Converter station fire-fighting emergency processing method and device based on video calling

Abstract

The embodiment of the invention provides a converter station fire-fighting emergency processing method and device based on video calling. The method comprises the following steps: acquiring first-level video data sent by a first-level camera group associated with a fire object in a converter station; when it is determined that first video data of a first view angle of the fire object does not meet an emergency aid decision-making condition according to the first-level video data, determining a first camera shooting the first video data from a first-level camera group, determining a second camera corresponding to the position of the first camera from a second-level camera group having a position mapping relationship with the first-level camera group; and acquiring second video data of the fire object at a first visual angle corresponding to the second camera, and performing fire emergency processing according to the first-level video data and the second video data. Therefore, timeliness, effectiveness and reliability of fire-fighting emergency processing of the converter station can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of converter station fire fighting, in particular to a converter station fire fighting emergency processing method and device based on video calling. BACKGROUND

[0002] As the core hub of the efficient and stable operation of the power system, the operation state of the converter station is directly related to the stability of the entire power system. The fire safety of the converter station, as a key link to ensure the smooth operation of the converter station, plays an important role in maintaining the stability of the power system. However, the valve hall, transformer and other areas of the converter station have dense live equipment and flammable insulating oil, and the fire has the characteristics of rapid spread, easy explosion and wide power outage influence. Therefore, it is necessary to efficiently and reliably control and handle the fire emergency of the converter station.

[0003] In the fire emergency handling of the converter station, in order to timely grasp the fire scene situation in the converter station in order to timely handle the corresponding fire emergency, currently, video data of the fire scene is generally obtained for emergency analysis. However, in the actual fire emergency handling process, the video data obtained from the camera of the converter station may not meet the current fire emergency needs, resulting in failure to make effective fire emergency decisions in time or leading to fire emergency decision errors, affecting the timeliness and effectiveness of the fire emergency handling of the converter station. Therefore, the existing fire emergency efficiency of the converter station is low, and the effectiveness and reliability of the fire emergency handling are not high. SUMMARY

[0004] The present application provides a converter station fire emergency handling method and device based on video calling, which can improve the fire emergency efficiency and reliability of the converter station.

[0005] In the first aspect, a converter station fire emergency handling method based on video calling is provided, and the method comprises:

[0006] Obtaining first video data sent by a first camera group associated with a fire object in a converter station, wherein the first video data comprises video data of multiple perspectives of the fire object respectively captured by multiple cameras at multiple positions;

[0007] When it is determined according to the first video data that the first video data of the first perspective of the fire object does not meet the emergency auxiliary decision condition, determining a first camera that captures the first video data from the first camera group, and determining a second camera corresponding to the position of the first camera from a second camera group having a position mapping relationship with the first camera group, wherein the second camera group and the first camera group have a position mapping relationship with the same perspective centering on the position of the fire object;

[0008] acquire second video data of the fire object in the first visual angle corresponding to the second camera;

[0009] perform fire emergency processing according to the first-level video data and the second video data.

[0010] In an implementation manner, the first video data of the fire object in the first visual angle determined according to the first-level video data does not satisfy an emergency auxiliary decision condition, including at least one of the following:

[0011] determining that the definition of the first video data is lower than a definition threshold;

[0012] determining that the resolution of the first video data is lower than a resolution threshold;

[0013] determining that a key target object in the first video data is blocked for a time length exceeding a predetermined time length;

[0014] determining that the contribution degree of the first video data in joint emergency decision with other video data in the first-level video data is less than a contribution degree threshold.

[0015] In an implementation manner, the second camera corresponding to the first camera position is determined according to a second camera group having a position mapping relationship with the first camera group, including:

[0016] determining the second camera group from candidate camera groups having a position mapping relationship with the first camera group according to the position of the fire object, wherein one candidate camera group is determined with a fire monitoring position in a shared visual angle range of the first camera group as a visual angle alignment center, the shared visual angle range of the first camera group includes at least one fire monitoring position, and the at least one fire monitoring position includes the position of the fire object;

[0017] determining the second camera corresponding to the first camera position according to the second camera group.

[0018] In an implementation manner, the second camera corresponding to the first camera position is determined according to a second camera group having a position mapping relationship with the first camera group, including:

[0019] determining a reference camera having a visual angle candidate relationship with a camera in the first camera group with the position of the fire object as a visual angle alignment center;

[0020] acquiring basic space data of the first camera group and the reference camera, wherein the basic space data includes at least one of position information, height information, angle information, visual angle range information, and environment information of the camera;

[0021] constructing a graph neural network model according to the basic spatial data of the primary camera group and the reference camera, wherein each camera in the first camera group and the reference camera is a node of the graph neural network model, the node feature of each node includes the basic spatial data of the corresponding camera, the edges between nodes represent that the corresponding cameras of the nodes have a view angle candidate relationship, and the edge weight is determined according to at least one of the view angle candidate range, the relative distance, the line-of-sight reachability, and the historical collaborative effectiveness score between the corresponding cameras;

[0022] determining, by using the graph neural network model, a secondary camera group from the reference camera according to the edge weight, the secondary camera group being composed of cameras that meet a position mapping relationship with each camera in the primary camera group;

[0023] determining a second camera corresponding to the position of the first camera according to the secondary camera group.

[0024] In an implementation manner, determining a second camera corresponding to the position of the first camera according to the secondary camera group includes:

[0025] inputting the position of the first camera, the environment information in which the first camera is located, and the emergency auxiliary decision demand information into the graph neural network model to obtain at least one candidate camera having a view angle candidate relationship with the first camera;

[0026] determining a view angle complementarity score of each candidate camera relative to the first camera, wherein the view angle complementarity score is determined according to at least one of a view angle candidate range of the candidate camera relative to the first camera, a missing information gain of the candidate camera under the environment information, a predicted image quality of the candidate camera, and a collaborative feasibility of the candidate camera and the first camera;

[0027] determining a second camera corresponding to the position of the first camera based on the view angle complementarity score of each candidate camera relative to the first camera.

[0028] In an implementation manner, determining a second camera corresponding to the position of the first camera based on the view angle complementarity score of each candidate camera relative to the first camera includes:

[0029] determining the candidate camera with the highest view angle complementarity score as the second camera;

[0030] or, determining the candidate camera with a view angle complementarity score greater than a first score threshold as the second camera;

[0031] Or, in the case that the view angle complementarity scores of all candidate cameras are less than the second score threshold, a candidate camera with a view angle complementarity score in the top N is selected as the second camera, wherein the second camera is used to synthesize a simulated view angle, the simulated view angle is used to synthesize the second video data, and N is a natural number.

[0032] In an implementation manner, the second video data of the fire object in the first view angle corresponding to the second camera is acquired by:

[0033] The at least one second camera is controlled to collect at least one candidate video data of the fire object;

[0034] Third video data of a first simulated view angle is synthesized according to the at least one candidate video data, and the third video data is taken as the second video data, wherein the first simulated view angle is within a shared view angle range of the at least one second camera for collecting corresponding candidate video data; or,

[0035] Fourth video data of a second simulated view angle is synthesized according to the first video data and the at least one candidate video data, and the fourth video data is taken as the second video data, wherein the second simulated view angle is within the shared view angle range of the at least one second camera for collecting corresponding candidate video data and within an overlapping view angle range of the first view angle.

[0036] In an implementation manner, the method further comprises:

[0037] A fire development trend of the fire object is predicted;

[0038] A key view angle is determined according to the fire development trend, wherein the key view angle is a view angle for collecting key video data relative to the fire object, or the key view angle is a view angle of a first-level camera relative to a failure of the fire object;

[0039] A backup camera corresponding to the key view angle is determined from the second camera group, and a backup instruction is sent to the backup camera, wherein the backup instruction is used to instruct the backup camera to start or prepare to acquire video data of the fire object in the key view angle.

[0040] In an implementation manner, the fire emergency decision module is configured to acquire second video data of the fire object in the first view angle collected by the second camera, comprising:

[0041] An identifier correspondence relationship between a device identifier of the second camera and a device identifier of the first camera is carried in the second video data, and the second video data is verified for validity according to the identifier correspondence relationship;

[0042] and / or,

[0043] The control carries a priority transmission identifier in the second video data, and the priority transmission identifier is used to indicate that the second video data is transmitted to the converter station digital fire control system with high priority.

[0044] In a second aspect, a converter station fire emergency handling device based on video calling is provided, and the device comprises:

[0045] A first acquisition module is configured to acquire first video data sent by a first camera group associated with a fire object in a converter station, wherein the first video data comprises video data of multiple perspectives of the fire object captured by multiple first cameras at different positions.

[0046] A first determination module is configured to determine a first camera that captures first video data of a first perspective of the fire object from the first camera group when the first video data does not meet an emergency auxiliary decision condition.

[0047] A second determination module is configured to determine a second camera corresponding to the first camera from a second camera group having a position mapping relationship with the first camera group, wherein the second camera group and the first camera group have a position mapping relationship with the same perspective alignment center at the position of the fire object.

[0048] A second acquisition module is configured to acquire second video data of the fire object in the first perspective corresponding to the second camera.

[0049] A fire emergency handling module is configured to perform fire emergency handling according to the first video data and the second video data.

[0050] In a third aspect, a computer storage medium is provided, and the computer storage medium stores a computer program, and the computer program is executed to implement steps of the converter station fire emergency handling method based on video calling according to any one of the first aspect.

[0051] In a third aspect, a computer program product is provided, and the computer program product comprises a computer program, and the computer program is executed to implement steps of the converter station fire emergency handling method based on video calling according to any one of the second aspect.

[0052] The method and device for fire emergency processing of a converter station based on video calling according to the embodiments of the present application first acquire first video data sent by a first camera group associated with a fire object in the converter station, the first video data including video data of multiple perspectives of the fire object respectively photographed by first cameras at multiple positions in the first camera group. In this way, the on-site situation of the fire object can be comprehensively understood through the multi-perspective video data of the fire object, to assist in making timely and effective fire emergency decisions. When it is determined according to the first video data that first video data of a first perspective of the fire object does not meet the conditions for emergency assistance decision-making, a first camera that photographs the first video data is determined from the first camera group, and a second camera corresponding to the first camera in position is determined from a second camera group having a position mapping relationship with the first camera group, where the second camera group and the first camera group have a position mapping relationship with the position of the fire object as the same perspective alignment center. Then, second video data of the fire object of the first perspective corresponding to the second camera is acquired, so as to make fire emergency decision-making processing according to the first video data and the second video data. That is, when the video data photographed by a certain camera (i.e., the first camera) in the first camera group from its corresponding perspective (i.e., the first perspective) cannot assist in making fire emergency decision-making, the second camera (i.e., the second camera) corresponding to the position of the first camera can be quickly linked as a backup / alternate perspective of the first perspective, so as to quickly acquire alternate video data (i.e., the second video data) that does not meet the requirements of the first perspective in the first video data. Then, timely and effective fire emergency decision-making is made according to the alternate video data of the backup / alternate perspective of the first perspective and the first video data of other perspectives. In this way, the video alternate emergency of a certain perspective of the fire object is realized through the quick linkage of the first camera and the second camera, and the timeliness, effectiveness and reliability of the fire emergency processing of the converter station are improved. BRIEF DESCRIPTION OF DRAWINGS

[0053] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0054] Figure 1 A schematic diagram of an application scenario applicable to the embodiments of the present application;

[0055] Figure 2 A flowchart of the fire emergency method of the converter station based on video in the embodiments of the present application;

[0056] Figure 3 A deployment diagram of the first camera group and the second camera group in the embodiments of the present application;

[0057] Figure 4This is a structural block diagram of the video-based converter station fire emergency device in the embodiments of this application. Detailed Implementation

[0058] To make the technical solutions and advantages of the embodiments of this application clearer, the exemplary embodiments of this application are described in further detail below. Obviously, the described embodiments are only a part of the embodiments of this application, and not an exhaustive list of all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0059] The technical solution of this application embodiment can be applied to a blockchain system. Through this technical solution, a certain degree of security control can be performed when writing data to the blockchain system and accessing data on the blockchain, thereby improving the security of data on the blockchain.

[0060] To better understand the technical solutions provided in the embodiments of this application, the application scenarios applicable to the technical solutions provided in the embodiments of this application are briefly introduced below. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided in the embodiments of this application can be flexibly applied according to actual needs.

[0061] Please see Figure 1 As shown, Figure 1 As an application scenario to which the technical solution of this application embodiment applies, this application embodiment can remotely manage the fire safety of converter stations based on a three-tier architecture of "headquarters (platform side) - provincial side - station side". In this three-tier architecture, "headquarters" can refer to the power grid system headquarters, "provincial side" can refer to the provincial unit of the power grid system, and "station side" can refer to converter stations deployed in various locations. Wherein, as... Figure 1 As shown, the "station side" is deployed with multiple converter stations, such as converter stations 1-n. Each converter station can connect to its respective provincial unit, for example, converter stations 1-2 connect to Province A, converter stations 3-4 connect to Province B, etc. On the other hand, each converter station can also directly connect to the converter station fire control system deployed at the "headquarters". In this way, each converter station can simultaneously report the fire IoT data in the converter station to its respective provincial unit and the converter station fire control system at the headquarters. In addition, the converter station digital fire control system of the provincial unit to which each converter station belongs and the converter station at the headquarters can also send relevant notifications and instructions to each converter station. For example, when a fire-fighting equipment in a converter station malfunctions or a fire hazard occurs in a converter station, the "headquarters" and the "provincial side" can send fire control-related instructions and fire emergency response-related instructions to the converter station, thereby realizing remote fire safety control and fire emergency response for the converter station.

[0062] The "headquarters" in the above-mentioned "headquarters-provincial side-station side" three-level architecture can also be understood as "platform side" or "system side", and the corresponding converter station fire control management system can also be referred to as a converter station fire control management platform at this time.

[0063] In addition, the above-mentioned "headquarters-provincial side-station side" three-level architecture can adopt a cloud-edge collaboration technical architecture, wherein the "headquarters" and the "provincial side" can deploy the converter station fire control management system in the cloud, and the converter station in the "station side" is deployed at the edge. Based on the converter station cloud-edge collaboration technical architecture, multi-level fire safety management and control and fire emergency decision-making of the power grid headquarters-power grid provincial units-converter station end can be realized. The fire data, fire resource data, and fire equipment state data of the converter station end are transmitted to the provincial units and the headquarters, and the provincial units and the headquarters can make fire emergency decisions based on these data, realize multi-level unified decision-making and online scheduling of digital fire emergency of the converter station, and improve the fire emergency handling efficiency.

[0064] In another implementation manner, as shown in Figure 1 the converter station fire control management system deployed in the headquarters can also be deployed in each provincial unit and each converter station end, for example, as shown in Figure 1 A province, B province, and C province in the above-mentioned embodiment each deploy a converter station fire control management system, and part or all of the converter stations 1-n can also deploy a converter station fire control management system. Each provincial unit can perform fire safety management and control and fire emergency handling on the subordinate converter stations through the locally deployed converter station fire control management system, and each converter station can perform fire safety management and control on itself through the locally deployed converter station fire control management system, and can also exchange information with the converter station fire control management systems of the provincial side and the headquarters through the locally deployed converter station fire control management system, so as to realize unified management and scheduling of fire control of the three ends on the converter station.

[0065] As mentioned above, in the fire emergency process of the converter station, the video data obtained by the related technology from the converter station camera can not meet the current fire emergency demand, which can cause ineffective fire emergency decision-making or cause fire emergency decision-making errors, and affect the timeliness and effectiveness of the converter station fire emergency handling. In view of this, the embodiment of the present application provides a converter station fire emergency handling method based on video calling, which can be executed by the converter station fire control management system or the converter station fire control management platform deployed in the headquarters (platform side), the provincial side, and the station side as shown in Figure 1 The method includes S201-S204, and the converter station fire emergency handling method based on video calling of the embodiment of the present application will be described below with reference to Figure 2 The method includes S201-S204, and the converter station fire emergency handling method based on video calling of the embodiment of the present application will be described below with reference to Figure 2 The method includes S201-S204, and the converter station fire emergency handling method based on video calling of the embodiment of the present application will be described below with reference to

[0066] S201: Obtain first-level video data sent by a first-level camera group associated with the fire object in the converter station, wherein the first-level video data includes video data of multiple perspectives of the fire object captured by multiple positions of the first-level camera.

[0067] A plurality of cameras are deployed in each area of the converter station to monitor the areas and equipment in the converter station by the cameras. In the embodiments of the present application, in order to monitor the fire object in all directions, a plurality of levels of cameras can be deployed in advance for the fire object. In specific implementation, the equipment in the converter station prone to fire can be counted, such as valve tower, converter valve, converter transformer, DC field equipment, cable trench, etc. in the converter station, and then a plurality of levels of camera groups can be deployed for the equipment, for example, two levels of camera groups are deployed for some conventional equipment, and for example, three levels of camera groups are deployed for some key equipment. The spatial deployment positions of the camera groups in each level are different, wherein the spatial deployment positions include distance and height from the equipment.

[0068] For example, referring to the two levels of camera groups deployed for some equipment in the converter station shown in FIG. 1, Figure 3 wherein the first-level camera group includes cameras 1-1, 1-2, 1-3, 1-4 deployed around the equipment, and the second-level camera group includes cameras 2-1, 2-2, 2-3, 2-4, 2-5, 2-6, 2-7, 2-8 deployed around the equipment. The distance between the first-level camera group and the equipment is less than the distance between the second-level camera group and the equipment. As can be understood, the distance between the multi-level camera groups and the equipment increases gradually, and the cameras in each level of camera group are deployed around the equipment as much as possible, for example, Figure 3 the deployment mode shown in FIG. 1, or for example, a square-like or triangle-like deployment mode can also be used. In this way, the cameras in each level can capture video data of different angles from multiple perspectives of the equipment, so that the detailed conditions of each perspective of the equipment can be viewed in all directions according to the video data of different perspectives, and then reliable and effective fire-fighting emergency decisions can be made for the equipment in time according to the detailed video data of each perspective when the equipment catches fire. In addition, the camera groups in different levels can have different or same deployment heights. It should be understood that “different or same” here means approximately the same or different height, for example, Figure 3For example, camera 1-2 in the first-level camera group is deployed at a height of about 4 meters, and cameras 2-3, 2-4, and 2-5 in the corresponding second-level camera group are deployed at heights of about 4.8 meters, 4 meters, and 3.3 meters, respectively. In this way, camera 1-2 and cameras 2-3, 2-4, and 2-5 can capture videos of the in-station equipment from different heights in the same visual angle, so as to obtain video data of the equipment at different heights in the same visual angle.

[0069] In the embodiments of the present application, each in-station equipment (for example, a fire object) can have a corresponding first-level camera group and a second-level camera group associated therewith, that is, the first-level camera group and the second-level camera group associated with each in-station equipment can be different. In other embodiments, if two in-station equipment are located close to each other, they can also share the same pair of first-level camera group and second-level camera group. The second-level camera group for a certain in-station equipment has a position mapping relationship with the first-level camera group with the position of the fire object as the same visual angle alignment center, that is, each second-level camera in the second-level camera group has a position mapping relationship with a certain first-level camera in the first-level camera group, and the position mapping relationship is based on the position of the in-station equipment as a reference point, so that the second-level camera and the first-level camera have the same visual angle range with the position of the in-station equipment as the alignment center. In other words, the second-level camera and the corresponding first-level camera have the same shooting visual angle range with the position of the in-station equipment as the reference point, that is, the multi-level camera groups have a visual angle backup / substitute relationship. In this way, when a certain first-level camera fails or the video data captured by the first-level camera does not meet the fire emergency use condition, the same visual angle second-level camera having a position corresponding relationship with the first-level camera can be used to substitute it, thereby improving the fault tolerance of the camera. Continuing with the above example, the second-level camera having a position corresponding relationship with the first-level camera 1-1 is camera 2-1 and 2-2. As can be seen, the first-level camera 1-1 and the second-level cameras 2-1 and 2-2 have approximately the same shooting visual angle range with the position of the equipment where the fire occurs in the figure as the alignment center, for example, both are video shooting for the "lower left visual angle" of the fire object. When the first-level camera 1-1 fails or the video data captured by the first-level camera 1-1 is unavailable, the second-level camera 2-1 and / or the second-level camera 2-2 can be quickly selected as the substitute of the first-level camera 1-1 to continue shooting the video data of the "lower left visual angle" of the fire object. Figure 3

[0070] For example, the equipment or area where the fire occurs in the converter station is referred to as a fire object. In order to timely handle the fire emergency of the fire object, the first-level video data sent by the first-level camera group associated with the fire object can be obtained. The first-level video data can include video data of the fire object captured by the multiple first-level cameras deployed at multiple positions in the first-level camera group from multiple visual angles. Continuing with the above example, the first-level video data sent by the first-level camera group can include video data of the fire object captured by the first-level cameras 1-1, 1-2, and 1-3 from the "upper left visual angle", "upper right visual angle", and "lower left visual angle", respectively. Figure 3 ​For example, the first-level video data can include multi-angle video data obtained by the first-level cameras 1-1, 1-2, 1-3, and 1-4 from respective angles, which can be used to view and analyze the real-time situation of the fire object from multiple angles, such as determining the area where the fire object is located, the type of fire, the range of fire, the root of the fire, and other equipment, personnel, or objects around the fire object, so as to determine the fire emergency plan or fire emergency rescue scheme in a timely manner according to the information, and improve the efficiency of fire emergency.

[0071] In S202, when the first video data of the first angle of the fire object determined according to the first-level video data does not meet the emergency auxiliary decision condition, a first camera that captures the first video data is determined from the first-level camera group, and a second camera corresponding to the first camera in position is determined from the second-level camera group having a position mapping relationship with the first-level camera group; wherein the second-level camera group has a position mapping relationship with the first-level camera group with the position of the fire object as the same angle alignment center.

[0072] After obtaining the first-level video data captured by the first-level camera group, the video data corresponding to each angle in the first-level video data is analyzed. If the video data of each angle meets the emergency auxiliary decision condition, fire emergency decision is made according to the video data. If the video data of one or more angles (for example, referred to as the first angle) does not meet the emergency auxiliary decision condition, the second-level camera with the first angle can be quickly linked to replace the video. Then, the first-level camera that captures the first video data of the first angle (for example, referred to as the first camera) is determined from the first-level camera group, and the second-level camera (for example, referred to as the second camera) with the same angle range as the first camera is determined from the second-level camera group according to the position mapping relationship between the first-level camera group and the second-level camera group. It can be understood that the second-level camera can be one or more, and the following example continues to take Figure 3 For example, the first camera 1-2 (i.e., the first camera) that captures the first video data of the first angle does not meet the emergency auxiliary decision condition, and the second-level cameras with the same angle as the first camera include the second-level cameras 2-3, 2-4, and 2-5. Therefore, the second-level camera (i.e., the second camera) used to replace the video can be one or more of the second-level cameras 2-3, 2-4, and 2-5, that is, some or all of the second-level cameras with the same replacement angle as the first camera are selected to participate in the subsequent fire emergency processing based on the video.

[0073] In a specific implementation process, determining that the first video data does not meet the emergency auxiliary decision condition can include at least one of the following: determining that the definition of the first video data is lower than a definition threshold, which indicates that the definition of the first video data is low and cannot meet the video analysis requirement, and thus cannot be used for fire emergency decision; or determining that the resolution of the first video data is lower than a resolution threshold, which indicates that the resolution of the first video data is low and cannot meet the video analysis requirement, and thus cannot be used for fire emergency decision; or determining that a key target object (for example, a key component of a device or a device ignition point) in the first video data is blocked for a time period longer than a predetermined time period, which will seriously affect the emergency processing judgment of the key target object, and thus it is considered that it cannot be used for fire emergency decision; or determining that the contribution degree of the first video data in joint emergency decision with other video data in the first-level video data is less than a contribution degree threshold, for example, the first video data and other video data in the first-level video data except the first video data are used for joint emergency decision to determine the fire object position, analyze the fire environment, and estimate the fire trend, and the contribution degree of the first video data in the entire joint emergency decision task is low, and it is considered that it cannot be used for this fire emergency decision, that is, the joint emergency decision includes at least one of fire object positioning, fire environment detection, and fire trend estimation.

[0074] At least one of the definition threshold, the resolution threshold, the predetermined time period, and the view angle contribution degree threshold is determined according to the attribute information of the fire object and / or the fire scene in which the fire object is located, that is, the corresponding threshold can be determined according to the specific fire scene to adapt to the current fire situation and improve the judgment accuracy of whether the emergency auxiliary decision condition is met.

[0075] Before the second camera is selected, the second camera group having a position mapping relationship with the first camera needs to be accurately selected, and the present application embodiment provides the following two implementation manners.

[0076] In the first implementation, the secondary camera group can be pre-configured, that is, the secondary camera group is a pre-configured static camera group. In this case, the secondary camera group can be determined in the following manner: according to the position of the fire object, the secondary camera group is determined from the candidate camera group having a position mapping relationship with the primary camera group. One candidate camera group is determined with a fire monitoring position in the shared view angle range of the primary camera in the primary camera group as the view angle alignment center. The shared view angle range of the primary camera group includes at least one fire monitoring position, and the at least one fire monitoring position includes the position of the fire object. That is, in the shared view angle range of all primary cameras in the primary camera group, there can be multiple station equipment that need to be monitored for fire. The position of each station equipment that needs to be monitored corresponds to a fire monitoring position. For each fire monitoring position in the multiple fire monitoring positions, one or more secondary cameras corresponding to each primary camera position are determined with the fire monitoring position as the same view angle alignment center, thereby obtaining the secondary camera group corresponding to the primary camera group of the fire monitoring position. The corresponding primary camera group and secondary camera group are pre-configured for each fire monitoring position. When the secondary camera is linked with the primary camera, the secondary camera that needs to be replaced can be quickly located, and the linkage efficiency is high.

[0077] In the second implementation, the secondary camera group can be dynamically determined by the system. For example, the secondary camera group can be dynamically determined for the fire object in the following manner: with the position of the fire object as the same view angle alignment center, a reference camera having a view angle candidate relationship with the camera in the primary camera group is determined. Specifically, for each primary camera in the primary camera group, a reference camera having a view angle candidate relationship with the primary camera is determined. Then, the basic space data of the primary camera group and the determined reference camera is obtained, wherein the basic space data of the camera includes at least one of the position information, height information, angle information, view angle range information, and environment information of the camera. A graph neural network model is constructed according to the basic space data of the primary camera group and the reference camera. Each primary camera and each reference camera in the primary camera group is taken as a node of the graph neural network model. The node feature of each node includes the basic space data of the camera corresponding to the node. The edge connecting the nodes represents that the cameras corresponding to the nodes have a view angle candidate relationship. That is, only two nodes having a view angle candidate relationship are connected by an edge. The edge weight is determined according to at least one of the view angle candidate range, relative distance, line-of-sight reachability, and historical cooperation effectiveness score between the cameras corresponding to the nodes. Then, the reference camera group satisfying the position mapping relationship with each primary camera in the primary camera group is determined from the reference camera to form the secondary camera group by using the constructed graph neural network model according to the edge weight.

[0078] That is, the second camera group can be dynamically determined by the graph neural network. According to the relative spatial relationship and historical cooperation of each first camera and each reference camera, the second camera group can be flexibly and accurately determined according to the scene situation of the fire scene, so as to realize effective linkage and complementation of the first camera.

[0079] After the second camera group is dynamically determined based on the above-mentioned second mode, in an embodiment, the second camera corresponding to the first camera in the first camera can be determined from the second camera group in the following manner: inputting the position of the first camera, the environment information in which the first camera is located, and the emergency auxiliary decision demand information into the graph neural network model to obtain at least one candidate camera having a perspective complementary relationship with the first camera; then determining the perspective complementarity score of each candidate camera relative to the first camera, wherein the perspective complementarity score is determined according to at least one of the perspective complementary range of the candidate camera relative to the first camera, the missing information gain of the candidate camera under the environment information, the predicted image quality of the candidate camera, and the cooperative feasibility of the candidate camera and the first camera; and determining the second camera corresponding to the position of the first camera based on the perspective complementarity score of each candidate camera relative to the first camera.

[0080] For the scoring factors for determining the perspective complementarity score, the perspective complementary range of the candidate camera relative to the first camera indicates the perspective overlap range between the shooting perspective of the candidate camera relative to the fire object and the shooting perspective of the first camera relative to the fire object. The greater the perspective overlap range, the greater the field of view that the corresponding candidate camera can provide for the missing angle of the first camera, and the candidate camera can completely cover or partially cover the perspective range of the first camera. The missing information gain of the candidate camera under the environment information indicates how much key information that the candidate camera can provide for the missing first camera under the current environment (smoke, light) and its own state, such as the clarity of the fire point root, the position of the fire spread front, the personnel situation in a specific area, and the like. The more key information provided, the greater the corresponding missing information gain. The predicted image quality of the candidate camera indicates the video quality of the predicted candidate camera under the current environment, such as clarity, occlusion degree, and the like. The cooperative feasibility of the candidate camera and the first camera can be determined by considering factors such as network condition, computing resource, physical line-of-sight accessibility (whether there is dynamic occlusion between the fire object and the like).

[0081] That is, the second camera with optimal view complementarity can be determined from at least one candidate camera with view complementation relationship with the first camera according to the view complementarity score of the graph neural network, and in specific implementation, each score factor for determining the view complementarity score can be assigned with a corresponding weight according to the current emergency auxiliary decision demand information, and then the view complementarity score of each candidate camera can be calculated in a weighted summation manner, and then the final second camera can be selected based on the obtained view complementarity score.

[0082] The embodiments of the present application determine the optimal second camera for the first camera through the graph neural network model, which can improve the accuracy and effectiveness of the selection of the second camera and the reliability of the fire emergency processing, because the current emergency auxiliary decision demand information and various score factors affecting the view complementarity score are considered.

[0083] In the embodiments of the present application, the second camera corresponding to the position of the first camera is determined based on the view complementarity score of each candidate camera relative to the first camera, and the following implementation manners can be specifically included.

[0084] In the first implementation manner, the candidate camera with the highest view complementarity score is determined as the second camera, and in this case, the second camera can be one or more.

[0085] In the second implementation manner, the candidate camera with a view complementarity score greater than a first score threshold is determined as the second camera, and in this case, the second camera can be one or more.

[0086] In the third implementation manner, in the case that the view complementarity score of each candidate camera is less than a second score threshold, the candidate camera with the top N view complementarity score is selected as the second camera, N is a natural number, and in this case, the second camera can be one or more, and the second camera selected in this manner is used to synthesize a simulated view, and the simulated view is used to synthesize the second video data.

[0087] S203: Obtain the second video data of the fire object in the first view corresponding to the second camera.

[0088] The second camera determined according to the above first and second manners has a higher view complementarity score, indicating that it can replace the first camera to a better extent, and in this case, the video data captured and photographed by the second camera can be directly used as the second video data to participate in the fire emergency decision processing, which is more efficient.

[0089] In a case where the second camera is determined to have a relatively low complementary score of the visual angle according to the third manner, the third video data of the first simulated visual angle can be synthesized according to the video data (for example, referred to as alternative video data) captured by the second camera, and the second video data of the fire object in the first visual angle is synthesized by using the obtained third video data, wherein the first simulated visual angle is within the shared visual angle range of the at least one second camera corresponding to the alternative video data. Alternatively, the fourth video data of the second simulated visual angle can be synthesized according to the first video data and the at least one alternative video data, and the second video data of the fire object in the first visual angle is synthesized by using the fourth video data, wherein the second simulated visual angle is within the shared visual angle range of the at least one alternative second camera corresponding to the alternative video data and within the overlapping visual angle range of the first visual angle. That is, in a case where the visual angle of each candidate camera is affected by the fire environment (for example, smoke in the fire scene, displacement or damage of the building or camera in the fire scene due to the fire), the video data captured by the candidate camera is not directly used as the alternative video of the first camera, but the video data captured by the second camera with a relatively low complementary score of the visual angle is used for video synthesis of a specific simulated visual angle, so that the video demand of the fire object in the first visual angle can be better met, and the effectiveness and reliability of the fire emergency decision for the fire object are improved. In addition, in order to improve the emergency efficiency and reduce the data processing amount, the key frame images in the alternative video data can be selected for synthesis processing when the video is synthesized.

[0090] S204: performing fire emergency processing according to the first video data and the second video data.

[0091] After obtaining the first video data captured by the first camera group and the second video data corresponding to the second camera, the first video data and the second video data can be visualized and displayed, and further fire emergency processing can be performed to realize timely and reliable fire emergency decision. For example, the video data of different visual angles can be spatially aligned and fused, and then mapped to a unified coordinate system based on accurate position mapping to obtain a view, such as 3D reconstruction, panoramic stitching, bird's eye view generation, and the like, to assist in determining an effective fire emergency decision scheme.

[0092] In the embodiments of the present application, as the fire development continues, the fire development trend of the fire object corresponding to the fire can be predicted, and then the key view angle is determined according to the predicted fire development trend, the key view angle being a view angle relative to the fire object that needs to shoot key video data or a view angle relative to the first camera that is invalid for the fire object; then the backup camera corresponding to the key view angle is determined from the second camera group, and a backup instruction is sent to the backup camera, the backup instruction being used to instruct the backup camera to start acquiring or preparing to acquire the video data of the fire object of the key view angle. That is, according to the change of the fire trend, the key view angle prediction and the second camera preloading can be actively performed, that is, the predictive calling of the second camera is realized, so as to reduce the calling delay of the second camera when it is really needed, improve the video back transmission efficiency, and further improve the fire emergency decision efficiency.

[0093] In addition, after the second video data of the fire object corresponding to the first view angle of the second camera is acquired, the second video data needs to be sent to the system as soon as possible.

[0094] In an implementation manner, the second video data can be controlled to carry a priority transmission identifier, the priority transmission identifier being used to instruct the second video data to be transmitted to the system with high priority, so that the video data of the second camera as a backup can be transmitted to the system as soon as possible to assist in making the fire emergency decision, and the efficiency of the fire emergency decision is improved.

[0095] In another implementation manner, the second video data can be controlled to carry an identifier correspondence relationship between the device identifier of the second camera and the device identifier of the first camera, so that the system can verify the effectiveness of the second video data according to the identifier correspondence relationship. Figure 3 For example, the device identifier of the first camera in the first camera group is "1-2", and the determined device identifier of the second camera is "2-3", and the corresponding relationship between "1-2" and "2-3" can be carried in the reported second video data. By carrying the identifier correspondence relationship between the second camera (the second camera) and the corresponding first camera (the first camera) in the reported second video data, the system can directly verify the second video data through the identifier correspondence relationship between the device identifier of the second camera and the device identifier of the first camera after receiving the second video data, for example, whether the two device identifiers have a position mapping relationship can be verified, and whether the second camera with the device identifier "2-3" is the backup second camera of the first camera as indicated by the system before is verified, which is equivalent to a rough check of the second video data through the identifier correspondence relationship, so as to improve the effectiveness of the second video data.

[0096] The method for fire emergency processing of a converter station based on video calling provided in the embodiments of the present application first acquires first video data sent by a first camera group associated with a fire object in the converter station. The first video data includes video data of multiple perspectives of the fire object respectively photographed by multiple first cameras in the first camera group. In this way, the on-site situation of the fire object can be comprehensively understood through the multi-perspective video data of the fire object, so as to assist in making timely and effective fire emergency decisions. When first video data of a first perspective of the fire object determined according to the first video data does not satisfy an emergency auxiliary decision condition, a first camera that photographs the first video data is determined from the first camera group, and a second camera corresponding to the first camera in position is determined from a second camera group having a position mapping relationship with the first camera group, where the second camera group and the first camera group have the position mapping relationship with the position of the fire object as the same perspective alignment center. Second video data of the fire object of the first perspective corresponding to the second camera is then acquired, so as to make fire emergency decision processing according to the first video data and the second video data. That is, when the video data photographed by a certain camera (i.e., the first camera) in the first camera group from its corresponding perspective (i.e., the first perspective) cannot assist in making fire emergency decisions, the second camera (i.e., the second camera) corresponding to the position of the first camera can be quickly linked as a backup / alternate perspective of the first perspective, so as to quickly acquire alternate video data (i.e., the second video data) that does not satisfy the requirement of the first perspective in the first video data, and then make timely and effective fire emergency decisions according to the alternate video data of the backup / alternate perspective of the first perspective and the first video data of other perspectives. In this way, the video alternate emergency of a certain perspective of the fire object is realized through the quick linkage of the first camera and the second camera, and the timeliness, effectiveness and reliability of the fire emergency processing of the converter station are improved.

[0097] Based on the same inventive concept, the embodiments of the present application provide a device for fire emergency processing of a converter station based on video calling. The device can be a hardware structure, a software module, or a hardware structure plus a software module. The device can be configured in a fire control and management system of a converter station. As shown in Figure 4 The device for fire emergency processing of a converter station based on video calling in the embodiments of the present application includes a first acquisition module 401, a first determination module 402, a second determination module 403, a second acquisition module 404 and a fire emergency processing module 405, where:

[0098] The first acquisition module 401 is configured to acquire first video data sent by a first camera group associated with a fire object in a converter station. The first video data includes video data of multiple perspectives of the fire object respectively photographed by multiple first cameras in the first camera group.

[0099] The first determining module 402 is configured to determine, when the first video data of the first view angle of the fire object determined according to the primary video data does not satisfy the emergency auxiliary decision condition, a first camera that captures the first video data from the primary camera group.

[0100] The second determining module 403 is configured to determine, from a secondary camera group that has a position mapping relationship with the primary camera group, a second camera corresponding to the position of the first camera; wherein the secondary camera group and the primary camera group have a position mapping relationship with the position of the fire object as a same view angle alignment center.

[0101] The second acquiring module 404 is configured to acquire second video data of the fire object of the first view angle corresponding to the second camera.

[0102] The fire emergency processing module 405 is configured to perform fire emergency processing according to the primary video data and the second video data.

[0103] In a possible implementation, the first determining module 402 is configured to perform at least one of the following:

[0104] determine that the definition of the first video data is lower than a definition threshold;

[0105] determine that the resolution of the first video data is lower than a resolution threshold;

[0106] determine that a time length in which a key target object in the first video data is blocked exceeds a predetermined time length;

[0107] determine that a contribution degree of the first video data when jointly performing emergency decision with other video data in the primary video data is less than a contribution degree threshold.

[0108] In a possible implementation, the second determining module 403 is configured to: determine, according to the position of the fire object, the secondary camera group from a candidate camera group that has a position mapping relationship with the primary camera group, wherein one candidate camera group is determined with one fire monitoring position in a shared view angle range of the primary camera group as a view angle alignment center, the shared view angle range of the primary camera group includes at least one fire monitoring position, and the at least one fire monitoring position includes the position of the fire object; and determine, according to the secondary camera group, the second camera corresponding to the position of the first camera.

[0109] In a possible implementation, the second determining module 403 is configured to:

[0110] determine, with the position of the fire object as a view angle alignment center, a reference camera that has a view angle candidate relationship with a camera in the primary camera group;

[0111] obtain basic spatial data of the first camera group and the reference camera, wherein the basic spatial data comprises at least one of position information, height information, angle information, visual angle range information, and environment information of the camera;

[0112] construct a graph neural network model according to the basic spatial data of the first camera group and the reference camera, wherein each camera in the first camera group and the reference camera is a node of the graph neural network model, node features of each node comprise the basic spatial data of the corresponding camera, edges between nodes represent that the cameras corresponding to the nodes have a visual angle complementary relationship, and an edge weight is determined according to at least one of a visual angle complementary range, a relative distance, a line-of-sight reachability, and a historical collaboration effectiveness score between the corresponding cameras;

[0113] determine, by using the graph neural network model, a second camera group from the reference camera according to the edge weight, the second camera group comprising cameras that meet a position mapping relationship with each camera in the first camera group;

[0114] determine a second camera corresponding to the position of the first camera according to the second camera group.

[0115] In a possible implementation, the second determining module 403 is configured to:

[0116] input the position of the first camera, environment information of the first camera, and emergency auxiliary decision demand information into the graph neural network model to obtain at least one candidate camera having a visual angle complementary relationship with the first camera;

[0117] determine a visual angle complementarity score of each candidate camera relative to the first camera, wherein the visual angle complementarity score is determined according to at least one of a visual angle complementary range of the candidate camera relative to the first camera, missing information gain of the candidate camera in the environment information, predicted image quality of the candidate camera, and collaboration feasibility of the candidate camera and the first camera;

[0118] determine a second camera corresponding to the position of the first camera based on the visual angle complementarity score of each candidate camera relative to the first camera.

[0119] In a possible implementation, the second determining module 403 is configured to:

[0120] determine the candidate camera with the highest visual angle complementarity score as the second camera;

[0121] or, determine the candidate camera with a visual angle complementarity score greater than a first score threshold as the second camera;

[0122] Or, in the case where the view angle complementarity scores of the candidate cameras are all less than the second score threshold, the candidate camera with the top N view angle complementarity score is selected as the second camera, wherein the second camera is used to synthesize a simulated view angle, the simulated view angle is used to synthesize the second video data, and N is a natural number.

[0123] In a possible implementation, the second acquisition module 404 is configured to:

[0124] acquire at least one candidate video data of the fire object captured by at least one second camera;

[0125] synthesize third video data of a first simulated view angle according to the at least one candidate video data, and use the third video data as the second video data, wherein the first simulated view angle is within a shared view angle range of the at least one second camera corresponding to the candidate video data; or

[0126] synthesize fourth video data of a second simulated view angle according to the first video data and the at least one candidate video data, and use the fourth video data as the second video data, wherein the second simulated view angle is within the shared view angle range of the at least one second camera corresponding to the candidate video data and within an overlapping view angle range of the first view angle.

[0127] In a possible implementation, the video-based converter station fire emergency processing device in the embodiment of the present application further includes a prediction module, which is configured to:

[0128] predict a fire development trend of the fire object;

[0129] determine a key view angle according to the fire development trend, wherein the key view angle is a view angle relative to the fire object that needs to capture key video data, or the key view angle is a view angle of a primary camera relative to the fire object that fails;

[0130] determine a backup camera corresponding to the key view angle from a secondary camera group, and send a backup instruction to the backup camera, wherein the backup instruction is used to instruct the backup camera to start or prepare to acquire video data of the fire object in the key view angle.

[0131] All related contents of each step involved in the foregoing embodiment of the video-based converter station fire emergency processing method can be cited to the function description of the function module corresponding to the video-based converter station fire emergency processing device in the embodiment of the present application, and will not be repeated here.

[0132] The division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, each function module in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software function module.

[0133] Based on the same inventive concept, the embodiments of the present application further provide a computer storage medium, which can be a computer readable storage medium, and the computer storage medium stores computer instructions or a computer program. When the computer instructions or the computer program run on a computer, the computer executes the steps of the method for handling a converter station fire emergency based on a video call.

[0134] Based on the same inventive concept, the embodiments of the present application further provide a computer program product, that is, each aspect of the method for handling a converter station fire emergency based on a video call provided by the embodiments of the present application can also be implemented in the form of a computer program product, which includes program codes or computer programs. When the computer program product runs on a computer, the program codes or the computer programs are used to make the computer execute the steps of the method for handling a converter station fire emergency based on a video call according to the various exemplary embodiments of the present application.

[0135] Those skilled in the art should understand that the embodiments of the present application can be provided in the form of a method, a system, or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to a magnetic disk storage, a CD-ROM, an optical storage, etc.) containing computer usable program codes.

[0136] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or blocks

[0137] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0138] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0139] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those of skill in the art once they have the benefit of the present disclosure. Therefore, the appended claims are intended to encompass within their scope all possible variations and modifications of the preferred embodiments.

[0140] It is apparent that a person skilled in the art can make a variety of changes and modifications to the application without departing from the spirit and scope of the application. Thus, if these modifications and variations of the application fall within the scope of the claims and their equivalents, it is intended to include them within the scope of the application.

Claims

1. A method for fire emergency response in converter stations based on video recall, characterized in that, The method includes: The system acquires primary video data sent by a primary camera group associated with a fire in the converter station. The primary video data includes video data of the fire from multiple perspectives captured by primary cameras at multiple locations. When the first video data of the fire object from the first perspective, determined based on the first-level video data, does not meet the emergency auxiliary decision-making conditions, a first camera that captures the first video data is determined from the first-level camera group, and a second camera corresponding to the position of the first camera is determined from the second-level camera group that has a positional mapping relationship with the first-level camera group; wherein, the second-level camera group and the first-level camera group have a positional mapping relationship with the fire object's position as the same perspective alignment center. Obtain second video data of the fire object from the first perspective corresponding to the second camera; Fire emergency response is carried out based on the first-level video data and the second-level video data.

2. The method for fire emergency response of converter stations based on video recall according to claim 1, characterized in that, Based on the aforementioned Level 1 video data, it is determined that the first-view video data of the fire target does not meet the emergency auxiliary decision-making conditions, including at least one of the following: It is determined that the resolution of the first video data is lower than the resolution threshold; It is determined that the resolution of the first video data is lower than a resolution threshold; It is determined that the key target object in the first video data is occluded for a duration exceeding a predetermined duration; It is determined that the contribution of the first video data to joint emergency decision-making with other video data in the first-level video data is less than the contribution threshold.

3. The method for fire emergency response of converter stations based on video recall according to claim 1, characterized in that, Determining the second camera corresponding to the position of the first camera based on the second camera group that has a positional mapping relationship with the first camera group includes: Based on the location of the fire object, the secondary camera group is determined from the candidate camera group that has a positional mapping relationship with the primary camera group. A candidate camera group is determined with a fire monitoring position within the shared field of view of the primary camera group as the center of view. The shared field of view of the primary camera group includes at least one fire monitoring position, and the at least one fire monitoring position includes the location of the fire object. The second camera corresponding to the position of the first camera is determined based on the secondary camera group.

4. The method for fire emergency response of converter stations based on video recall according to claim 1, characterized in that, Determining the second camera corresponding to the position of the first camera based on the second camera group that has a positional mapping relationship with the first camera group includes: Using the location of the fire object as the center of view, determine a reference camera that has a viewpoint candidate relationship with the cameras in the first-level camera group; Acquire basic spatial data of the primary camera group and the reference camera, wherein the basic spatial data includes at least one of the following: camera position information, height information, angle information, field of view information, and environment information of the camera. A graph neural network model is constructed based on the basic spatial data of the first-level camera group and the reference camera. Each camera in the first-level camera group and the reference camera serves as a node in the graph neural network model. The node features of each node include the basic spatial data of the corresponding camera. The edges between nodes indicate that there is a viewpoint candidate relationship between the cameras corresponding to that node. The edge weights are determined based on at least one of the following: viewpoint candidate range, relative distance, line-of-sight accessibility, and historical collaborative effectiveness score between the corresponding cameras. Using the graph neural network model, a second-level camera group is formed by determining, based on the edge weights, cameras from the reference cameras that satisfy the position mapping relationship with each camera in the first-level camera group; The second camera corresponding to the position of the first camera is determined based on the secondary camera group.

5. The converter station fire emergency response method based on video recall according to claim 4, characterized in that, Determining the second camera corresponding to the position of the first camera based on the secondary camera group includes: The location of the first camera, the environmental information of the first camera, and the emergency auxiliary decision-making requirements are input into the graph neural network model to obtain at least one candidate camera that has a viewpoint candidate relationship with the first camera. Determine the view complementarity score of each candidate camera relative to the first camera, wherein the view complementarity score is determined based on at least one of the following: the view candidate range of the candidate camera relative to the first camera, the missing information gain of the candidate camera under the environmental information, the predicted image quality of the candidate camera, and the cooperative feasibility of the candidate camera and the first camera. The second camera corresponding to the position of the first camera is determined based on the complementarity score of the viewpoints of each candidate camera relative to the first camera.

6. The converter station fire emergency response method based on video recall according to claim 5, characterized in that, Determining the second camera corresponding to the position of the first camera based on the view complementarity score of each candidate camera relative to the first camera includes: The candidate camera with the highest viewpoint complementarity score was selected as the second camera; Alternatively, candidate cameras whose viewpoint complementarity scores are greater than the first score threshold can be identified as the second camera; Alternatively, if the view complementarity scores of all candidate cameras are less than the second score threshold, the top N candidate cameras with the highest view complementarity scores are selected as the second camera. The second camera is used to synthesize a simulated viewpoint, which is used to synthesize the second video data, and N is a natural number.

7. The method for fire emergency response of converter stations based on video recall according to claim 6, characterized in that, Acquiring second video data of the fire object from the first perspective corresponding to the second camera includes: Acquire at least one alternative video data of the fire target captured by the at least one second camera; A third video data representing a first simulated perspective is synthesized based on the at least one candidate video data, and this third video data is used as the second video data, wherein the first simulated perspective is within the shared viewpoint range of the candidate video data captured by the at least one second camera; or... A fourth video data of a second simulated perspective is synthesized based on the first video data and the at least one alternative video data, and the fourth video data is used as the second video data, wherein the second simulated perspective is within the shared perspective range of the alternative video data captured by the at least one second camera and the overlapping perspective range of the first perspective.

8. The method for fire emergency response of converter stations based on video recall according to claim 1, characterized in that, The method further includes: Predict the development trend of the fire at the target location; The key perspective is determined based on the fire development trend, wherein the key perspective is the perspective from which key video data needs to be captured relative to the fire object, or the key perspective is the perspective from the perspective of a primary camera that has failed relative to the fire object. A backup camera corresponding to the key viewpoint is determined from the secondary camera group, and a preparation instruction is sent to the backup camera. The preparation instruction is used to instruct the backup camera to start or prepare to acquire video data of the fire object from the key viewpoint.

9. The method for fire emergency response of converter stations based on video recall according to claim 1, characterized in that, The fire emergency decision-making module is used to acquire second video data of the fire object from the first perspective captured by the second camera, including: Control the identification correspondence between the device identifier of the second camera and the device identifier of the first camera carried in the second video data, and verify the validity of the second video data according to the identification correspondence; And / or, The control includes carrying a priority transmission identifier in the second video data, which indicates that the second video data should be transmitted to the converter station digital fire control system with high priority.

10. A video-based fire emergency response device for converter stations, characterized in that, The device includes: The first acquisition module is used to acquire first-level video data sent by the first-level camera group associated with the fire object in the converter station. The first-level video data includes video data of the fire object from multiple perspectives captured by the first-level cameras at multiple locations. The first determining module is used to determine, from the first-level camera group, the first camera that captured the first video data when the first video data of the first perspective of the fire object determined according to the first-level video data does not meet the emergency auxiliary decision-making conditions. The second determining module is used to determine a second camera corresponding to the position of the first camera from a second-level camera group that has a positional mapping relationship with the first-level camera group; wherein the second-level camera group and the first-level camera group have a positional mapping relationship with the same viewing angle center as the position of the fire object; The second acquisition module is used to acquire second video data of the fire object from the first perspective corresponding to the second camera; The fire emergency response module is used to perform fire emergency response based on the first-level video data and the second-level video data.

11. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed, implements the steps of the video-based emergency response method for converter stations as described in any one of claims 1-9.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed, implements the steps of the video-based emergency response method for converter stations as described in any one of claims 1-9.

Images