Alarm system and method based on face recognition

Abstract

The invention discloses an alarm system based on face recognition and a method thereof, and relates to the technical field of face recognition, and the alarm system comprises a disaster area face information acquisition module, a land trapped person analysis module, a water surface trapped person analysis module, a rescue scheduling processing module and a local database. For trapped persons in a land area and a water surface area, influences of environments and body data of the trapped persons are considered, the trapped persons in the water surface area are rescued preferentially, and under the condition that the number of rescue workers is not enough, the preferential rescue workers in the water surface area are screened, and the unmanned aerial vehicle is used for cooperative delivery of materials. The occurrence rate of irreversible body injuries of trapped persons is reduced, and meanwhile, the nutrition intake of the trapped persons which cannot be rescued temporarily is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of face recognition, and in particular to an alarm system and method based on face recognition. Background Art

[0002] When emergency rescue is carried out after a flood, the rescue team often finds it difficult to find the trapped people in time and misses the best rescue time, thereby reducing the physical and mental health of the trapped people in the flood-stricken area. However, through the face recognition technology of drones, the trapped position of the trapped people in the flood-stricken area can be quickly located, so as to provide timely rescue. Therefore, it is very necessary to study the disaster area rescue warning system based on face recognition.

[0003] Prior art, such as the invention patent application with announcement number: CN117011797A, discloses a method for urban flood monitoring based on image recognition technology, which includes: intelligent screening of decision information for dispatching, and the target city server generates a real-time feedback map of floods. This invention effectively calls on the existing large-scale urban monitoring probes to achieve smart urban flood control. Compared with the existing flood control methods that only rely on rainfall monitoring, the judgment is more accurate and reliable. This invention adopts grayscale algorithms, convolutional neural network recognition and other means, and uses hierarchical probes from point to surface, from identifying the depth of water accumulation and water accumulation area at the probe location to covering the entire city’s affected area, and determining the disaster situation by region, providing a reference for the effective dispatch of relevant departments.

[0004] Prior art, such as the invention patent application with announcement number: CN110265124A, discloses an urban public health emergency rescue decision-making support system based on artificial intelligence technology, which includes: a wounded positioning module that controls a drone to search in disaster areas that are inaccessible to ground transportation based on real-time on-site images; a face recognition module that searches for trapped wounded persons and locates the current geographical location information when there are trapped wounded persons; a receiving module that receives the transmitted images and geographical location information of the trapped wounded; and a medical condition review module that queries the medical history records of the trapped wounded based on the images of the trapped wounded and transmits them to on-site rescue personnel.

[0005] From the above scheme, it can be seen that the current disaster rescue warning system based on face recognition lacks certain attention to calculating the life threat coefficient according to the environmental data and physical data of the trapped persons in the water area and the ground area respectively. The flood area can be divided into the water area and the land area. The trapped persons in the water area are often more in need of rescue, but the number of rescue teams is often insufficient. The trapped persons in the water area who are not suitable for age, have faster water flow around them, have low water temperature, are severely hypothermic, and have a history of illness need to be rescued with higher priority. If these trapped persons are not rescued in time, they may suffer irreversible physical injuries. Summary of the invention

[0006] The purpose of the present invention is to provide an alarm system based on face recognition and a method thereof, which solves the problems existing in the background technology.

[0007] To solve the above technical problems, the present invention adopts the following technical solutions: The first aspect of the present invention provides an alarm system based on face recognition, including: a disaster area face information acquisition module, which is used to obtain the surface image of the flood area through a drone after a flood occurs and the rescue team arrives at the flood area, divide the flood area into a water surface area and a land area, and obtain the water surface height of the flood area, search for trapped people in the flood area through a drone, obtain face recognition images of each trapped person in the flood area, and obtain the historical medical conditions and ages of each trapped person in the flood area based on this.

[0008] The land trapped personnel analysis module is used to obtain the geographical coordinates, altitude and ambient temperature values ​​of the trapped positions of each trapped person in the land area through a drone, and analyze the life threat coefficient of each trapped person in the land area.

[0009] The module for analyzing trapped persons on the water surface is used to obtain the body temperature values ​​of each trapped person in the water surface area and the geographical coordinates of the trapped location, water depth, water flow velocity, and water temperature through drones, and analyze the life threat coefficient of each trapped person in the water surface area.

[0010] The rescue dispatch processing module is used for the drone to track the geographical coordinates of the trapped positions of each trapped person in the water surface area at all times through face recognition, and send them in real time to the communication equipment of the rescue personnel that the current rescue team can deploy, to determine whether the personnel of the current rescue team are sufficient to rescue all the trapped persons in the water surface area. If not, the priority rescue personnel and material delivery personnel in the water surface area are screened, and the priority rescue personnel in the water surface area are rescued first, the material delivery personnel in the flood-stricken area are counted, the material delivery volume of each material delivery personnel in the flood-stricken area is calculated, and materials are delivered by drones accordingly. If sufficient, while rescuing the trapped persons in the water surface area, the priority rescue personnel and material delivery personnel in the land area are screened, and the priority rescue personnel in the land area are rescued first, and land material delivery operations are performed by drones.

[0011] Preferably, the flood-hit area is divided into a water surface area and a land area, and the specific method of the division is: based on the surface image of the flood-hit area and through the landform feature distinction technology, the flood-hit area is divided into a water surface area and a land area.

[0012] Preferably, the specific method for obtaining the historical medical conditions and ages of each trapped person in the flood-stricken area is: obtaining the face recognition image, historical medical conditions and age of each recorded person from the household registration management platform.

[0013] The face recognition images of the trapped persons in the flood-stricken area are matched with the face recognition images of the recorded persons, so as to obtain the recorded persons matched with the faces of the trapped persons in the flood-stricken area, and map the historical medical conditions and ages of the trapped persons in the flood-stricken area.

[0014] Preferably, the life threat coefficient of each trapped person in the land area is analyzed by a specific analysis method: obtaining the age group of young people from a local database, and extracting the maximum age A and the minimum age B of the age group of young people.

[0015] According to the historical medical conditions and ages of the trapped people in the flood area, extract the historical medical conditions and ages of the trapped people in the land area .

[0016] Obtain the land trapped threat value of each medical condition from the local database, and extract the land trapped threat value of each historical medical condition of each trapped person in the land area according to the historical medical conditions of each trapped person in the land area. , where x represents the number of each trapped person in the land area, , y is a positive integer greater than 2, i represents the number of each historical medical condition of the trapped persons in the land area, , j is a positive integer greater than 2.

[0017] Obtain the suitable ambient temperature value C for being trapped on land from the local database, based on the altitude of the trapped location of each trapped person in the land area and ambient temperature , and calculate the life threat coefficient of each trapped person in the land area according to the water surface height D in the flood area , where y represents the number of trapped people in the land area.

[0018] Preferably, the life threat coefficient of each trapped person in the water surface area is analyzed by a specific analysis method: according to the historical conditions and ages of each trapped person in the flood area, the historical conditions and ages of each trapped person in the water surface area are extracted. , where n represents the number of each trapped person in the water area, , m is a positive integer greater than 2.

[0019] Obtain the water surface trapped threat value of each disease condition from the local database, and extract the water surface trapped threat value of each historical disease condition of each trapped person in the water surface area , where r represents the historical medical condition number of the trapped persons in the water area, , s is a positive integer greater than 2.

[0020] Get the average height and suitable body temperature of each age from the local database, and map the average height of each trapped person in the water area. , suitable body temperature .

[0021] Based on the body temperature of each trapped person in the water area and the water depth of the trapped location , water flow rate , water temperature , calculate the water flow hazard body coefficient of each trapped person in the water surface area , where m is the total number of trapped persons in the water surface area.

[0022] Calculate the life threat coefficient of each trapped person in the water area .

[0023] Preferably, the specific judgment method for judging whether the personnel of the current rescue team are sufficient to rescue all trapped persons in the water surface area is: obtaining the number of rescue personnel that can be deployed by the current rescue team and the number of rescue personnel required for a single trapped person in the water surface area from the local database.

[0024] According to the trapped persons in the water surface area, the total number of trapped persons in the water surface area is counted, and the total number of rescue persons required in the water surface area is counted accordingly.

[0025] The number of rescue personnel that the current rescue team can deploy is compared with the total number of rescue personnel required in the water surface area. If the number of rescue personnel that the current rescue team can deploy is less than the total number of rescue personnel required in the water surface area, it is judged that the personnel of the current rescue team are insufficient to rescue all trapped persons in the water surface area. Otherwise, it is judged that the personnel of the current rescue team are sufficient to rescue all trapped persons in the water surface area.

[0026] Preferably, the priority rescue personnel and material delivery personnel in the water surface area are screened by obtaining the geographical coordinates of the stationed positions of the rescue teams from the local database, and calculating the distance between the trapped positions of the trapped personnel in the water surface area and the stationed position of the nearest rescue team according to the geographical coordinates of the trapped positions of the trapped personnel in the water surface area. .

[0027] According to the life threat coefficient of each trapped person in the water area , calculate the priority rescue coefficient of each trapped person in the water area .

[0028] The trapped persons in the water surface area are sorted from large to small according to the priority rescue coefficient, so as to obtain the sorted trapped persons in the water surface area.

[0029] Based on the number of rescue personnel that the current rescue team can deploy and the number of rescue personnel required for a single trapped person in the water surface area, the maximum number of people that the current rescue team can rescue at one time in the water surface area is calculated, and the maximum number of rescue personnel that the current rescue team can rescue at one time in the water surface area is selected from the sorted trapped persons in the water surface area starting from the first one in the sorting. The selected trapped persons in the water surface area are marked as priority rescue personnel in the water surface area, and the remaining trapped persons in the water surface area are marked as material delivery personnel in the water surface area.

[0030] Preferably, the specific calculation method for calculating the material delivery amount of each material delivery personnel in the flood-stricken area is: obtaining the material delivery amount corresponding to each life threat coefficient interval of the water surface area from a local database, and mapping the material delivery amount for each trapped person in the water surface area according to the life threat coefficient of each trapped person in the water surface area.

[0031] The material delivery amount corresponding to each life threat coefficient interval in the land area is obtained from the local database, and the material delivery amount for each trapped person in the land area is mapped according to the life threat coefficient of each trapped person in the land area.

[0032] Summarize the material delivery quantities of each material delivery personnel in the flood-stricken areas.

[0033] Preferably, the specific screening method for screening the priority rescue personnel and material delivery personnel in the land area is: based on the method for screening the priority rescue personnel and material delivery personnel in the water area, the priority rescue personnel and material delivery personnel in the land area are screened similarly.

[0034] The second invention of the present invention provides an alarm method for executing the above-mentioned face recognition-based alarm system, including: Step 1. Acquisition of face information in the disaster area: After a flood occurs and the rescue team arrives at the flood-stricken area, the surface image of the flood-stricken area is obtained by a drone, the flood-stricken area is divided into a water surface area and a land area, and the water surface height of the flood-stricken area is obtained. The flood-stricken area is searched for trapped people by a drone, and face recognition images of each trapped person in the flood-stricken area are obtained, and the historical medical conditions and ages of each trapped person in the flood-stricken area are obtained based on this.

[0035] Step 2. Analysis of trapped persons on land: The geographical coordinates, altitude and ambient temperature of each trapped person in the land area are obtained through drones, and the life threat coefficient of each trapped person in the land area is analyzed.

[0036] Step 3. Analysis of trapped persons on the water surface: The body temperature of each trapped person in the water surface area and the geographical coordinates of the trapped location, water depth, water flow velocity, and water temperature are obtained through drones to analyze the life threat coefficient of each trapped person in the water surface area.

[0037] Step 4. Rescue dispatch processing: The drone tracks the geographic coordinates of the trapped positions of each trapped person in the water surface area through facial recognition, and sends them in real time to the communication equipment of the rescue personnel that the current rescue team can deploy, to determine whether the personnel of the current rescue team are sufficient to rescue all the trapped persons in the water surface area. If not, the priority rescue personnel and material delivery personnel in the water surface area are screened, and the priority rescue personnel in the water surface area are given priority in rescue. The material delivery personnel in the flood-stricken area are counted, and the material delivery volume of each material delivery personnel in the flood-stricken area is calculated, and materials are delivered through drones accordingly. If sufficient, while rescuing the trapped persons in the water surface area, the priority rescue personnel and material delivery personnel in the land area are screened, and the priority rescue personnel in the land area are given priority in rescue, and land material delivery operations are performed through drones.

[0038] The beneficial effects of the present invention are as follows: (1) The disaster area face information acquisition module of the present invention makes a preliminary division of the flood area and obtains relevant information of the trapped persons in the flood area, thereby facilitating subsequent analysis.

[0039] (2) The land trapped persons analysis module and the water trapped persons analysis module of the present invention analyze the life threat coefficient of each trapped person in the land area by taking into account the influence of inappropriate age, previous medical history, and altitude difference for the trapped persons in the land area; and analyze the life threat coefficient of each trapped person in the water area by taking into account the influence of inappropriate age, faster water flow around them, low water temperature, severe hypothermia, and previous medical history for the trapped persons in the water area, thereby facilitating subsequent rescue arrangements.

[0040] (3) The rescue dispatch processing module of the present invention prioritizes the rescue of trapped persons in the water surface area by deploying rescue personnel of the rescue team. When the number of rescue personnel is insufficient, the priority rescue personnel in the water surface area are screened according to the life threat coefficient of the trapped persons in the water surface area and the distance to the nearest rescue station. Regardless of whether the number of rescue personnel is sufficient or insufficient, drones are used for collaborative material delivery to deliver materials to the material delivery personnel in the flood-stricken area, thereby reducing the incidence of irreversible physical injuries to the trapped persons and ensuring the nutritional intake of the trapped persons who cannot be rescued temporarily. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is a schematic diagram of the system module of the present invention.

[0043] Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Reference Figure 1 As shown, the first invention of the present invention provides an alarm system based on face recognition, including: a disaster area face information acquisition module, a land trapped person analysis module, a water trapped person analysis module, a rescue dispatch processing module and a local database.

[0046] It should be noted that the disaster area facial information acquisition module is connected to the land trapped persons analysis module and the water trapped persons analysis module, the rescue dispatch processing module is connected to the land trapped persons analysis module and the water trapped persons analysis module, and the local database is connected to the land trapped persons analysis module, the water trapped persons analysis module, and the rescue dispatch processing module.

[0047] It should also be noted that the local database is used to store the age groups of young people, the land trapping threat values ​​of various medical conditions, the suitable ambient temperature values ​​for land trapping, the water trapping threat values ​​of various medical conditions, the average height values ​​of various ages, the suitable body temperature values, the number of rescue personnel that the current rescue team can deploy, the number of rescue personnel required for a single trapped person in the water area, the geographical coordinates of the stationing locations of each rescue team, the amount of material delivery corresponding to each life threat coefficient interval in the water area, and the amount of material delivery corresponding to each life threat coefficient interval in the land area.

[0048] The module for acquiring facial information in the disaster area is used to acquire the surface image of the flood-stricken area by means of a drone after a flood occurs and the rescue team arrives at the flood-stricken area, divide the flood-stricken area into a water surface area and a land area, and acquire the water surface height of the flood-stricken area, search for trapped persons in the flood-stricken area by means of a drone, acquire facial recognition images of each trapped person in the flood-stricken area, and thereby obtain the historical medical conditions and ages of each trapped person in the flood-stricken area.

[0049] In a specific embodiment, the surface image of the flood-hit area is obtained by a specific method: the surface image of the flood-hit area is obtained by a high-speed camera carried by a drone.

[0050] In a specific embodiment, the water surface height in the flood-hit area is obtained by a specific method: obtaining the water surface height in the flood-hit area by using a radar altimeter carried by a drone.

[0051] In a specific embodiment, the facial recognition images of the trapped persons in the flood-stricken area are obtained by a specific method: the facial recognition images of the trapped persons in the flood-stricken area are obtained by using an infrared high-speed camera carried by a drone.

[0052] In a specific embodiment of the present invention, the flood-stricken area is divided into a water surface area and a land area, and the specific method of distinguishing the flood-stricken area is: based on the surface image of the flood-stricken area and through the landform feature distinction technology, the flood-stricken area is distinguished into a water surface area and a land area.

[0053] It should be noted that the existing geomorphic feature differentiation technology is relatively mature. Through the existing geomorphic feature differentiation technology and combined with the surface image of the flood-stricken area, the flood-stricken area can be divided into water surface area and land area.

[0054] In a specific embodiment of the present invention, the historical medical conditions and ages of the trapped persons in the flood-stricken area are obtained by obtaining the facial recognition images, historical medical conditions and ages of the recorded persons from the household registration management platform.

[0055] The face recognition images of the trapped persons in the flood-stricken area are matched with the face recognition images of the recorded persons, so as to obtain the recorded persons matched with the faces of the trapped persons in the flood-stricken area, and map the historical medical conditions and ages of the trapped persons in the flood-stricken area.

[0056] In a specific embodiment, the facial matching record of each trapped person in the flood-stricken area is obtained by the following method: the existing facial matching technology is relatively mature, and the facial matching record of each trapped person in the flood-stricken area can be obtained by the existing facial matching technology.

[0057] The disaster area facial information acquisition module of the present invention makes a preliminary division of the flood area and obtains relevant information of the trapped persons in the flood area, so as to facilitate subsequent analysis.

[0058] The land trapped personnel analysis module is used to obtain the geographical coordinates, altitude and ambient temperature of the trapped positions of each trapped person in the land area through a drone, and analyze the life threat coefficient of each trapped person in the land area.

[0059] In a specific embodiment, the geographical coordinates, altitude and ambient temperature of the trapped positions of each trapped person in the land area are obtained by: obtaining the geographical coordinates of the trapped positions of each trapped person in the land area by remote sensing technology, obtaining the altitude of the trapped positions of each trapped person in the land area by a radar altimeter carried by an unmanned aerial vehicle, and obtaining the ambient temperature of the trapped positions of each trapped person in the land area by a temperature sensor.

[0060] In a specific embodiment of the present invention, the life threat coefficient of each trapped person in the land area is analyzed by a specific analysis method: the age group of young people is obtained from a local database, and the maximum age A and the minimum age B of the age group of young people are extracted.

[0061] According to the historical medical conditions and ages of the trapped people in the flood area, extract the historical medical conditions and ages of the trapped people in the land area .

[0062] Obtain the land trapped threat value of each medical condition from the local database, and extract the land trapped threat value of each historical medical condition of each trapped person in the land area according to the historical medical conditions of each trapped person in the land area. , where x represents the number of each trapped person in the land area, , y is a positive integer greater than 2, i represents the number of each historical medical condition of the trapped persons in the land area, , j is a positive integer greater than 2.

[0063] Obtain the suitable ambient temperature value C for being trapped on land from the local database, based on the altitude of the trapped location of each trapped person in the land area and ambient temperature , and calculate the life threat coefficient of each trapped person in the land area according to the water surface height D in the flood area , where y represents the number of trapped people in the land area.

[0064] The module for analyzing trapped persons on the water surface is used to obtain the body temperature value of each trapped person in the water surface area and the geographical coordinates of the trapped position, water depth value, water flow velocity, and water temperature value through a drone, and analyze the life threat coefficient of each trapped person in the water surface area.

[0065] In a specific embodiment, the method for obtaining the body temperature value of each trapped person in the water surface area and the geographical coordinates of the trapped position, water depth value, water flow velocity, and water temperature value is as follows: obtaining the body temperature value of each trapped person in the flood-stricken area by an infrared high-speed camera carried by an unmanned aerial vehicle, obtaining the geographical coordinates and water temperature value of the trapped position of each trapped person in the water surface area by remote sensing technology, and obtaining the body temperature value of each trapped person in the water surface area and the water depth value and water flow velocity of the trapped position by a portable Doppler flowmeter carried by the unmanned aerial vehicle.

[0066] In a specific embodiment of the present invention, the life threat coefficient of each trapped person in the water surface area is analyzed, and the specific analysis method is: according to the historical conditions and ages of each trapped person in the flood area, the historical conditions and ages of each trapped person in the water surface area are extracted. , where n represents the number of each trapped person in the water area, , m is a positive integer greater than 2.

[0067] Obtain the water surface trapped threat value of each disease condition from the local database, and extract the water surface trapped threat value of each historical disease condition of each trapped person in the water surface area , where r represents the historical medical condition number of the trapped persons in the water area, , s is a positive integer greater than 2.

[0068] Get the average height and suitable body temperature of each age from the local database, and map the average height of each trapped person in the water area. , suitable body temperature .

[0069] Based on the body temperature of each trapped person in the water area and the water depth of the trapped location , water flow rate , water temperature , calculate the water flow hazard body coefficient of each trapped person in the water surface area , where m is the total number of trapped persons in the water surface area.

[0070] Calculate the life threat coefficient of each trapped person in the water area .

[0071] The land trapped persons analysis module and the water trapped persons analysis module of the present invention analyze the life threat coefficient of each trapped person in the land area by taking into account the influence of unsuitable age, previous medical history, and altitude difference for the trapped persons in the land area; and analyze the life threat coefficient of each trapped person in the water area by taking into account the influence of unsuitable age, faster water flow rate around them, low water temperature, severe hypothermia, and previous medical history for the trapped persons, thereby facilitating subsequent rescue arrangements.

[0072] The rescue dispatch processing module is used for the drone to track the geographical coordinates of the trapped positions of each trapped person in the water surface area at all times through face recognition, and send them in real time to the communication equipment of the rescue personnel that the current rescue team can deploy, to determine whether the personnel of the current rescue team are sufficient to rescue all the trapped persons in the water surface area; if not, the priority rescue personnel and material delivery personnel in the water surface area are screened, and the priority rescue personnel in the water surface area are rescued first, the material delivery personnel in the flood-stricken area are counted, the material delivery volume of each material delivery personnel in the flood-stricken area is calculated, and materials are delivered by the drone accordingly; if sufficient, while rescuing the trapped persons in the water surface area, the priority rescue personnel and material delivery personnel in the land area are screened, and the priority rescue personnel in the land area are rescued first, and the land material delivery operation is performed by the drone.

[0073] In a specific embodiment of the present invention, the method for judging whether the personnel of the current rescue team are sufficient to rescue all trapped persons in the water surface area is as follows: obtaining the number of rescue personnel that can be deployed by the current rescue team and the number of rescue personnel required for a single trapped person in the water surface area from a local database.

[0074] According to the trapped persons in the water surface area, the total number of trapped persons in the water surface area is counted, and the total number of rescue persons required in the water surface area is counted accordingly.

[0075] The number of rescue personnel that the current rescue team can deploy is compared with the total number of rescue personnel required in the water surface area. If the number of rescue personnel that the current rescue team can deploy is less than the total number of rescue personnel required in the water surface area, it is judged that the personnel of the current rescue team are insufficient to rescue all trapped persons in the water surface area. Otherwise, it is judged that the personnel of the current rescue team are sufficient to rescue all trapped persons in the water surface area.

[0076] In a specific embodiment of the present invention, the priority rescue personnel and material delivery personnel in the water surface area are screened by obtaining the geographical coordinates of the stationed positions of the rescue teams from the local database, and calculating the distance between the trapped positions of the trapped personnel in the water surface area and the stationed position of the nearest rescue team according to the geographical coordinates of the trapped positions of the trapped personnel in the water surface area. .

[0077] According to the life threat coefficient of each trapped person in the water area , calculate the priority rescue coefficient of each trapped person in the water area .

[0078] The trapped persons in the water surface area are sorted from large to small according to the priority rescue coefficient, so as to obtain the sorted trapped persons in the water surface area.

[0079] Based on the number of rescue personnel that the current rescue team can deploy and the number of rescue personnel required for a single trapped person in the water surface area, the maximum number of people that the current rescue team can rescue at one time in the water surface area is calculated, and the maximum number of rescue personnel that the current rescue team can rescue at one time in the water surface area is selected from the sorted trapped persons in the water surface area starting from the first one in the sorting. The selected trapped persons in the water surface area are marked as priority rescue personnel in the water surface area, and the remaining trapped persons in the water surface area are marked as material delivery personnel in the water surface area.

[0080] In a specific embodiment, the specific statistical method for counting the personnel delivering supplies in the flood-stricken area is as follows: summarizing the personnel delivering supplies in the flood-stricken area based on the personnel delivering supplies in the water area and the trapped persons in the land area.

[0081] In a specific embodiment of the present invention, the material delivery amount of each material delivery personnel in the flood-stricken area is calculated by obtaining the material delivery amount corresponding to each life threat coefficient interval of the water surface area from a local database, and mapping the material delivery amount for each trapped person in the water surface area according to the life threat coefficient of each trapped person in the water surface area.

[0082] The material delivery amount corresponding to each life threat coefficient interval in the land area is obtained from the local database, and the material delivery amount for each trapped person in the land area is mapped according to the life threat coefficient of each trapped person in the land area.

[0083] Summarize the material delivery quantities of each material delivery personnel in the flood-stricken areas.

[0084] In a specific embodiment of the present invention, the specific screening method for screening the priority rescue personnel and material delivery personnel in the land area is: based on the method for screening the priority rescue personnel and material delivery personnel in the water area, the priority rescue personnel and material delivery personnel in the land area are screened similarly.

[0085] In a specific embodiment, the specific operation method of the land material delivery operation is: based on calculating the material delivery amount of each material delivery personnel in the flood-stricken area, the material delivery amount of each material delivery personnel in the land area is calculated similarly, and the material delivery is carried out through a drone.

[0086] The rescue dispatch processing module of the present invention prioritizes the rescue of trapped persons in the water surface area by deploying rescue personnel of the rescue team. When the number of rescue personnel is insufficient, the priority rescue personnel in the water surface area are screened according to the life threat coefficient of the trapped persons in the water surface area and the distance to the nearest rescue station. Regardless of whether the number of rescue personnel is sufficient or insufficient, drones are used for collaborative delivery of materials to deliver materials to the material delivery personnel in the flood-stricken area, thereby reducing the incidence of irreversible physical injuries to the trapped persons and ensuring the nutritional intake of the trapped persons who cannot be rescued temporarily.

[0087] Reference Figure 2 As shown, the second invention of the present invention provides an alarm method for executing the face recognition-based alarm system, including: Step 1. Acquisition of facial information in the disaster area: After a flood occurs and the rescue team arrives at the flood-stricken area, the surface image of the flood-stricken area is obtained by a drone, the flood-stricken area is divided into a water surface area and a land area, and the water surface height of the flood-stricken area is obtained. The flood-stricken area is searched for trapped people by a drone, and facial recognition images of each trapped person in the flood-stricken area are obtained, and the historical medical conditions and ages of each trapped person in the flood-stricken area are obtained accordingly.

[0088] Step 2. Analysis of trapped persons on land: The geographical coordinates, altitude and ambient temperature of each trapped person in the land area are obtained through drones, and the life threat coefficient of each trapped person in the land area is analyzed.

[0089] Step 3. Analysis of trapped persons on the water surface: The body temperature of each trapped person in the water surface area and the geographical coordinates of the trapped location, water depth, water flow velocity, and water temperature are obtained through drones to analyze the life threat coefficient of each trapped person in the water surface area.

[0090] Step 4. Rescue dispatch processing: The drone tracks the geographic coordinates of the trapped positions of each trapped person in the water surface area through facial recognition, and sends them in real time to the communication equipment of the rescue personnel that the current rescue team can deploy, to determine whether the personnel of the current rescue team are sufficient to rescue all the trapped persons in the water surface area. If not, the priority rescue personnel and material delivery personnel in the water surface area are screened, and the priority rescue personnel in the water surface area are given priority in rescue. The material delivery personnel in the flood-stricken area are counted, and the material delivery volume of each material delivery personnel in the flood-stricken area is calculated, and materials are delivered through drones accordingly. If sufficient, while rescuing the trapped persons in the water surface area, the priority rescue personnel and material delivery personnel in the land area are screened, and the priority rescue personnel in the land area are given priority in rescue, and land material delivery operations are performed through drones.

[0091] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. The alarm system based on face recognition is characterized by: include: The face information acquisition module of the disaster area is used to obtain the surface image of the flood area through the drone after the flood occurs and the rescue team arrives at the flood area, divide the flood area into the water surface area and the land area, and obtain the water surface height of the flood area, search for trapped people in the flood area through the drone, obtain the face recognition image of each trapped person in the flood area, and obtain the historical medical condition and age of each trapped person in the flood area based on this; The land trapped personnel analysis module is used to obtain the geographical coordinates, altitude and ambient temperature of each trapped person in the land area through the drone, and analyze the life threat coefficient of each trapped person in the land area; The module for analyzing trapped persons on the water surface is used to obtain the body temperature value of each trapped person in the water surface area and the geographical coordinates, water depth value, water flow velocity, and water temperature value of the trapped position through the drone, and analyze the life threat coefficient of each trapped person in the water surface area; The rescue dispatch processing module is used for the drone to track the geographical coordinates of the trapped positions of each trapped person in the water surface area at all times through face recognition, and send them in real time to the communication equipment of the rescue personnel that the current rescue team can deploy, to determine whether the personnel of the current rescue team are sufficient to rescue all the trapped persons in the water surface area. If not, the priority rescue personnel and material delivery personnel in the water surface area are screened, and the priority rescue personnel in the water surface area are rescued first, the material delivery personnel in the flood-stricken area are counted, the material delivery volume of each material delivery personnel in the flood-stricken area is calculated, and materials are delivered by drones accordingly. If sufficient, while rescuing the trapped persons in the water surface area, the priority rescue personnel and material delivery personnel in the land area are screened, and the priority rescue personnel in the land area are rescued first, and land material delivery operations are performed by drones.

2. The face recognition based alarm system according to claim 1, characterized in that: The flood disaster area is divided into water surface area and land area, and the specific method of distinction is as follows: Based on the surface image of the flood-stricken area and the use of geomorphic feature differentiation technology, the flood-stricken area is divided into water surface area and land area.

3. The face recognition based alarm system according to claim 1, characterized in that: The specific method for obtaining the historical medical conditions and ages of the trapped persons in the flood-hit area is as follows: Obtain the facial recognition image, historical medical condition and age of each recorded person from the household registration management platform; The face recognition images of the trapped persons in the flood-stricken area are matched with the face recognition images of the recorded persons, so as to obtain the recorded persons matched with the faces of the trapped persons in the flood-stricken area, and map the historical medical conditions and ages of the trapped persons in the flood-stricken area.

4. The face recognition based alarm system according to claim 1, characterized in that: The specific analysis method for analyzing the life threat coefficient of each trapped person in the land area is as follows: Obtain the age range of young people from the local database, and extract the maximum age A and the minimum age B of the age range of young people; According to the historical medical conditions and ages of the trapped people in the flood area, extract the historical medical conditions and ages of the trapped people in the land area ; Obtain the land trapped threat value of each medical condition from the local database, and extract the land trapped threat value of each historical medical condition of each trapped person in the land area according to the historical medical conditions of each trapped person in the land area. , where x represents the number of each trapped person in the land area, , y is a positive integer greater than 2, i represents the number of each historical medical condition of the trapped persons in the land area, , j is a positive integer greater than 2; Obtain the suitable ambient temperature value C for being trapped on land from the local database, based on the altitude of the trapped location of each trapped person in the land area and ambient temperature , and calculate the life threat coefficient of each trapped person in the land area according to the water surface height D in the flood area , where y represents the number of trapped people in the land area.

5. The face recognition based alarm system according to claim 4, characterized in that: The specific analysis method for analyzing the life threat coefficient of each trapped person in the water surface area is as follows: According to the historical medical conditions and ages of the trapped people in the flood area, extract the historical medical conditions and ages of the trapped people in the water area , where n represents the number of each trapped person in the water area, , m is a positive integer greater than 2; Obtain the water surface trapped threat value of each disease condition from the local database, and extract the water surface trapped threat value of each historical disease condition of each trapped person in the water surface area , where r represents the historical medical condition number of the trapped persons in the water area, , s is a positive integer greater than 2; Get the average height and suitable body temperature of each age from the local database, and map the average height of each trapped person in the water area. , suitable body temperature ; Based on the body temperature of each trapped person in the water area and the water depth of the trapped location , water flow rate , water temperature , calculate the water flow hazard body coefficient of each trapped person in the water surface area , where m is the total number of trapped persons in the water surface area; Calculate the life threat coefficient of each trapped person in the water area .

6. The face recognition-based alarm system according to claim 5, characterized in that: The specific method for judging whether the current rescue team has enough personnel to rescue all trapped persons in the water area is as follows: Obtain the number of rescuers that can be deployed by the current rescue team and the number of rescuers required for a single trapped person in the surface area from the local database; According to the trapped persons in the water surface area, the total number of trapped persons in the water surface area is counted, and the total number of rescue persons required in the water surface area is counted accordingly; The number of rescue personnel that the current rescue team can deploy is compared with the total number of rescue personnel required in the water surface area. If the number of rescue personnel that the current rescue team can deploy is less than the total number of rescue personnel required in the water surface area, it is judged that the personnel of the current rescue team are insufficient to rescue all trapped persons in the water surface area. Otherwise, it is judged that the personnel of the current rescue team are sufficient to rescue all trapped persons in the water surface area.

7. The face recognition based alarm system according to claim 6, characterized in that: The specific screening method for screening the priority rescue personnel and material delivery personnel in the water surface area is as follows: Obtain the geographic coordinates of the stationed positions of each rescue team from the local database, and calculate the distance between the trapped positions of each trapped person in the water area and the stationed position of the nearest rescue team based on the geographic coordinates of the trapped positions of each trapped person in the water area ; According to the life threat coefficient of each trapped person in the water area , calculate the priority rescue coefficient of each trapped person in the water area ; Sort the trapped persons in the water surface area from large to small according to the priority rescue coefficient, and obtain the sorted trapped persons in the water surface area; Based on the number of rescue personnel that the current rescue team can deploy and the number of rescue personnel required for a single trapped person in the water surface area, the maximum number of people that the current rescue team can rescue at one time in the water surface area is calculated, and the maximum number of rescue personnel that the current rescue team can rescue at one time in the water surface area is selected from the sorted trapped persons in the water surface area starting from the first one in the sorting. The selected trapped persons in the water surface area are marked as priority rescue personnel in the water surface area, and the remaining trapped persons in the water surface area are marked as material delivery personnel in the water surface area.

8. The face recognition based alarm system according to claim 1, characterized in that: The specific calculation method for calculating the material delivery amount of each material delivery personnel in the flood-stricken area is as follows: Obtain the amount of material delivered corresponding to each life threat coefficient interval in the water surface area from the local database, and map the amount of material delivered to each trapped person in the water surface area according to the life threat coefficient of each trapped person in the water surface area; Obtain the material delivery amount corresponding to each life threat coefficient interval in the land area from the local database, and map the material delivery amount for each trapped person in the land area according to the life threat coefficient of each trapped person in the land area; Summarize the material delivery quantities of each material delivery personnel in the flood-stricken areas.

9. The face recognition based alarm system according to claim 1, characterized in that: The specific screening method for screening the priority rescue personnel and material delivery personnel in the land area is as follows: The priority rescue personnel and material delivery personnel in the land area are screened in the same way as the method of screening the priority rescue personnel and material delivery personnel in the water area.

10. An alarm method for executing the alarm system based on face recognition according to any one of claims 1 to 9, characterized in that: include: Step 1. Acquisition of facial information in the disaster area: After a flood occurs and the rescue team arrives at the flood-stricken area, the surface image of the flood-stricken area is obtained by drone, and the flood-stricken area is divided into the water surface area and the land area. The water surface height of the flood-stricken area is obtained, and the trapped people in the flood-stricken area are searched by drone, and the facial recognition images of the trapped people in the flood-stricken area are obtained, and the historical medical conditions and ages of the trapped people in the flood-stricken area are obtained accordingly; Step 2. Analysis of trapped persons on land: The geographical coordinates, altitude and ambient temperature of each trapped person in the land area are obtained by drone, and the life threat coefficient of each trapped person in the land area is analyzed; Step 3. Analysis of trapped persons on the water surface: The body temperature of each trapped person in the water surface area and the geographical coordinates, water depth, water flow velocity, and water temperature of the trapped position are obtained through the drone, and the life threat coefficient of each trapped person in the water surface area is analyzed; Step 4. Rescue dispatch processing: The drone tracks the geographic coordinates of the trapped positions of each trapped person in the water surface area through facial recognition, and sends them in real time to the communication equipment of the rescue personnel that the current rescue team can deploy, to determine whether the personnel of the current rescue team are sufficient to rescue all the trapped persons in the water surface area. If not, the priority rescue personnel and material delivery personnel in the water surface area are screened, and the priority rescue personnel in the water surface area are given priority in rescue. The material delivery personnel in the flood-stricken area are counted, and the material delivery volume of each material delivery personnel in the flood-stricken area is calculated, and materials are delivered through drones accordingly. If sufficient, while rescuing the trapped persons in the water surface area, the priority rescue personnel and material delivery personnel in the land area are screened, and the priority rescue personnel in the land area are given priority in rescue, and land material delivery operations are performed through drones.

Images