Risk area identification methods, systems, electronic devices, and readable storage devices

Abstract

This application discloses a method, system, electronic device, and computer-readable storage device for determining a risk area. The method includes: acquiring monitoring images from at least two monitoring devices of the same height and the position information of each monitoring device in a world coordinate system; upon identifying smoke in the monitoring images, obtaining the initial position information of the smoke in the world coordinate system based on the position information of the monitoring devices; obtaining the area of ​​the smoke and its tilt direction in the world coordinate system based on the monitoring images, the initial position information, and the position information of each monitoring device; and generating a fire risk area based on the initial position information, tilt direction, and area of ​​the smoke. Through the above method, this application can determine the area from which a fire can spread.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, system, electronic device, and computer-readable storage device for determining risk areas. Background Technology

[0002] In recent years, the frequency of forest fires has been gradually increasing. Forest fires not only reduce biodiversity but also produce smoke pollution, harming the atmospheric environment and further impacting the climate, posing a serious threat to human survival. Therefore, forest fire prevention has become a crucial aspect of field forest firefighting efforts. Because the density of trees in forests makes fires difficult to detect, most fires are already quite large by the time they become observable. Even after a fire has started, predicting its spread is just as important as detecting it. Predicting the area of ​​fire spread allows for the delineation of relatively accurate evacuation zones, reducing potential losses and aiding in fire suppression decisions, enabling targeted firefighting operations based on the spread area. Typically, fire monitoring relies on video surveillance, which lacks the capability to determine the extent of fire spread. Summary of the Invention

[0003] The main objective of this application is to provide a method, system, electronic device, and computer-readable storage device for determining risk areas, which can solve the technical problem of how to determine the area of ​​fire spread.

[0004] To address the aforementioned technical problems, the first technical solution adopted in this application is: providing a method for determining a risk area. This method includes: acquiring monitoring images from at least two monitoring devices of the same height and the position information of each monitoring device in a world coordinate system; upon identifying smoke in the monitoring images, obtaining the initial position information of the smoke in the world coordinate system based on the position information of the monitoring devices; obtaining the area of ​​the smoke and its tilt direction in the world coordinate system based on the monitoring images, the initial position information, and the position information of each monitoring device; and generating a fire risk area based on the initial position information, tilt direction, and area of ​​the smoke.

[0005] To address the aforementioned technical problems, the second technical solution adopted in this application is to provide a risk area determination system. This system includes at least two monitoring devices and a data processing device. The monitoring devices are at the same height in the world coordinate system. The data processing device is communicatively connected to the monitoring devices to obtain their monitoring images, thus implementing the method described in the first technical solution.

[0006] To address the aforementioned technical problems, the third technical solution adopted in this application is to provide an electronic device. This electronic device includes a memory and a processor. The memory stores program data, which can be executed by the processor to implement the method described in the first technical solution.

[0007] To address the aforementioned technical problems, the fourth technical solution adopted in this application is to provide a computer-readable storage device. This computer-readable storage device stores program data and can be executed by a processor to implement the method described in the first technical solution.

[0008] The beneficial effects of this application are as follows: At least two video surveillance devices at the same height are used to capture and monitor the location of the fire. Based on the acquired surveillance footage and the location information of the monitoring devices, the initial location of the smoke, i.e., the initial location of the fire, is determined. Furthermore, based on the acquired initial location of the smoke, the location of the monitoring devices, and the image information of the smoke in the surveillance footage, the tilt direction of the smoke in the real environment and the area of ​​the smoke in the image are determined. The size of the smoke area in the image can, to a certain extent, reflect the size of the fire. Therefore, the risk area for fire spread is ultimately determined based on the initial location, tilt direction, and area of ​​the smoke. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating the first embodiment of the risk area determination method of this application;

[0011] Figure 2 This is a flowchart illustrating the second embodiment of the risk area determination method of this application;

[0012] Figure 3 This is a flowchart illustrating the third embodiment of the risk area determination method of this application;

[0013] Figure 4 This is a flowchart illustrating the fourth embodiment of the risk area determination method of this application;

[0014] Figure 5 This is a flowchart illustrating the fifth embodiment of the risk area determination method of this application;

[0015] Figure 6 This is a schematic diagram for obtaining the tilt direction of the smoke;

[0016] Figure 7 This is a schematic diagram of the surveillance footage;

[0017] Figure 8 This is a flowchart illustrating the sixth embodiment of the risk area determination method of this application;

[0018] Figure 9 This is a schematic diagram illustrating the acquisition of risk areas;

[0019] Figure 10 This is a detailed and complete flowchart of risk acquisition method one;

[0020] Figure 11 This is a schematic diagram of the structure of an embodiment of the risk area determination system of this application;

[0021] Figure 12 This is a schematic diagram of the structure of an embodiment of the electronic device of this application;

[0022] Figure 13 This is a schematic diagram of the structure of an embodiment of the computer-readable storage device of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0024] The terms "first," "second," etc., used in this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0025] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0026] Reference Figure 1 , Figure 1This is a flowchart illustrating the first embodiment of the risk area determination method of this application. It includes the following steps:

[0027] S11: Obtain the monitoring images of at least two monitoring devices with the same height and the position information of each monitoring device in the world coordinate system.

[0028] In forest fire prevention zones, at least two monitoring devices at the same height are installed, capable of monitoring and capturing images of forests and other areas from a high vantage point. The images captured are sent to a data processing center and processed along with the corresponding location information of the monitoring devices in the world coordinate system to obtain relevant data for determining fire risk areas. The location information of the monitoring devices in the world coordinate system, i.e., their geographical location in the real world, is subsequently used in the process of determining the location and size of fires.

[0029] S12: When smoke is detected in the monitoring screen, the initial position information of the smoke in the world coordinate system is obtained based on the position information of the monitoring equipment.

[0030] The monitoring footage pushed to the data processing center will undergo smoke detection based on deep learning algorithms. When smoke is detected in the monitoring footage, the initial position information of the smoke in the world coordinate system will be further obtained, which is equivalent to the location information of the fire occurrence point.

[0031] In one embodiment, monitoring images from two devices at the same height are acquired, and smoke is identified in both images. Based on the determined location information of the two monitoring devices, a binocular positioning algorithm is used to determine the initial spatial position of the smoke relative to the monitoring devices. Furthermore, by combining the height of the monitoring devices, the initial position information of the smoke in the world coordinate system is calculated.

[0032] S13: Based on the monitoring screen, initial location information, and location information of each monitoring device, obtain the area of ​​the smoke and its tilt direction in the world coordinate system.

[0033] Having determined the initial position of the smoke in the world coordinate system, the tilt direction of the smoke in the real environment can be determined based on the location information of the monitoring equipment and the direction of the smoke in the monitoring screen. Based on the initial position information of the smoke in the world coordinate system and the location information of the monitoring equipment, the smoke area information detected in the monitoring screen corresponding to the monitoring equipment can be processed to obtain multiple smoke area information. The smoke area can then be further determined based on these multiple smoke area information. The obtained smoke area can reflect the size of the fire to a certain extent.

[0034] S14: Generate a fire risk zone based on the initial location information, tilt direction, and area of ​​the smoke.

[0035] After determining the direction of the smoke's tilt, the size of the risk area can be determined based on the area of ​​the smoke. Based on the initial position information of the smoke, the direction of the smoke's tilt and the size of the risk area are matched to finally obtain the fire risk area corresponding to the detected smoke.

[0036] In this embodiment, at least two video surveillance devices at the same height are used to capture and monitor the location of the fire. Based on the acquired surveillance footage and the location information of the monitoring devices, the initial location of the smoke, i.e., the initial location of the fire, is determined. Furthermore, based on the acquired initial location of the smoke, the location of the monitoring devices, and the image information of the smoke in the surveillance footage, the tilt direction of the smoke in the real environment and the area of ​​the smoke in the image are determined. The size of the smoke area in the image can, to a certain extent, reflect the size of the fire. Therefore, the risk area for fire spread is ultimately determined based on the initial location, tilt direction, and area of ​​the smoke.

[0037] Reference Figure 2 , Figure 2 This is a flowchart illustrating a second embodiment of the method for determining the risk area of ​​this application. This method is a further extension of step S13. It includes the following steps:

[0038] S21: Obtain the target detection box corresponding to the smoke in each monitoring screen.

[0039] During the process of deep learning algorithms detecting smoke in surveillance footage, corresponding pixels identified as smoke and target detection boxes surrounding those pixels are obtained in the surveillance footage.

[0040] S22: Determine the tilt direction of the smoke based on the location information, initial location information of each monitoring device, and coordinate information of the target detection box in each monitoring screen.

[0041] The coordinates of the target detection box in the monitoring screen reflect its tilt direction; that is, the target detection box information includes tilt angle information, which is equivalent to reflecting the tilt direction of the smoke in the monitoring screen. Given the location information of the monitoring equipment and the initial location information of the smoke, combining the tilt direction of the smoke in each monitoring screen allows us to obtain the actual tilt direction of the smoke in the environment.

[0042] S23: Determine the area of ​​the smoke based on the location information, initial location information, and area information of the target detection box in each monitoring screen.

[0043] Because the initial horizontal distance between the smoke's location and different monitoring devices may vary, the smoke data captured by each device—that is, the area information of the target detection box—will differ in their respective monitoring screens. Therefore, given the location information of the monitoring devices and the initial location information of the smoke, the distance is determined based on the location information. The area information of the corresponding target detection box is then processed based on the distance between the monitoring devices and the initial smoke location to ensure that the area information of the target detection boxes in each monitoring screen is under the same standard, facilitating subsequent determination of the smoke's area in the standard screen.

[0044] Reference Figure 3 , Figure 3 This is a flowchart illustrating a third embodiment of the method for determining the risk area of ​​this application. This method is a further extension of step S23. It includes the following steps:

[0045] S31: Obtain the area information of the target detection box in each monitoring screen.

[0046] In the process of deep learning algorithms detecting smoke in surveillance footage, the corresponding pixels identified as smoke and the bounding boxes surrounding those pixels are obtained from the footage. This allows the determination of the area information of the bounding boxes.

[0047] S32: Based on the positional relationship between the positional information of each monitoring device and the initial positional information of the smoke, adjust the area information of the target detection box in each monitoring screen to obtain the area information in the standard screen.

[0048] Because the initial horizontal distance between the smoke's location and different monitoring devices may vary, the smoke data captured by each device—that is, the area information of the target detection box—will differ across their respective monitoring screens. Therefore, given the location information of the monitoring devices and the initial location of the smoke, the distance is determined based on the location information. The area information of the corresponding target detection box is then processed based on the distance between the monitoring devices and the initial smoke location to ensure that the area information of the target detection boxes in each monitoring screen is under the same standard, resulting in multiple area information data for the same smoke under a standard screen.

[0049] S33: Determine the area of ​​smoke in the standard frame based on all adjusted area information.

[0050] After processing the area information of smoke in the monitoring screens of different monitoring devices according to the distance information, the numerical difference is not significant. Therefore, the area information is usually averaged. The average of all the area information data obtained under the standard screen is used as the area of ​​smoke in the standard screen.

[0051] In one embodiment, if the area information of the target detection box in the monitoring screen is less than a preset threshold, then no processing is required on the area information of the target detection box in the monitoring screen. When the area information of the target detection box in the monitoring screen is too small, processing it to the area information under the standard screen may result in a significant difference between the obtained area information and other obtained area information. This is because the original data is too small, and the amplified data result obtained after processing may have a large error compared with the actual data result. Therefore, before adjusting the area information of the target detection box in the monitoring screen, the area information data of the target detection box in the monitoring screen that is less than the preset threshold can be removed and not processed.

[0052] Reference Figure 4 , Figure 4 This is a flowchart illustrating the fourth embodiment of the risk area determination method for this application. This method is a further extension of step S32. It includes the following steps:

[0053] S41: Based on the location information of each monitoring device and the initial location information of the smoke, obtain the target distance between each monitoring device and the smoke.

[0054] S42: Using a preset distance as a benchmark, determine the ratio of each target distance to the preset distance.

[0055] S43: Based on the ratio, adjust the area information of the target detection box in the corresponding monitoring screen to obtain the area information in the standard screen corresponding to the preset distance.

[0056] After obtaining the location information of the monitoring equipment and the initial location information of the smoke, the target distance between the monitoring equipment and the initial location of the smoke can be calculated by combining the height of the monitoring equipment. The target distance is compared with a preset distance, and the ratio is used as the benchmark for adjusting the area information.

[0057] For example, the initial location of the smoke is 100 meters away from the target of the first monitoring device and 200 meters away from the target of the second monitoring device. The area information of the target detection box in the monitoring screen of the first monitoring device is the first area, and the area information of the target detection box in the monitoring screen of the second monitoring device is the second area. The monitoring screens captured by the first and second monitoring devices are images with the same resolution. Using 100 meters as the preset distance, the initial location of the smoke is 100 meters away from the target of the first monitoring device, and the ratio of this distance to the preset distance is 1. Therefore, the area information of the target detection box in the monitoring screen of the first monitoring device is also the same in the standard image, which is the first area. However, the initial location of the smoke is 200 meters away from the target of the second monitoring device, and the ratio of this distance to the preset distance is 1 / 2. Therefore, dividing the area information of the target detection box in the monitoring screen of the second monitoring device by this ratio yields the area information in the standard image, which is twice the second area. This example of area information and ratio adjustment is merely illustrative and does not limit the adjustment methods of this application.

[0058] The preset distance can be set individually beforehand as described above, or it can be determined based on the target distance between the monitoring device and the initial position of the smoke. For example, if the initial position of the smoke is 100 meters away from the target distance of the first monitoring device and 200 meters away from the target distance of the second monitoring device, then the distance between the initial position of the smoke and the first monitoring device is used as the preset distance. In this case, the monitoring screen of the first monitoring device is equivalent to the standard screen, and the area information of the target detection boxes in the monitoring screens of other monitoring devices is adjusted and converted to the area information in the standard screen.

[0059] When obtaining the area information in the standard image, all the area information is processed, such as by taking the average value to obtain the final area information indicating the size of the smoke.

[0060] Based on the coordinates of the target detection box in the monitoring screen, its size, the distance between the monitoring device and the initial position of the smoke, and the focal length, an area corresponding to the target detection box can be obtained as area information. The above calculation process can be implemented using deep learning algorithms, and will not be described in detail here.

[0061] Reference Figure 5 , Figure 5 This is a flowchart illustrating the fifth embodiment of the risk area determination method for this application. This method is a further extension of step S22. It includes the following steps:

[0062] S51: Determine the undetermined tilt direction of the smoke based on the coordinate information of the target detection box in each monitoring screen.

[0063] Based on the coordinate information of the target detection box in the monitoring screen, the tilt direction of the target detection box in the monitoring screen can be determined. This tilt direction is used as the undetermined tilt direction for subsequent determination of the tilt direction of the smoke in the world coordinate system.

[0064] S52: Determine the tilt direction of the smoke based on each undetermined tilt direction, the position information of the monitoring device corresponding to the monitoring screen, and the initial position information.

[0065] By determining the tilt direction of the smoke in the monitoring image, and combining this with the location information of the corresponding monitoring equipment and the initial position information of the smoke, the tilt direction of the smoke in the world coordinate system can be further determined. When the monitoring equipment is monitoring and capturing images of the smoke, its field of view is oriented directly towards the initial position of the smoke.

[0066] In one embodiment, reference is made to Figure 6 , Figure 6 This diagram illustrates the direction of smoke inclination. Circles represent surveillance cameras, and triangles represent the initial position of the smoke, which can be equated to the location of the fire. Based on the positions of the surveillance cameras and the initial smoke position, four distinct areas can be identified. (Example...) Figure 7 As shown, Figure 7 This is a schematic diagram of a monitoring screen. In the monitoring screen of monitoring camera 1, the target detection box, i.e., the smoke, is tilted to the right. In the monitoring screen of monitoring camera 2, the smoke is tilted to the left. Combining the positions of monitoring camera 1 and monitoring camera 2 with the initial position of the smoke, it can be determined that the actual tilting direction of the smoke is from the initial position towards the position of area 2.

[0067] Similarly, if the smoke tilts to the right in the monitoring footage of camera 1, and also tilts to the right in the monitoring footage of camera 2, then it can be determined that the actual tilt direction of the smoke is from the initial position towards the position of area 3.

[0068] Refer to the diagram. Figure 8 This is a flowchart illustrating the sixth embodiment of the risk area determination method for this application. This method is a further extension of step S14. It includes the following steps:

[0069] S61: Generate several areas based on the initial location information of the smoke and the location information of the monitoring equipment.

[0070] A line drawn between the initial location of the smoke and the location of the monitoring equipment can divide the area near the fire into multiple sections. (Refer to...) Figure 9 , Figure 9 This diagram illustrates the risk areas. Circles represent surveillance cameras, and triangles represent the initial location of the smoke, which can be considered the location of the fire. Based on the locations of the surveillance cameras and the initial smoke location, four distinct areas can be identified.

[0071] S62: Determine a potential risk area from several regions based on the tilt direction.

[0072] Based on the target detection box, i.e. the tilt direction of the smoke in the monitoring screen, the tilt direction of the smoke in the actual environment can be determined, and a potential risk area can be identified accordingly.

[0073] For example, if the target detection box (i.e., the smoke) tilts to the right in the monitoring screen of camera 1, and tilts to the left in the monitoring screen of camera 2, by combining the positions of camera 1 and camera 2 with the initial position of the smoke, it can be determined that the actual tilt direction of the smoke is from the initial position towards the position of region 2. Region 2 is the undetermined risk area.

[0074] S63: Determine a risk radius based on area.

[0075] After obtaining the area of ​​the smoke in the standard image, the area is matched against a preset database to determine a risk radius corresponding to the area.

[0076] S64: Generate a risk area by combining the undetermined risk area and the risk radius.

[0077] By combining the undetermined risk area and the risk radius, a risk area can be generated based on the initial position of the smoke.

[0078] Reference Figure 9 The risk radius R was determined based on the calculated smoke area. Then, four sector-shaped regions were obtained, centered on the initial smoke location. Sector 2, located within the undetermined risk region 2, was determined as the final risk region.

[0079] The following specific embodiment will be used to illustrate the complete process of the risk area determination method of this application in detail.

[0080] Reference Figure 10 , Figure 10 This is a detailed and complete flowchart of risk acquisition method one.

[0081] First, two visible light binocular PTZ cameras capable of horizontal scanning and cruising are installed at the same height in two different locations in the field. The cameras are used in cruise mode to sample and monitor the forest scene, and the geographical locations of the two cameras can be obtained at the same time.

[0082] After acquiring the camera's monitoring footage, a deep learning algorithm is used to detect the footage and obtain the area and tilt direction of the target detection boxes. A neural network detector with multiple convolutional, downsampling, and pooling layers is used. Cross-entropy is employed for target category classification, and logistic regression is used to obtain the position, area, and tilt direction of the target's detection box. Thus, the area of ​​smoke in the standard image and its tilt direction in the world coordinate system can be obtained using the method described in the above embodiments. The area of ​​smoke in the standard image is then matched against a preset database to obtain a corresponding risk radius.

[0083] Simultaneously, a binocular localization algorithm is used to obtain the initial spatial position of the smoke relative to the camera, and the geographical location of the fire's origin is further calculated based on the camera's height. Based on the geographical location of the fire's origin and the geographical locations of the two cameras, four zones can be identified.

[0084] Finally, by combining the tilt direction of the smoke with the divided area, a risk area can be determined. By further combining the risk radius, a risk sector can be obtained.

[0085] like Figure 11 As shown, Figure 11 This is a schematic diagram of the structure of an embodiment of the risk area determination system of this application.

[0086] The risk area determination system includes at least two monitoring devices 10 and a data processing device 11. The monitoring devices 10 are located in the area requiring fire monitoring and are at the same altitude in the world coordinate system. The data processing device 11 is communicatively connected to the monitoring devices 10 to obtain data information such as monitoring images transmitted by the monitoring devices 10. The data processing device 11, through its communicative connection with the monitoring devices 10, implements the method provided by any embodiment and possible combinations of the risk area determination method described above.

[0087] like Figure 12 As shown, Figure 12 This is a schematic diagram of the structure of an embodiment of the electronic device of this application.

[0088] The electronic device includes a processor 110 and a memory 120.

[0089] Processor 110 controls the operation of electronic devices. Processor 110 may also be referred to as a CPU (Central Processing Unit). Processor 110 may be an integrated circuit chip with signal sequence processing capabilities. Processor 110 may also be a general-purpose processor, a digital signal sequence processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0090] The memory 120 stores the instructions and program data required for the processor 110 to operate.

[0091] The processor 110 is used to execute instructions to implement the methods provided by any embodiment and possible combination of the loop closure detection optimization method described above in this application.

[0092] like Figure 13 As shown, Figure 13 This is a schematic diagram of the structure of an embodiment of the computer-readable storage device of this application.

[0093] One embodiment of the readable storage device of this application includes a memory 210 that stores program data, which, when executed, implements the method provided by any embodiment and possible combinations of the loop closure detection optimization method of this application.

[0094] The memory 210 may include a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or other media that can store program instructions. Alternatively, it may be a server that stores the program instructions, which can send the stored program instructions to other devices for execution or execute the stored program instructions itself.

[0095] In summary, at least two video surveillance devices at the same height are used to monitor the location of the fire. Based on the acquired surveillance footage and the location information of the monitoring devices, the initial location of the smoke, i.e., the initial location of the fire, is determined. Furthermore, based on the initial location of the smoke, the location of the monitoring devices, and the image information of the smoke in the surveillance footage, the direction of the smoke's movement in the real environment and the area of ​​the smoke in the image are determined. The size of the smoke area in the image can, to some extent, reflect the size of the fire. Therefore, the risk area for fire spread is ultimately determined based on the initial location, direction of movement, and area of ​​the smoke.

[0096] Compared to some methods that use large amounts of data to build local databases for modeling, this application only needs to use a small amount of data to build a database for estimating the risk radius, and combine the data from the monitoring screen to obtain the initial position and tilt direction of the smoke, thereby determining a fire spread risk area.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0098] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0099] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0100] If the integrated units in the other embodiments described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for determining risk areas, characterized in that, The method includes: Acquire monitoring images from at least two monitoring devices at the same height, as well as the position information of each monitoring device in the world coordinate system; When smoke is detected in the monitoring screen, the initial position information of the smoke in the world coordinate system is obtained based on the position information of the monitoring device. Based on the monitoring screen, the initial location information, and the location information of each monitoring device, the area of ​​the smoke and its tilt direction in the world coordinate system are obtained. A fire risk zone is generated based on the initial location information of the smoke, the tilt direction, and the area. The step of obtaining the area of ​​the smoke based on the monitoring screen, the initial location information, and the location information of each monitoring device includes: Obtain the target detection box corresponding to the smoke in each of the aforementioned monitoring screens; Based on the location information of each monitoring device, the initial location information, and the coordinate information of the target detection box in each monitoring screen, the tilt direction of the smoke is determined; The step of determining the tilt direction of the smoke based on the location information of each monitoring device, the initial location information, and the coordinate information of the target detection box in each monitoring screen includes: The undetermined tilt direction of the smoke is determined based on the coordinate information of the target detection box in each of the monitoring screens; The tilt direction of the smoke is determined based on each of the proposed tilt directions, the location information of the monitoring device corresponding to the monitoring screen, and the initial location information.

2. The method according to claim 1, characterized in that, The method of obtaining the tilt direction of the smoke in the world coordinate system based on the monitoring screen, the initial location information, and the location information of each monitoring device includes: Obtain the target detection box corresponding to the smoke in each of the aforementioned monitoring screens; The area of ​​the smoke is determined based on the location information of each monitoring device, the initial location information, and the area information of the target detection box in each monitoring screen.

3. The method according to claim 2, characterized in that, The determination of the smoke area based on the location information of each monitoring device, the initial location information, and the area information of the target detection box in each monitoring screen includes: Obtain the area information of the target detection box in each of the aforementioned monitoring screens; Based on the positional relationship between the positional information of each monitoring device and the initial positional information of the smoke, the area information of the target detection box in each monitoring screen is adjusted to obtain the area information in the standard screen. The area of ​​the smoke in the standard image is determined based on all adjusted area information.

4. The method according to claim 3, characterized in that, The method of adjusting the area information of the target detection box in each monitoring screen based on the positional relationship between the position information of each monitoring device and the initial position information of the smoke to obtain the area information in the standard screen includes: Based on the location information of each monitoring device and the initial location information of the smoke, the target distance between each monitoring device and the smoke is obtained; Using a preset distance as a benchmark, determine the ratio of each target distance to the preset distance; Based on the ratio, the area information of the target detection box in the corresponding monitoring screen is adjusted to obtain the area information in the standard screen corresponding to the preset distance.

5. The method according to claim 1, characterized in that, The risk zone for generating a fire based on the initial location information of the smoke, the tilt direction, and the area includes: Several areas are generated based on the initial location information of the smoke and the location information of the monitoring device; Based on the tilt direction, a potential risk area is determined from the plurality of areas; A risk radius is determined based on the area; The risk area is generated by combining the undetermined risk area and the risk radius.

6. The method according to claim 5, characterized in that, Determining a risk radius based on the area includes: The risk radius corresponding to the area is determined by matching the area in a preset database.

7. A risk area determination system, characterized in that, include: At least two monitoring devices, wherein the monitoring devices are at the same height in the world coordinate system; A data processing device, which is communicatively connected to the monitoring device, to obtain the monitoring screen of the monitoring device and implement the method as described in any one of claims 1-6.

8. An electronic device, characterized in that, It includes a memory and a processor, the memory being used to store program data, the program data being executable by the processor to implement the method as described in any one of claims 1-6.

9. A computer-readable storage device, characterized in that, It stores program data and can be executed by a processor to implement the method as described in any one of claims 1-6.

Images