506: Determine that the risk level of the target detection area is the first level.

[0133] If the risk level of the target detection area is the first level, the electronic device can obtain the area of ​​the fireworks area in the captured image to determine whether an immediate warning is needed.

[0134] S507: Determine whether the area is greater than a preset area threshold.

[0135] If the area of ​​the fireworks area in the captured image is greater than the preset area threshold, the electronic device executes S518 to output warning information. If the area of ​​the fireworks area in the captured image is less than or equal to the preset area threshold, the electronic device executes S508 to further obtain the posture of the target object in the fireworks area, so as to accurately identify whether there is an abnormality in the fireworks area and avoid false alarms.

[0136] S508: Acquire the posture of the target object.

[0137] For example, a pre-trained lamp state detection model based on a deep neural network can be configured in the electronic device. The lamp state detection model is used to identify target objects such as lamps or candlesticks placed separately in the image, as well as the posture of the target objects. In this way, the electronic device can efficiently recognize the captured image through the lamp state detection model and obtain the posture of the target object in the fireworks area in the captured image.

[0138] Or further, the lamp state detection model can also identify the on and off properties of the flame feature points. Fig. 9 , which is a schematic diagram of another fireworks area provided in an embodiment of the present application. Fig. 9The figure shows the tilted and upright postures of the lamp body, as well as the lighting and extinguishing of the flame feature points. In this way, the electronic device can also identify the captured image through the lamp body state detection model to obtain the on and off properties of the flame feature points, so as to accurately identify the flame feature points. For example, if there is a small fireworks area in the first level area, and the target object is upright, and the flame feature points are extinguished, it may be that other combustibles are starting to burn. The electronic device can determine that the fireworks area in the captured image of the target detection area is abnormal to avoid missing reports.

[0139] S509: Determine whether the posture is upright.

[0140] If the target object is upright, the electronic device ignores the captured image and reacquires captured images of other areas. If the target object is not upright, that is, the target object is not identified or the target object is tilted, the electronic device executes S518 to output a warning message.

[0141] S510: Determine that the risk level of the target detection area is the second level.

[0142] If the risk level of the target detection area is the second level, the electronic device can obtain the area of ​​the fireworks area in the captured image, so as to further obtain the target features matching the fireworks area.

[0143] S511: Determine whether the area is greater than a preset area threshold.

[0144] If the area of ​​the fireworks region in the captured image is greater than the preset area threshold, the electronic device executes S512. If the area of ​​the fireworks region in the captured image is less than or equal to the preset area threshold, the electronic device executes S516.

[0145] S512: Obtain the distribution state of flame feature points in the fireworks area.

[0146] For example, the electronic device may also be configured with a pre-trained fire point state detection model based on a deep neural network. The fire point state detection model is used to identify the distribution state of normal fire points such as multiple oil lamps or candle lamps placed closely together in a large area in the image. In this way, the electronic device can efficiently identify the captured image through the fire point state detection model and obtain the distribution state of the flame feature points in the fireworks area in the captured image.

[0147] S513: Determine whether the distribution state is a clustered state.

[0148] If the distribution state of the flame feature points in the fireworks area is a clustered state, the electronic device executes S518. If the distribution state of the flame feature points in the fireworks area is not a clustered state but a dispersed state, the electronic device executes S514.

[0149] S514: Acquire the posture of the target object.

[0150] If the distribution state of the flame feature points in the fireworks area is a dispersed state, the electronic device can further obtain the posture of the target object in the fireworks area to further eliminate the fire risk.

[0151] S515: Determine whether the posture is upright.

[0152] If the target object is in a fallen posture or the target object is not recognized, the electronic device executes S518.

[0153] If the target object is in an upright position, the electronic device ignores the captured image, thereby filtering out normal fire points such as oil lamps or candle lamps to avoid false alarms. In addition, the electronic device can further re-acquire the captured images of other detection areas to identify and warn other detection areas.

[0154] S516: Acquire the posture of the target object.

[0155] If the area of ​​the fireworks region in the captured image is less than or equal to the preset area threshold, the electronic device can obtain the posture of the target object in the fireworks region to further identify the type of the fireworks region.

[0156] S517: Determine whether the posture is upright.

[0157] If the target object is in a fallen posture or the target object is not recognized, the electronic device executes S518.

[0158] If the target object is in an upright position, the electronic device ignores the captured image, thereby filtering out normal fire points such as oil lamps or candle lamps to avoid false alarms. In addition, the electronic device can further re-acquire the captured images of other detection areas to identify and warn other detection areas.

[0159] S518: Output warning information.

[0160] Based on the above embodiments of the present application, the electronic device can determine whether the fireworks area appearing in the target detection area is a normal fire point allowed to appear in the target detection area according to the extracted target features, thereby determining whether to issue an early warning. Compared with the early warning decision based on the distance between the identified fireworks point and the unique object, it is easy to cause missed reports when the distance between the identified fireworks point and the unique object is close but the fireworks point is not a normal fire point, and to cause false reports when the distance between the identified fireworks point and the unique object is far but the fireworks point is a normal fire point. The present application can accurately identify based on the multi-dimensional features of the fireworks area, effectively avoid the problem of false reports or missed reports, and realize accurate and effective fire detection and early warning for ancient buildings.

[0161] In the above-mentioned embodiments of the present application, the scheme of the embodiments of the present application is mainly introduced from the perspective of the method. It is understandable that in order to realize the above-mentioned functions, the robot includes at least one of the hardware structure and software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0162] The embodiment of the present application can divide the robot into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0163] For example, Fig.10 The structure diagram of a fire and smoke warning device is shown. The fire and smoke warning device 60 can be used to execute the method involved in the above embodiment. The fire and smoke warning device 60 includes: an acquisition unit 601 and an output unit 602.

[0164] The acquisition unit 601 is used to acquire the target features of the fireworks area when there is a fireworks area in the target detection area. The target features include the distribution state of the flame feature points in the fireworks area and / or the target object detection information. The target object detection information is used to indicate whether there is a target object in the fireworks area and the posture of the target object when the target object exists. The target object is used to place the burning object.

[0165] The output unit 602 is used to output warning information corresponding to the fireworks area when the target feature meets the preset warning condition.

[0166] In a possible embodiment, the distribution state of the flame feature points in the fireworks area includes a dispersed state or a clustered state. The posture of the target object includes standing upright or falling down.

[0167] In a possible embodiment, the output unit 602 is specifically configured to: output warning information if the distribution state is a gathering state, and output warning information if the target object detection information indicates that there is no target object in the fireworks area, or the target object is in a falling posture.

[0168] In a possible embodiment, the output unit 602 is specifically configured to: output warning information if the distribution state is a dispersed state, and there is no target object in the fireworks area or the target object is in a tilted posture.

[0169] In a possible embodiment, the target feature further includes: human body recognition information corresponding to the fireworks area. The human body recognition information is used to indicate whether there is a target human body in the target detection area. The distance between the position of the target human body and the fireworks area is less than a preset distance. The output unit 602 is specifically used to: if the target object detection information is used to indicate that there is no target object in the fireworks area, and the human body recognition information indicates that there is a target human body, or if the target object detection information is used to indicate that the posture of the target object is tilted, and the human body recognition information indicates that there is no target human body, then output a warning message.

[0170] In a possible embodiment, the target feature further includes the area of ​​the fireworks area in the captured image corresponding to the target detection area. The acquisition unit 601 is specifically used to: acquire the area of ​​the fireworks area in the captured image. If the area is greater than a preset area threshold, the distribution state of the flame feature points in the fireworks area is acquired. If the area is less than or equal to the preset area threshold, the target object detection information is acquired.

[0171] In a possible embodiment, the target feature also includes a risk level of the detection area where the fireworks area is located. The risk level includes a first level or a second level. Fireworks with an area larger than a preset area threshold are not allowed to appear in the first level detection area. Fireworks with an area larger than a preset area threshold are allowed to appear in the second level detection area. The output unit 602 is specifically used to: if the risk level of the detection area where the fireworks area is located is the first level, and the area of ​​the fireworks area is larger than the preset area threshold, then output warning information.

[0172] For the detailed description of the above optional methods, please refer to the above method embodiments, which will not be repeated here. In addition, the explanation and description of the beneficial effects of any of the above-mentioned fire and smoke warning devices 60 can refer to the above corresponding method embodiments, which will not be repeated here.

[0173] As an example, combining Figure 4 The functions of the acquisition unit 601 and the output unit 600 in the fire and smoke warning device 60 can be partially or completely realized by Figure 4 Processor 201 in the Figure 4 The program code in the memory 202 is implemented.

[0174] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed on an electronic device, the electronic device executes any of the methods executed by the electronic devices provided above.

[0175] For the explanation of the relevant contents and description of the beneficial effects of any of the above-mentioned computer-readable storage media, reference may be made to the above-mentioned corresponding embodiments, which will not be repeated here.

[0176] The embodiment of the present application also provides a computer program product including instructions, which, when executed on an electronic device, causes the electronic device to perform any one of the methods in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the electronic device, the process or function according to the embodiment of the present application is generated in whole or in part.

[0177] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided in the embodiments of the present application, such as but not limited to the above-mentioned memories, computer-readable storage media, etc., are all non-transitory.

[0178] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on an electronic device, all or part of the processes or functions according to the embodiments of the present application are generated.

[0179] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0180] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A fire warning method, characterized in that: include: When there is a fireworks area in the target detection area, obtaining target features of the fireworks area; When the area of ​​the fireworks area in the captured image corresponding to the target detection area is greater than a preset area threshold, the target feature includes a distribution state of flame feature points in the fireworks area, and / or when the area of ​​the fireworks area in the captured image corresponding to the target detection area is less than or equal to a preset area threshold, the target feature includes target object detection information; the distribution state of flame feature points in the fireworks area includes a dispersed state or a clustered state; the target object detection information is used to indicate whether there is a target object in the fireworks area and the posture of the target object when the target object exists; The target object is used to place burning objects; When the target feature meets the preset warning condition, the warning information corresponding to the fireworks area is output.

2. The fire and smoke warning method according to claim 1, characterized in that: The posture of the target object includes standing upright or falling down.

3. The fire and smoke warning method according to claim 2, characterized in that: When the target feature meets the preset warning condition, outputting the warning information corresponding to the fireworks area includes: If the distribution state is an aggregated state, outputting the warning information; If the target object detection information indicates that the target object does not exist in the fireworks area, or the target object is in a state of falling, the warning information is output.

4. The fire and smoke warning method according to claim 2 or 3, characterized in that: When the target feature meets the preset warning condition, outputting the warning information corresponding to the fireworks area also includes: If the distribution state is a dispersed state, and the target object does not exist in the fireworks area or the target object is in a tilted state, a warning message is output.

5. The fire and smoke warning method according to claim 2, characterized in that: The target feature also includes: human body recognition information corresponding to the fireworks area; the human body recognition information is used to indicate whether there is a target human body in the target detection area; the distance between the position of the target human body and the fireworks area is less than a preset distance; when the target feature meets the preset warning condition, outputting the warning information corresponding to the fireworks area includes: If the target object detection information indicates that the target object does not exist in the fireworks area and the human body recognition information indicates that there is no target human body, or the target object detection information indicates that the target object is in a fallen posture and the human body recognition information indicates that there is no target human body, the warning information is output.

6. The fire and smoke warning method according to claim 5, characterized in that: The target feature also includes the risk level of the detection area where the fireworks area is located; the risk level includes the first level or the second level; fireworks with an area larger than a preset area threshold are not allowed to appear in the detection area of ​​the first level; fireworks with an area larger than a preset area threshold are allowed to appear in the detection area of ​​the second level; When the target feature meets the preset warning condition, outputting the warning information corresponding to the fireworks area includes: If the risk level of the detection area where the fireworks area is located is the first level, and the area of ​​the fireworks area is greater than the preset area threshold, the warning information is output.

7. A fire warning device, characterized in that: include: Acquisition unit and output unit; The acquisition unit is used to acquire the target features of the fireworks area when there is a fireworks area in the target detection area; When the area of ​​the fireworks area in the captured image corresponding to the target detection area is greater than a preset area threshold, the target feature includes a distribution state of flame feature points in the fireworks area, and / or when the area of ​​the fireworks area in the captured image corresponding to the target detection area is less than or equal to a preset area threshold, the target feature includes target object detection information; the distribution state of flame feature points in the fireworks area includes a dispersed state or a clustered state; the target object detection information is used to indicate whether there is a target object in the fireworks area and the posture of the target object when the target object exists; The target object is used to place burning objects; The output unit is used to output warning information corresponding to the fireworks area when the target feature meets the preset warning condition.

8. An electronic device, characterized in that: include: processor; The processor is connected to a memory, the memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions stored in the memory, so that the electronic device implements the fireworks warning method according to any one of claims 1 to 6.

9. A fire warning system, characterized in that: include: Electronic equipment and camera equipment; the electronic equipment is used to execute the fire and smoke warning method according to any one of claims 1 to 6; The camera device is used to collect image information.

Images