A method, device, electronic equipment and medium for initial fire detection
By analyzing smoke concentration and historical alarm counts to determine risk levels, and utilizing drone inspections, the accuracy and timeliness of initial fire detection in ancient building sites have been addressed, thus improving fire response efficiency.
Patent Information
- Application Number
- CN202410487023.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-22
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2044-04-22
AI Technical Summary
In ancient buildings, gardens, or scenic areas, fires spread rapidly, and existing smoke detectors have long response times, lacking effective means for early fire detection.
By acquiring smoke concentration values and historical alarm counts in multiple areas within the ancient building site, analyzing the trend and rate of concentration changes, determining the risk level, and controlling drones to inspect high-risk areas, precise detection is achieved by combining monitoring video, temperature measurement, and wind direction information.
It enables accurate and timely detection of fires in their early stages, reducing response time and improving the efficiency and safety of fire response.
Smart Images

Figure CN118379844B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of fire detection, and in particular to a method, apparatus, electronic device, and medium for early fire detection. Background Technology
[0002] In ancient architectural gardens or scenic areas, fires are prone to occur due to the large number of visitors and the predominantly wooden construction. Currently, multiple smoke detectors are typically installed in these sites to detect fires. When the smoke concentration becomes too high, the detectors are triggered, and staff then extinguish the fire. However, because many of these sites contain wooden structures, fires spread rapidly. The long response time for staff during initial fire suppression is a significant drawback. Therefore, early fire suppression is crucial, but currently, effective methods for detecting fires in their early stages are lacking. Thus, how to more accurately and promptly detect fires in their initial stages remains a challenge. Summary of the Invention
[0003] To more accurately and promptly detect fires in their early stages, this application provides a method, apparatus, electronic device, and medium for early fire detection.
[0004] Firstly, this application provides a method for initial fire detection, employing the following technical solution:
[0005] A method for initial fire detection includes:
[0006] Obtain smoke concentration values in multiple areas within the ancient building site and the historical alarm count for each area;
[0007] Based on the smoke concentration value, the concentration change trend and concentration change rate of each area are determined, and the concentration change trend includes increasing, decreasing and remaining unchanged.
[0008] If there are suspicious areas with an increasing trend, the risk level of the suspicious area is determined based on the concentration change rate of the suspicious area and the number of historical alarms in the suspicious area;
[0009] If a target suspicious area is found with a risk level that reaches a preset threshold, the drone will be controlled to inspect the target suspicious area.
[0010] By adopting the above technical solution, obtaining smoke concentration values and historical alarm counts for multiple areas facilitates understanding the current smoke situation in each area and the number of times alarms were triggered due to excessively high fire concentrations in the past. Based on the current smoke concentration value, the trend and rate of change of smoke concentration in each area can be determined, which facilitates subsequent analysis and judgment of the early stage of fire development based on the concentration change area and the concentration change rate. An increase in the change area indicates the presence of a fire point in the area. The concentration change rate and the number of historical alarms are important factors affecting whether there is a fire point in the area. Therefore, the risk level of suspicious areas can be accurately determined based on the concentration change rate and the number of historical alarms. Based on the risk level, it is possible to accurately distinguish whether there is a fire in the early stage of development in each area. Areas without fires in the early stage of development are excluded according to the preset level threshold, resulting in target suspicious areas with fires in the early stage of development. Controlling drones to inspect the target suspicious areas can more accurately and timely detect fires in the early stage of development.
[0011] In another possible implementation, determining the risk level of the suspected area based on the concentration change rate of the suspected area and the historical number of alarms in the suspected area includes:
[0012] The alarm time for reaching the preset concentration threshold is determined based on the smoke concentration value, the rate of concentration change, and the preset concentration threshold.
[0013] The first score of the suspicious area is determined based on the concentration change rate, the number of historical alarms, the alarm time, and their respective first coefficients.
[0014] The target score interval where the first score is located is determined from multiple preset score intervals, and the preset risk level corresponding to the target score interval is determined as the risk level of the suspicious area. Each preset score interval has a preset risk level.
[0015] In another possible implementation, each area comprises multiple sub-areas, and the controlled drone inspects the target suspicious area, including:
[0016] Obtain surveillance video of the suspicious area within the target region;
[0017] The number of people in each sub-area is determined based on the surveillance video;
[0018] The proportion of ancient buildings in each sub-region is determined based on a pre-set site map;
[0019] The second score for each sub-region is determined based on the number of people, the proportion of ancient buildings, and their respective second coefficients.
[0020] The multiple sub-regions are sorted from largest to smallest based on the second score;
[0021] The flight path of the UAV within the suspected target area is determined based on the sorting results;
[0022] The drone is controlled to perform inspections based on the flight path.
[0023] In another possible implementation, the method further includes:
[0024] Obtain the temperature values of the suspicious areas collected during the drone inspection process;
[0025] If a target sub-region is detected where the temperature value reaches a preset temperature threshold, then the total number of times the preset temperature threshold is reached within the target sub-region is obtained.
[0026] If the total number of attempts reaches a preset threshold and there are no fire-fighting facilities in the target sub-area, then the first prompt message will be output.
[0027] In another possible implementation, the method further includes:
[0028] Acquire historical surveillance videos of each area within a preset time period;
[0029] The total number of people in each area is determined based on the historical surveillance video.
[0030] The third score for each region is determined based on the proportion of ancient buildings, the total number of people, the number of historical alarms in each region, and their respective third coefficients.
[0031] The inspection frequency for each area is determined based on the third score.
[0032] In another possible implementation, the method further includes:
[0033] Obtain wind direction information;
[0034] The suspected target area is determined to be the target area covered by the upwind direction of the wind direction information;
[0035] Once the drone has completed its inspection of the suspicious target area, control the drone to inspect the target area.
[0036] In another possible implementation, the method further includes:
[0037] If the smoke concentration in any area reaches a preset concentration threshold and no alarm signal is received from the smoke alarm in that area, a second prompt message will be output.
[0038] Secondly, this application provides a fire initial detection device, which adopts the following technical solution:
[0039] A fire early detection device, comprising:
[0040] The data acquisition module is used to acquire smoke concentration values in multiple areas within the ancient building site and the historical number of alarms for each area;
[0041] The data determination module is used to determine the concentration change trend and concentration change rate of each area based on the smoke concentration value, wherein the concentration change trend includes increasing, decreasing, and remaining unchanged.
[0042] The risk level determination module is used to determine the risk level of a suspicious area based on the concentration change rate of the suspicious area and the number of historical alarms in the suspicious area when there is a suspicious area with an increasing trend.
[0043] The first control module is used to control the drone to inspect the target suspicious area when there is a target suspicious area whose risk level reaches a preset level threshold.
[0044] By adopting the above technical solution, the data acquisition module obtains smoke concentration values and historical alarm counts for multiple areas, which facilitates understanding the current smoke situation in each area and the number of times alarms were triggered due to excessively high fire concentrations in the past. The data determination module can determine the trend and rate of change of smoke concentration in each area based on the current smoke concentration value, which facilitates subsequent analysis and judgment of the early stage of fire development based on the concentration change area and concentration change rate. An increase in the change area indicates the presence of a fire point in the area. The concentration change rate and the number of historical alarms are important factors affecting whether there is a fire point in the area. Therefore, the risk level determination module can accurately determine the risk level of the suspicious area based on the concentration change rate and the number of historical alarms. Based on the risk level, it can accurately distinguish whether there is a fire in the early stage of development in each area. Areas without fires in the early stage of development are excluded according to the preset level threshold, resulting in target suspicious areas with fires in the early stage of development. The first control module controls the drone to inspect the target suspicious areas, thereby enabling more accurate and timely detection of fires in the early stage of development.
[0045] In another possible implementation, when determining the risk level of a suspicious area based on the concentration change rate of the suspicious area and the number of historical alarms in the suspicious area, the risk level determination module is specifically used for:
[0046] The alarm time for reaching the preset concentration threshold is determined based on the smoke concentration value, the rate of concentration change, and the preset concentration threshold.
[0047] The first score of the suspicious area is determined based on the concentration change rate, the number of historical alarms, the alarm time, and their respective first coefficients.
[0048] The target score interval where the first score is located is determined from multiple preset score intervals, and the preset risk level corresponding to the target score interval is determined as the risk level of the suspicious area. Each preset score interval has a preset risk level.
[0049] In another possible implementation, each region includes multiple sub-regions, and the first control module, when controlling the drone to inspect the target suspicious region, is specifically used for:
[0050] Obtain surveillance video of the suspicious area within the target region;
[0051] The number of people in each sub-area is determined based on the surveillance video;
[0052] The proportion of ancient buildings in each sub-region is determined based on a pre-set site map;
[0053] The second score for each sub-region is determined based on the number of people, the proportion of ancient buildings, and their respective second coefficients.
[0054] The multiple sub-regions are sorted from largest to smallest based on the second score;
[0055] The flight path of the UAV within the suspected target area is determined based on the sorting results;
[0056] The drone is controlled to perform inspections based on the flight path.
[0057] In another possible implementation, the device further includes:
[0058] The temperature acquisition module is used to acquire the temperature value of the suspicious area collected during the inspection of the UAV;
[0059] The count acquisition module is used to acquire the total number of times the preset temperature threshold is reached within the target sub-region when a target sub-region is detected to have a temperature value that reaches the preset temperature threshold.
[0060] The first output module is used to output a first prompt message when the total number of times reaches a preset threshold and there are no fire-fighting facilities in the target sub-area.
[0061] In another possible implementation, the device further includes:
[0062] The surveillance video acquisition module is used to acquire historical surveillance videos of each area within a preset time period.
[0063] The total number of personnel module is used to determine the total number of personnel in each area based on the historical surveillance video.
[0064] The scoring module is used to determine the third score for each region based on the proportion of ancient buildings, the total number of people, the number of historical alarms in each region, and their respective third coefficients.
[0065] The inspection frequency determination module is used to determine the inspection frequency of each area based on the third score.
[0066] In another possible implementation, the device further includes:
[0067] The wind direction acquisition module is used to acquire wind direction information;
[0068] The target area determination module is used to determine the target area covered by the wind direction information upwind of the suspected target area;
[0069] The second control module is used to control the drone to inspect the target area after it is detected that the drone has completed its inspection of the suspicious area.
[0070] In another possible implementation, the device further includes:
[0071] The second output module is used to output a second prompt message when the smoke concentration value in any area reaches a preset concentration threshold and no alarm signal is received from the smoke alarm in any area.
[0072] Thirdly, this application provides an electronic device that adopts the following technical solution:
[0073] An electronic device comprising:
[0074] At least one processor;
[0075] Memory;
[0076] At least one application, wherein the application is stored in memory and configured to be executed by at least one processor, the at least one configuration being for: executing a fire initial detection method as shown in any possible implementation of the first aspect.
[0077] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:
[0078] A computer-readable storage medium that, when the computer program is executed in a computer, causes the computer to perform a fire initial detection method as described in any one of the first aspects.
[0079] In summary, this application includes at least one of the following beneficial technical effects:
[0080] Obtaining smoke concentration values and historical alarm counts from multiple areas facilitates understanding the current smoke conditions in each area and the number of times alarms were triggered due to excessively high fire concentrations in the past. Based on the current smoke concentration value, the trend and rate of change of smoke concentration in each area can be determined, which facilitates subsequent analysis and judgment of the early stages of fire development based on the concentration change area and rate of change. An increase in the change area indicates the presence of a fire point in the area. The concentration change rate and the number of historical alarms are both important factors affecting whether there is a fire point in the area. Therefore, the risk level of suspicious areas can be accurately determined based on the concentration change rate and the number of historical alarms. Based on the risk level, it is possible to accurately identify whether there is a fire in the early stages of development in each area. Areas without fires in the early stages of development are excluded according to preset level thresholds, resulting in target suspicious areas with fires in the early stages of development. Controlling drones to inspect the target suspicious areas can more accurately and timely detect fires in the early stages of development. Attached Figure Description
[0081] Figure 1 This is a flowchart illustrating an early fire detection method according to an embodiment of this application.
[0082] Figure 2 This is a schematic diagram illustrating the specific process for determining the risk level in the embodiments of this application.
[0083] Figure 3 This is a schematic diagram illustrating the specific process of controlling the drone inspection in the embodiments of this application.
[0084] Figure 4 This is an example diagram of the flight path in the embodiments of this application.
[0085] Figure 5 This is a flowchart illustrating the process of outputting the first prompt message in an embodiment of this application.
[0086] Figure 6 This is a flowchart illustrating the process of determining the inspection frequency in an embodiment of this application.
[0087] Figure 7 This is a schematic diagram of the structure of a fire early detection device according to an embodiment of this application.
[0088] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0089] The present application will be further described in detail below with reference to the accompanying drawings.
[0090] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.
[0091] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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 some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0092] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.
[0093] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.
[0094] This application provides a method for initial fire detection, executed by an electronic device. This electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method includes steps S101, S102, S103, and S104, wherein,
[0095] S101, obtain the smoke concentration values of multiple areas within the ancient building site and the historical number of alarms for each area.
[0096] In this embodiment of the application, in ancient building complexes or gardens, the site can be divided into multiple areas. After dividing into multiple areas, staff can install smoke sensors and smoke alarms at the center of each area. The smoke sensor can monitor the smoke concentration in the air in real time, and the smoke alarm can be a stand-alone audible and visual smoke detection alarm. If the smoke alarm does not have the function of real-time smoke concentration monitoring, it can still sound an alarm when the smoke concentration reaches a preset threshold. Therefore, the smoke sensor can be integrated into the smoke alarm, and the integrated smoke alarm can be installed at the center of the area. Both the smoke sensor and the smoke alarm are connected to electronic equipment via wires or wirelessly. The smoke sensor collects the smoke concentration value, which is then acquired by the electronic equipment.
[0097] After a smoke alarm in each area goes off, the electronic device records and accumulates the number of alarms in each area and stores it in the local storage medium within the electronic device, so that the electronic device can obtain the historical number of alarms for each area.
[0098] S102, determine the concentration change trend and concentration change rate of each area based on the smoke concentration value.
[0099] The concentration change trends include increasing, decreasing, and remaining unchanged.
[0100] In this embodiment, since the smoke concentration value is acquired in real time, a coordinate system for the smoke concentration value changing over time can be preset within the electronic device. After acquiring the smoke concentration value, the electronic device combines the time of acquisition to form coordinate points and maps them onto the preset coordinate system. Then, the electronic device performs linear fitting on the coordinate points to obtain a linear function. The trend of concentration change is determined based on the sign of the slope of the linear function: a positive slope indicates an increasing trend, a negative slope indicates a decreasing trend, and no slope indicates no change. The rate of concentration change is then determined based on the magnitude of the slope. The electronic device determines the concentration change trend and rate of concentration change for each region using the above method.
[0101] S103. If there are suspicious areas with an increasing trend, the risk level of the suspicious area is determined based on the concentration change rate of the suspicious area and the number of historical alarms in the suspicious area.
[0102] In this embodiment of the application, if the concentration change trend in a certain area is increasing, it indicates that there may be a ignition point in that area, i.e., the area is a suspected area. The greater the rate of concentration change, the higher the probability of fire in that area, and vice versa. The more historical alarms a region has, the more frequently smoke concentrations exceed the standard, indicating a higher probability of fire. Therefore, the probability of a fire occurring in that area at present is higher, and vice versa. In other words, the rate of concentration change and the number of historical alarms are both important factors affecting whether a fire will occur in a region. Therefore, the risk level of a suspected area can be accurately determined based on the rate of concentration change and the number of historical alarms.
[0103] S104: If there is a target suspicious area with a risk level that reaches the preset threshold, control the drone to inspect the target suspicious area.
[0104] In this embodiment of the application, the higher the risk level, the greater the possibility of a fire, and vice versa. Staff can set a preset risk level threshold in the electronic device. The preset risk level threshold serves as the dividing point between whether the risk level is too high. After the electronic device determines the risk level of a suspicious area, it compares it with the preset risk level threshold. If the preset risk level threshold is reached, it indicates that the area is more likely to experience a fire. Therefore, the electronic device controls a drone to inspect the target suspicious area, thereby more accurately and promptly detecting the ignition point in the early stages of a fire, facilitating staff to respond in the early stages of a fire, and reducing economic losses and casualties.
[0105] One possible implementation of this application embodiment involves determining the risk level of a suspicious area in step S103 based on the concentration change rate and the historical alarm count of the suspicious area. Specifically, this includes steps S1031, S1032, and S1033. Figure 2 As shown, where,
[0106] S1031, based on the smoke concentration value, the rate of concentration change and the preset concentration threshold, determine the alarm time when the preset concentration threshold is reached.
[0107] In this embodiment, the preset concentration threshold is the threshold for determining the occurrence of a fire; when the preset concentration threshold is reached, the smoke alarm will sound. Therefore, the electronic device determines the alarm time when the preset concentration threshold is reached based on the current smoke concentration value, the rate of change of concentration, and the preset concentration threshold. Specifically, the electronic device calculates the difference between the preset concentration threshold and the smoke concentration value, and then divides the difference by the rate of change of concentration to obtain the alarm time. A shorter alarm time indicates a more urgent situation in the suspected area and a faster fire progression, which also affects the risk level of the suspected area.
[0108] S1032, the first score of the suspicious area is determined based on the concentration change rate, the number of historical alarms, the alarm time, and the corresponding first coefficient.
[0109] In this embodiment of the application, the concentration change rate, the number of historical alarms, and the alarm time are all key factors affecting the risk level of the area, and the degree of influence of the above three factors is different. Therefore, different first coefficients are set for the above three factors. Assuming that the first coefficient for the concentration change rate is 0.7, the first coefficient for the number of historical alarms is 0.5, and the first coefficient for the alarm time is -0.2, since the correlation between alarm time and risk level is inversely proportional, the first coefficient for alarm time is negative.
[0110] Assume a concentration change rate of 8 ppm / s in a suspected area, 10 historical alarms, and an alarm duration of 30 seconds. The electronic equipment determines the first score for this suspected area as 8 × 0.7 + 10 × 0.5 + 30 × (-0.07) = 8.5. It should be noted that this first coefficient can be adaptively adjusted according to actual conditions and needs.
[0111] S1033, determine the target score interval where the first score is located from multiple preset score intervals, and determine the preset risk level corresponding to the target score interval as the risk level of the suspicious area.
[0112] Each preset score range corresponds to a preset risk level.
[0113] In this embodiment, staff can determine the preset score ranges and the risk level corresponding to each preset score range in advance through experiments or calculations, and then store the preset score ranges and corresponding risk levels in the local storage medium of the electronic device. After the electronic device determines the first score of the suspicious area, it determines the preset score range that the first score hits, i.e., the target score range, and determines the risk level corresponding to the target score range as the risk level of the suspicious area.
[0114] For example, there are five preset score intervals: (0, 3], (3, 6], (6, 9], (9, 12], and (12, +∞). Each corresponds to a risk level of Level 1, Level 2, Level 3, Level 4, and Level 5. Taking step S1032 as an example, the first score for the suspected area falls within the (6, 9] interval, therefore the risk level for this suspected area is Level 3. By utilizing the factors most influential on fire risk and applying the first score to the preset score intervals, the determination of the risk level becomes more intuitive and accurate.
[0115] One possible implementation of this application embodiment is that each area includes multiple sub-areas. In step S104, the drone is controlled to inspect the suspected target area, specifically including steps S1041, S1042, S1043, S1044, S1045, S1046, and S1047, as follows. Figure 3 As shown, where,
[0116] S1041, Obtain surveillance video of the suspicious area of the target.
[0117] In this embodiment of the application, the surveillance video can be collected by surveillance camera devices within the area, or by surveillance cameras in other areas capturing video of the target suspicious area. Therefore, a more detailed understanding of the situation within the target suspicious area is possible, resulting in more complete information. The surveillance camera devices within the ancient building site are all connected to electronic devices via wires or wirelessly, facilitating the acquisition of surveillance video by the electronic devices.
[0118] S1042, determine the number of people in each sub-area based on surveillance video.
[0119] In this embodiment of the application, after the electronic device acquires the surveillance video, it can input the video into a trained network model for personnel feature recognition, thereby obtaining the personnel features within the target suspicious area and the location of the personnel features. Then, combined with a preset location map within the electronic device, the sub-region where each personnel feature is located is determined, and the number of personnel in each sub-region is obtained. Specifically, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models.
[0120] S1043, determine the proportion of ancient buildings in each sub-region based on the preset site map.
[0121] In this embodiment of the application, the preset site map can be an aerial view of the ancient building site. The staff stores the preset site map in an electronic device, and then the electronic device inputs the preset site map into a trained network model for recognition, thereby marking the outline of the ancient building on the preset site map. Then, the preset site map is divided according to multiple regions to obtain the outline of the ancient building in each region. Since each region is composed of multiple sub-regions, the preset site map part corresponding to each region is further divided according to the sub-regions to obtain the outline of the ancient building in each sub-region. The ratio of the ancient building outline to the area of the sub-region can be used to obtain the proportion of the ancient building, or the number of pixels in the outline of the ancient building and the number of pixels in the sub-region can be determined, and then the ratio of the number of pixels in the outline of the ancient building to the number of pixels in the sub-region can be used to obtain the proportion of the ancient building.
[0122] In another implementation, edge detection can be performed on a preset site map to obtain the edge outline of the ancient buildings, and then the ancient buildings can be divided according to the region and sub-regions to obtain the proportion of the ancient buildings.
[0123] S1044, the second score for each sub-region is determined based on the number of people, the proportion of ancient buildings, and their respective second coefficients.
[0124] In this embodiment, the greater the number of people and the higher the proportion of ancient buildings, the higher the importance of the sub-region, and vice versa. That is, both the number of people and the proportion of ancient buildings are key factors affecting the importance of a sub-region, and their influence varies. Therefore, different second coefficients can be set for the number of people and the proportion of ancient buildings. Assuming the second coefficient for the number of people is 0.8 and the second coefficient for the proportion of ancient buildings is 7, and a sub-region has 8 people and 0.6 ancient buildings, the electronic device determines the second score of this sub-region as 8 × 0.8 + 0.6 × 7 = 10.6. Quantifying the importance of a sub-region by calculating the second score is more accurate and intuitive. The electronic device calculates the second score for each sub-region using the above method to obtain the score for each sub-region. The second coefficients can be adaptively modified according to actual conditions or needs.
[0125] S1045, sort multiple sub-regions from largest to smallest based on the second score.
[0126] In this embodiment of the application, after the electronic device determines the second score of each sub-region, it sorts the multiple sub-regions within each target suspicious region from largest to smallest, that is, sorts them according to importance, to facilitate subsequent processing. Assuming that the target suspicious region consists of nine 3×3 sub-regions, the second scores of the nine sub-regions are then sorted.
[0127] S1046, Determine the flight path of the UAV within the suspected target area based on the sorting results.
[0128] In this embodiment of the application, after the electronic device determines the sorting result, it determines the flight path of the drone based on the sorting result, that is, the order in which the drone inspects the target suspicious area. Taking step S1045 as an example, assuming the sorted order of the nine sub-areas is 3, 9, 5, 6, 2, 1, 4, 7, and 8, the drone will inspect according to this order. Figure 4 As shown.
[0129] S1047, a drone used for inspection based on flight path control.
[0130] In this embodiment, the location coordinates of the center of each sub-region represent the location of the sub-region. Staff can determine the center coordinates of each sub-region within the ancient building site in advance using a GPS positioning device. After determining the flight route, the electronic device generates control commands based on the geographic coordinates of the suspected target location, the location coordinates of each sub-region within the suspected target area, the location coordinates of each sub-region, and the flight route. These control commands are then transmitted to the drone via wired or wireless means. Upon receiving the control commands, the drone flies and inspects according to the commands, prioritizing inspections based on importance, thereby improving inspection efficiency and effectiveness and enabling more timely fire detection. It should be noted that the drone is equipped with an infrared thermometer or other non-contact thermometer to collect the highest temperature value within each sub-region and transmit it to the electronic device. When a sub-region's temperature value reaches a preset temperature threshold, the electronic device, combined with the sub-region number or location that reached the preset temperature threshold, sends a notification to the staff's terminal device, ensuring timely notification.
[0131] One possible implementation of this application embodiment includes steps S1, S2, and S3, such as... Figure 5 As shown, step S1 can be performed after step S104.
[0132] S1, acquire the temperature value of the suspicious area collected during the drone inspection.
[0133] In this embodiment of the application, the drone is equipped with an infrared temperature measuring device or other type of non-contact temperature measuring device. During its flight path inspection, the drone collects temperature values for each sub-region and transmits them to an electronic device for acquisition. The temperature value represents the highest temperature within the sub-region.
[0134] S2, if a target sub-region with a temperature value reaching a preset temperature threshold is detected, then the total number of times the preset temperature threshold is reached within the target sub-region is obtained.
[0135] In this embodiment of the application, after the electronic device obtains the temperature value within a sub-region, it compares the temperature value with a preset temperature threshold. The preset temperature threshold is the dividing point between whether the temperature within the sub-region is too high. Assuming the preset temperature threshold is 65°C, and the obtained temperature value of a certain sub-region is 70°C, the electronic device compares 70°C with 65°C. If the preset temperature threshold is reached, then the sub-region is the target sub-region. During inspection, when the temperature of a sub-region reaches the preset temperature threshold, the electronic device records and stores each instance of reaching the preset temperature threshold, thereby enabling the electronic device to obtain the total number of times the target sub-region reaches the preset temperature threshold. Assuming that a certain target sub-region reaches the preset temperature threshold 5 times.
[0136] S3. If the total number of attempts reaches the preset threshold and there are no fire-fighting facilities in the target sub-area, the first prompt message will be output.
[0137] In this embodiment of the application, the preset number threshold is the dividing point between whether the temperature value in the target sub-region reaches the preset temperature threshold too many times. After the electronic device obtains the total number of times the preset temperature threshold is reached, it compares the total number of times with the preset number threshold. Taking step S2 as an example, assuming the preset number is 3 times, the electronic device compares 5 times with 3 times. Since the preset number threshold is reached 3 times, it means that the temperature value in the target sub-region reaches the preset temperature threshold too many times, and the fire hazard is relatively large.
[0138] The electronic device stores a preset location map with the locations of fire-fighting facilities marked on it. The electronic device determines whether there are suitable facilities in the target sub-area based on the preset location map and the distribution of fire-fighting facilities. If there are no facilities, it means that the area is not convenient for immediate fire fighting in the event of a fire. Therefore, the electronic device outputs the first prompt message. The first prompt message can be combined with the location and number of the target sub-area, and then combined with the text message "lacking fire-fighting facilities" to send the location or number of the target sub-area to the terminal device of the relevant staff so that the relevant staff can promptly improve the fire-fighting facilities.
[0139] One possible implementation of this application embodiment includes steps Sa, Sb, Sc, and Sd, wherein step Sa can be executed after step S101, such as... Figure 6 As shown, where,
[0140] Sa retrieves historical surveillance videos for each area within a preset time period.
[0141] In this embodiment of the application, the preset time period can be the past three days, the past seven days, etc. The electronic device is connected to all surveillance camera devices within the premises via wired or wireless means. Surveillance video in a certain area may be covered by surveillance camera devices in other areas. Therefore, staff can determine the correspondence between each area and a surveillance camera in advance based on the distribution and coverage of the surveillance cameras. The electronic device acquires surveillance video in a certain area, and based on the correspondence between that area and the surveillance cameras, it can obtain historical surveillance video of the area captured by the specified surveillance camera.
[0142] Sb determines the total number of people in each area based on historical surveillance video.
[0143] In this embodiment of the application, the electronic device can input historical surveillance videos into a trained network model for personnel identification, obtain the number of people in the historical surveillance videos of each surveillance camera, and then sum the number of people in the historical surveillance videos of all surveillance cameras to obtain the total number of people. The total number of people represents the popularity of the area; the higher the total number of people, the higher the popularity of the area, and the higher the importance of the area, and vice versa.
[0144] Sc is determined by the proportion of ancient buildings, the total number of people, the number of historical alarms in each region, and the corresponding third coefficient to determine the third score of each region.
[0145] In this embodiment, the proportion of ancient buildings, the total number of people, and the number of historical alarms all indicate the importance of a region, and these three factors have different levels of importance. Therefore, different third coefficients are set for these three factors. For example, the third coefficient for the proportion of ancient buildings is 0.8, the third coefficient for the total number of people is 0.06, and the third coefficient for the number of historical alarms is 0.5. If a region has a proportion of ancient buildings of 0.7, a total number of people of 200, and 7 historical alarms, the electronic equipment determines the region's third score to be 0.7 × 5 + 200 × 0.06 + 7 × 0.7 = 20.4. Calculating the third score quantifies the importance of each region, and the score provides a more specific and accurate representation.
[0146] Sd determines the inspection frequency for each area based on the third score.
[0147] In this embodiment of the application, after the third score is determined, the staff can set multiple preset score intervals in advance. Each preset score interval corresponds to an inspection frequency. After the electronic device determines the preset score interval in which the third score is located, it can determine the inspection frequency corresponding to the interval as the inspection frequency of that area. By determining the inspection frequency through the third score, the inspection frequency set according to the importance of each interval is more suitable and fits better, thus improving inspection efficiency.
[0148] One possible implementation of this application embodiment includes steps one, two, and three, wherein step one can be executed after step S104.
[0149] Step 1: Obtain wind direction information.
[0150] Step two: Determine the target area that is covered by the upwind direction of the wind direction information, which is the area of suspicion.
[0151] Step 3: Once the drone has completed its inspection of the suspicious area, control the drone to inspect the target area.
[0152] In this embodiment, the drone is equipped with a wind direction sensor to collect wind direction information, or the electronic device obtains the current wind direction information through an internet cloud server. Smoke in the suspected target area may originate from a fire point in the upwind area and flow along the wind direction to the suspected target area. However, if the smoke sensors and smoke alarms in the upwind area malfunction or are abnormal, the electronic device cannot identify the upwind area as the suspected target area. The electronic device determines the target area covered by the upwind direction based on the wind direction information and a preset location map, indicating that the target area has a certain risk of fire. When the electronic device detects that the drone has completed its inspection of the last sub-area in the sorted results within the suspected target area, the electronic device generates an instruction to inspect the target area and sends it to the drone. Upon receiving the instruction, the drone begins to inspect the upwind target area, thereby improving the inspection effect, further enabling timely detection of early fires, and making the inspection more accurate.
[0153] One possible implementation of this application embodiment includes the following steps after step S101:
[0154] If the smoke concentration in any area reaches the preset concentration threshold and no alarm signal is received from the smoke alarm in any area, a second prompt message will be output.
[0155] In this embodiment, the smoke alarm sounds when the ambient smoke concentration reaches a preset threshold. Therefore, the smoke alarm can be calibrated using a smoke sensor. After the electronic device acquires the smoke concentration value of a certain area, it compares the smoke concentration values. If the smoke concentration value of a certain area reaches the preset threshold, and the electronic device does not acquire any alarm information from the smoke alarm in that area, it indicates that the smoke alarm in that area is abnormal. The electronic device outputs a second prompt message, which, combined with the location or number of the area and the text message "Smoke alarm is abnormal," is sent to the terminal device of relevant personnel. This allows relevant personnel to promptly detect the abnormality of the smoke alarm and perform maintenance.
[0156] The above embodiments describe a method for initial fire detection from the perspective of process flow. The following embodiments describe an initial fire detection device from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.
[0157] This application provides a fire initial detection device 20, such as... Figure 7 As shown, the initial fire detection device 20 may specifically include:
[0158] Data acquisition module 201 is used to acquire smoke concentration values in multiple areas within the ancient building site and the historical number of alarms in each area;
[0159] The data determination module 202 is used to determine the concentration change trend and concentration change rate of each area based on the smoke concentration value. The concentration change trend includes increasing, decreasing and remaining unchanged.
[0160] The risk level determination module 203 is used to determine the risk level of a suspicious area based on the concentration change rate of the suspicious area and the number of historical alarms in the suspicious area when there is a suspicious area with an increasing trend.
[0161] The first control module 204 is used to control the drone to inspect the target suspicious area when there is a target suspicious area with a risk level that reaches a preset level threshold.
[0162] This application discloses a fire initial detection device 20. The data acquisition module 201 acquires smoke concentration values and historical alarm counts for multiple areas to understand the current smoke situation in each area and the number of times alarms were triggered due to excessively high fire concentrations in the past. The data determination module 202 determines the trend and rate of change of smoke concentration in each area based on the current smoke concentration value, which facilitates subsequent analysis and judgment of the initial stage of fire development based on the concentration change area and concentration change rate. An increase in the change area indicates the presence of a fire point in the area. The concentration change rate and the number of historical alarms are important factors affecting whether there is a fire point in the area. Therefore, the risk level determination module 203 can accurately determine the risk level of the suspicious area based on the concentration change rate and the number of historical alarms. Based on the risk level, it can accurately distinguish whether there is a fire in the initial stage in each area. Areas without fire in the initial stage are excluded according to a preset level threshold to obtain the target suspicious area with fire in the initial stage. The first control module 204 controls a drone to inspect the target suspicious area to detect the fire in the initial stage more accurately and timely.
[0163] In one possible implementation of this application embodiment, when determining the risk level of a suspicious area based on the concentration change rate of the suspicious area and the historical alarm count of the suspicious area, the risk level determination module 203 is specifically used for:
[0164] The alarm time for reaching the preset concentration threshold is determined based on the smoke concentration value, the rate of concentration change, and the preset concentration threshold.
[0165] The first score of the suspicious area is determined based on the concentration change rate, the number of historical alarms, the alarm time, and the corresponding first coefficient.
[0166] The target score interval where the first score is located is determined from multiple preset score intervals. The preset risk level corresponding to the target score interval is determined as the risk level of the suspicious area. Each preset score interval has a preset risk level.
[0167] In one possible implementation of this application embodiment, each region includes multiple sub-regions. When the first control module 204 controls the drone to inspect the target suspicious region, it is specifically used for:
[0168] Obtain surveillance video of the suspicious area within the target region;
[0169] The number of people in each sub-area is determined based on surveillance video.
[0170] The proportion of ancient buildings in each sub-region is determined based on a pre-set site map;
[0171] The second score for each sub-region is determined based on the number of people, the proportion of ancient buildings, and their respective second coefficients.
[0172] Sort multiple sub-regions from largest to smallest based on the second score;
[0173] The flight path of the UAV within the suspected target area is determined based on the ranking results;
[0174] Drones are used for inspections based on flight paths.
[0175] In one possible implementation of this application embodiment, the apparatus 20 further includes:
[0176] The temperature acquisition module is used to acquire temperature values in suspicious areas collected during drone inspections.
[0177] The count acquisition module is used to acquire the total number of times the preset temperature threshold is reached within the target sub-region when a target sub-region is detected to have a temperature value that reaches the preset temperature threshold.
[0178] The first output module is used to output the first prompt information when the total number of times reaches the preset number of times threshold and there are no fire-fighting facilities in the target sub-area.
[0179] In one possible implementation of this application embodiment, the apparatus 20 further includes:
[0180] The surveillance video acquisition module is used to acquire historical surveillance videos of each area within a preset time period.
[0181] The total number of personnel determination module is used to determine the total number of personnel in each area based on historical surveillance video.
[0182] The scoring module is used to determine the third score for each region based on the proportion of ancient buildings, the total number of people, the number of historical alarms in each region, and their respective third coefficients.
[0183] The inspection frequency determination module is used to determine the inspection frequency of each area based on the third score.
[0184] In one possible implementation of this application embodiment, the apparatus 20 further includes:
[0185] The wind direction acquisition module is used to acquire wind direction information;
[0186] The target area determination module is used to determine the target area covered by the wind direction information upwind of the suspected target area;
[0187] The second control module is used to control the drone to inspect the target area after it is detected that the drone has completed its inspection of the suspicious area.
[0188] In one possible implementation of this application embodiment, the apparatus 20 further includes:
[0189] The second output module is used to output a second prompt message when the smoke concentration value in any area reaches a preset concentration threshold and no alarm signal is received from the smoke alarm in any area.
[0190] In the embodiments of this application, the first control module 204 and the second control module can be the same control module or different control modules. The first output module and the second output module can be the same output module or different output modules.
[0191] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the fire initial detection device 20 described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0192] This application provides an electronic device, such as... Figure 8 As shown, Figure 8 The illustrated electronic device 30 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 30 does not constitute a limitation on the embodiments of this application.
[0193] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0194] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0195] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.
[0196] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.
[0197] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0198] This application provides a computer-readable storage medium storing a computer program. When the program is run on a computer, it enables the computer to execute the corresponding content in the aforementioned method embodiments. Compared with related technologies, this application provides an embodiment that obtains smoke concentration values and historical alarm counts for multiple areas, facilitating the understanding of the current smoke conditions in each area and the number of times alarms were triggered due to excessively high fire concentrations in the past. Based on the current smoke concentration value, the trend and rate of change of smoke concentration in each area can be determined, which facilitates subsequent analysis and judgment of the early stages of fire development based on the concentration change area and the concentration change rate. An increase in the change area indicates the presence of a fire point in the area. The concentration change rate and the number of historical alarm counts are important factors affecting the presence of a fire point in the area. Therefore, the risk level of a suspicious area can be accurately determined based on the concentration change rate and the number of historical alarm counts. Based on the risk level, it is possible to accurately distinguish whether there is a fire in the early stages of development in each area. Areas without fires in the early stages of development are excluded according to a preset level threshold, resulting in target suspicious areas with fires in the early stages of development. Controlling a drone to inspect the target suspicious areas can more accurately and promptly detect fires in the early stages of development.
[0199] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.
[0200] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A method for initial fire detection, characterized in that, include: Obtain smoke concentration values in multiple areas within the ancient building site and the historical alarm count for each area; Based on the smoke concentration value, the concentration change trend and concentration change rate of each area are determined, and the concentration change trend includes increasing, decreasing and remaining unchanged. If there are suspicious areas with an increasing trend, the risk level of the suspicious area is determined based on the concentration change rate of the suspicious area and the number of historical alarms in the suspicious area; If a target suspicious area is found with a risk level that reaches a preset threshold, the drone will be controlled to inspect the target suspicious area. Each region includes multiple sub-regions, and the controlled drone inspects the suspected target region, including: Obtain surveillance video of the suspicious area within the target region; The number of people in each sub-area is determined based on the surveillance video; The proportion of ancient buildings in each sub-region is determined based on a pre-set site map; The second score for each sub-region is determined based on the number of people, the proportion of ancient buildings, and their respective second coefficients. The multiple sub-regions are sorted from largest to smallest based on the second score; The flight path of the UAV within the suspected target area is determined based on the sorting results; The drone is controlled to perform inspections based on the flight path.
2. The method for initial fire detection according to claim 1, characterized in that, The method of determining the risk level of a suspicious area based on the concentration change rate of the suspicious area and the historical alarm count of the suspicious area includes: The alarm time for reaching the preset concentration threshold is determined based on the smoke concentration value, the rate of concentration change, and the preset concentration threshold. The first score of the suspicious area is determined based on the concentration change rate, the number of historical alarms, the alarm time, and their respective first coefficients. The target score interval where the first score is located is determined from multiple preset score intervals, and the preset risk level corresponding to the target score interval is determined as the risk level of the suspicious area. Each preset score interval has a preset risk level.
3. The method for initial fire detection according to claim 1, characterized in that, The method further includes: Obtain the temperature values of the suspicious areas collected during the drone inspection process; If a target sub-region is detected where the temperature value reaches a preset temperature threshold, then the total number of times the preset temperature threshold is reached within the target sub-region is obtained. If the total number of attempts reaches a preset threshold and there are no fire-fighting facilities in the target sub-area, then the first prompt message will be output.
4. The method for initial fire detection according to claim 1, characterized in that, The method further includes: Acquire historical surveillance videos of each area within a preset time period; The total number of people in each area is determined based on the historical surveillance video. The third score for each region is determined based on the proportion of ancient buildings, the total number of people, the number of historical alarms in each region, and their respective third coefficients. The inspection frequency for each area is determined based on the third score.
5. The method for initial fire detection according to claim 1, characterized in that, The method further includes: Obtain wind direction information; The suspected target area is determined to be the target area covered by the upwind direction of the wind direction information; Once the drone has completed its inspection of the suspicious target area, control the drone to inspect the target area.
6. The method for initial fire detection according to claim 1, characterized in that, The method further includes: If the smoke concentration in any area reaches a preset concentration threshold and no alarm signal is received from the smoke alarm in that area, a second prompt message will be output.
7. A fire initial detection device, characterized in that, include: The data acquisition module is used to acquire smoke concentration values in multiple areas within the ancient building site and the historical number of alarms for each area; The data determination module is used to determine the concentration change trend and concentration change rate of each area based on the smoke concentration value, wherein the concentration change trend includes increasing, decreasing, and remaining unchanged. The risk level determination module is used to determine the risk level of a suspicious area based on the concentration change rate of the suspicious area and the number of historical alarms in the suspicious area when there is a suspicious area with an increasing trend. The first control module is used to control the drone to inspect the target suspicious area when there is a target suspicious area with a risk level that reaches a preset level threshold. Each region includes multiple sub-regions, and the controlled drone inspects the suspected target region, including: Obtain surveillance video of the suspicious area within the target region; The number of people in each sub-area is determined based on the surveillance video; The proportion of ancient buildings in each sub-region is determined based on a pre-set site map; The second score for each sub-region is determined based on the number of people, the proportion of ancient buildings, and their respective second coefficients. The multiple sub-regions are sorted from largest to smallest based on the second score; The flight path of the UAV within the suspected target area is determined based on the sorting results; The drone is controlled to perform inspections based on the flight path.
8. An electronic device, characterized in that, It includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, the at least one application being used to perform a fire initial detection method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in the computer, the computer is instructed to perform a method for initial fire detection as described in any one of claims 1 to 6.
Citation Information
Patent Citations
Fire monitoring method and device and edge computing device
CN109686036A
Ancient architectural complex fire hazard alarming method and device based on unmanned aerial vehicle, and storage medium
CN110084992A
Fire emergency response method, device and system
CN111754715A
