Indoor human body detection method and 5G electronic equipment

Abstract

The invention discloses an indoor human body detection method and 5G electronic equipment, the 5G electronic equipment comprises a data acquisition unit, a data storage unit, a data processing unit, a 5G communication unit, an alarm unit and a front-end control unit, the data acquisition unit is in communication connection with the data storage unit, the data storage unit is in communication connection with the data processing unit, and the data processing unit is in communication connection with the alarm unit. The data acquisition unit, the data storage unit, the data processing unit and the alarm unit are respectively in communication connection with the front-end control unit, and the front-end control unit is in communication connection with remote equipment through the 5G communication unit. According to the method, the human body posture is analyzed and judged by utilizing the change of the human body lateral observation radar point cloud picture and the human body upward observation radar point cloud picture and the speed data related to the human body, and misjudgment in human body posture detection is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor human body monitoring. Specifically, it is an indoor human body detection method and a 5G electronic device. Background Art

[0002] When people of different ages fall, the injuries suffered by the human body are different, and different falling methods will also cause different injuries. For example, when the elderly fall, they are very likely to have fractures and other situations, while it is relatively unlikely for young and middle-aged people and teenagers to have such situations. Again, when falling forward or sideways, people will subconsciously bend their knees and curl their bodies to reduce the degree of harm caused by the fall. When falling backward, it is difficult to take other effective protection measures except trying to keep the back in contact with the ground first.

[0003] At present, many elderly people or children fall indoors and are not discovered in time, and the resulting injuries are not dealt with accordingly, causing permanent injuries or more serious impacts on the human body. In order to reduce the labor intensity of caregivers and also relieve the burden on the children of the elderly and the parents of children, people have researched and developed an indoor human body fall monitoring system. Since most of the existing human body fall monitoring systems analyze whether a person has fallen through the change of the point cloud map, misjudgments will occur. For example, when an elderly person squats down and sits on the ground, judging from the change of the point cloud map, the body posture of the elderly person has changed, similar to the change of the point cloud map when a person falls. If this phenomenon is regarded as not a fall by default, new misjudgments will occur. For example, during the squatting process of the elderly person, due to insufficient leg strength, the buttocks of the elderly person hit the ground, thus forming the illusion that the elderly person is sitting on the ground. For those with insufficient waist strength or poor spinal strength, this drop will still cause certain harm to the elderly person. Summary of the Invention

[0004] Therefore, the technical problem to be solved by the present invention is to provide an indoor human body detection method and a 5G electronic device, which use the changes of the human body side-view radar point cloud map and the human body upward-view radar point cloud map and the speed data related to the human body to analyze and judge the human body posture, and reduce misjudgments in human body posture detection.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: An indoor human body detection method includes the following steps: (S100) Real-time collect radar data of a human body from above and from the side; (S200) Use the radar data collected in step (S100) to generate a human body side-view radar point cloud map and a human body upward-view radar point cloud map, and calculate the speed data V related to the human body 人, where the speed data includes the overall horizontal movement speed V1 of the human body, the upper body horizontal movement speed V2 of the human body, the lower body horizontal movement speed V3 of the human body, the upper body movement angular velocity ω1 of the human body, and the lower body movement angular velocity ω2 of the human body; (S300) Use the human body lateral observation radar point cloud map, the human body upward observation radar point cloud map, and the speed data V obtained in step (S200) 人 Analyze and judge the human body posture to determine whether someone has fallen. Specifically, the judgment steps are as follows: (S310) First, judge the change of the human body posture according to the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map obtained in step (S200). When the human body posture changes from upright to lying down or prone, then execute step (S320); (S320) Statistically analyze the speed data within the time t when the human body posture changes from upright to lying down or prone. When the difference ΔV between the upper body horizontal movement speed V2 and the lower body horizontal movement speed V3 of the human body exceeds the threshold V0 and both the upper body movement angular velocity ω1 and the lower body movement angular velocity ω2 of the human body exceed the threshold ω0, then a preliminary judgment result is given; 变 (S330) Conduct a regular analysis on the changes of the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map within the time t. When the changes of both the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map are non-regular changes, then a final judgment result is given, and it is judged that the situation where the human body posture changes from upright to lying down or prone within the time t belongs to a fall. (S330) For the time t 变 When conducting a regular analysis on the changes of the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map within the time t, the time t 变 is divided into t

[0006] In the above indoor human body detection method, in step (S330), when conducting a regular analysis on the changes of the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map within the time t, 变 the time t 变 is divided into t 变1 and t 变2 and t 变1 : t 变2 is 10 to 5:1. Then, a comparative analysis is conducted on the changes of the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map within t 变1 and t 变2 . The specific operation is as follows: (S331) Take t 变1Divide it into m time periods, and compare the human body side-view radar point cloud maps and the human body upward-view radar point cloud maps within the m time periods. When the similarity difference between the human body side-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV1 or the similarity difference between the human body upward-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV2, it is considered that the changes in the human body side-view radar point cloud map and the human body upward-view radar point cloud map within time t 变1 are both non-regular changes, where m is a natural number greater than or equal to 5; (S332)Divide t 变2 into n time periods, and compare the human body side-view radar point cloud maps and the human body upward-view radar point cloud maps within the n time periods. When the similarity difference between the human body side-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV3 or the similarity difference between the human body upward-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV4, it is considered that the changes in the human body side-view radar point cloud map and the human body upward-view radar point cloud map within time t 变2 are both non-regular changes, where n is a natural number greater than or equal to 3.

[0007] In the above indoor human body detection method, in step (S200), when the vertical dimension change amplitude of the human body side-view radar point cloud map within the unit time T exceeds 10% or / and the horizontal dimension change amplitude of the human body upward-view radar point cloud map exceeds 15%, calculate the velocity data V related to the human body 人 , otherwise, do not calculate the velocity data V related to the human body 人 , where the unit time T is a preset parameter value greater than or equal to 10 ms and less than or equal to 50 ms.

[0008] In the above indoor human body detection method, when calculating the upper body movement angular velocity ω1 and the lower body movement angular velocity ω2 of the human body in step (S200), correct ω1 and ω2 according to the following strategy: (CL1)When the direction of ω1 is the same as the overall horizontal movement direction of the human body when the human body begins to tilt, correct ω1 and ω2 using the following formula: In the formula, both σ1 and σ2 are parameters related to the human body front inclination threshold α, and σ1 and σ2 are calculated by the following formula: (CL2) When the human body begins to tilt, the direction of ω1 is opposite to the overall horizontal movement direction of the human body, and the following formula is used to correct ω1 and ω2: Wherein, σ3 and σ4 are parameters related to the threshold of the backward tilt angle of the human body, and σ1 and σ2 are calculated by the following formula: In the above-mentioned indoor human body detection method, when ω1 and ω2 are in the same direction, a first-level risk fall is identified in the final judgment result given in step (S330), otherwise, a second-level risk fall is identified, wherein the degree of harm of a first-level risk fall is higher than that of a second-level risk fall.

[0009] In the above-mentioned indoor human body detection method, in step (S300), the human body side observation radar point cloud map, the human body upward observation radar point cloud map and the speed data V obtained in step (S200) are used. 人 When the human body posture is analyzed and judged and it is determined that someone has fallen, the direction of the person's fall is analyzed using the radar point cloud map of the side observation of the human body and the radar point cloud map of the upward observation of the human body to determine whether there is a risk of head collision, and it is marked in the final judgment result.

[0010] In the above-mentioned indoor human body detection method, in step (S300), the human body side observation radar point cloud map, the human body upward observation radar point cloud map and the speed data V obtained in step (S200) are used. 人 When analyzing and judging the human body posture and determining that someone has fallen, calculate the time t 变 The value of 变 The numerical value of the fall risk level is marked in the final judgment result.

[0011] The 5G electronic device using the above-mentioned indoor human body examination method for human body examination includes: A data acquisition unit is used to collect radar data of the human body; the data acquisition unit includes an upward 4D millimeter-wave radar installed on the roof and a side 4D millimeter-wave radar installed on the upper half of the side wall; A data storage unit, used for storing radar data collected by the data collection unit; The data processing unit is used to process the radar data collected by the data collection unit; the data processing unit includes a radar point cloud image generation module, a speed data V related to the human body, and a 人 A speed calculation module and a radar point cloud image generated by the radar point cloud image generation module and a speed data V calculated by the speed calculation module 人an analysis module to perform the analysis; 5G communication unit, used to send alarm information to remote devices, where the remote devices include servers, handheld smart terminals and networked computers; An alarm unit, used for giving an alarm by sound; A front-end control unit, used to control a data acquisition unit, a data storage unit, a data processing unit, a 5G communication unit, and an alarm unit; The data acquisition unit is communicatively connected to the data storage unit, the data storage unit is communicatively connected to the data processing unit, the data acquisition unit, the data storage unit, the data processing unit and the alarm unit are communicatively connected to the front-end control unit respectively, and the front-end control unit is communicatively connected to the remote device through the 5G communication unit.

[0012] For the above-mentioned 5G electronic devices, the alarm unit also provides an alarm by flashing an indicator light.

[0013] In the above-mentioned 5G electronic device, the data acquisition unit is communicatively connected with the data storage unit via the UWB communication module.

[0014] The technical solution of the present invention achieves the following beneficial technical effects: 1. The present invention utilizes the changes in the human body side observation radar point cloud map and the human body upward observation radar point cloud map, as well as the changes in the overall horizontal movement speed of the human body, the horizontal movement speed of the upper body of the human body, the horizontal movement speed of the lower body of the human body, the angular velocity of the upper body of the human body, and the angular velocity of the lower body of the human body when the above two point cloud maps change to judge whether the indoor personnel have fallen, avoiding the misjudgment that occurs when judging whether the human body has fallen only by relying on the changes in the radar point cloud map, and can effectively detect the low-level fall of the elderly. Among them, low-level fall refers to the fall that occurs when the human body is in a half-squatting or squatting state. Compared with high-level fall, this kind of fall is less harmful, but for some elderly people, it will also cause more serious injuries.

[0015] 2. The present invention divides the time periods when the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map change, and analyzes the regularity of the changes in the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map in different time periods to ensure that the human body's fall is not intentional. Specifically, a person leans forward, then bends his knees, and then lies on the ground. At this time, according to the changes in the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map, as well as the changes in the overall horizontal movement speed of the human body, the horizontal movement speed of the upper body of the human body, the horizontal movement speed of the lower body of the human body, the angular velocity of the upper body of the human body, and the angular velocity of the lower body of the human body, there is also the possibility of judging that the human body has fallen. However, the changes in the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map in this process have a regularity that can be followed.

[0016] 3. Identifying the risk level of falls in the final judgment result is beneficial for people to take corresponding treatment methods according to different risk levels, and avoid the aggravation of injuries caused by untimely treatment. Description of the Drawings

[0017] Figure 1 It is a schematic diagram of the working principle of a 5G electronic device capable of indoor human body detection; Figure 2 It is a flowchart of wireless positioning for 5G terminal devices; Figure 3 It is a schematic diagram of the calculation principle of the relative angular velocity between two points during the translation process. Detailed Embodiment

[0018] As Figure 1 shown, the present invention provides a 5G electronic device capable of indoor human body detection, which includes a data acquisition unit, a data storage unit, a data processing unit, a 5G communication unit, an alarm unit, and a front-end control unit. The data acquisition unit is communicatively connected to the data storage unit through a UWB communication module. The data storage unit is communicatively connected to the data processing unit. The data acquisition unit, the data storage unit, the data processing unit, and the alarm unit are respectively communicatively connected to the front-end control unit. The front-end control unit is communicatively connected to a remote device through the 5G communication unit, where the remote device includes a server, a handheld intelligent terminal, a networked computer, etc.

[0019] In the present invention, the data acquisition unit is used to collect radar data of the human body; the data acquisition unit includes an upward 4D millimeter-wave radar installed on the roof and a lateral 4D millimeter-wave radar installed on the upper half of the side wall. The data storage unit is used to store the radar data collected by the data acquisition unit. The data processing unit is used to process the radar data collected by the data acquisition unit. The data processing unit includes a radar point cloud map generation module, a speed calculation module for calculating the speed data V 人 related to the human body, and an analysis module for analyzing the radar point cloud map generated by the radar point cloud map generation module and the speed data V 人 calculated by the speed calculation module. The 5G communication unit is used to send alarm information to the remote device. The alarm unit is used to give an alarm through sound and indicator light flashing. The front-end control unit is used to control the data acquisition unit, the data storage unit, the data processing unit, the 5G communication unit, and the alarm unit.

[0020] When applying the 5G electronic device in the present invention to indoor human detection, an upward 4D millimeter-wave radar and a lateral 4D millimeter-wave radar should be set according to the indoor structure, and these two 4D millimeter-wave radars should be communicatively connected to the data storage unit. At the same time, the data storage unit, the data processing unit, the alarm unit, the 5G communication unit, and the front-end control unit are centrally arranged in a device box.

[0021] As Figure 2 shown, in the indoor environment where the 5G electronic device in the present invention is set, the human detection of this indoor environment is realized through the following steps: (S100) Collect radar data of the human body in real time from above and from the side.

[0022] When using the 4D millimeter-wave radar to collect radar data of the human body, sensors can be set at the entrances and exits of the room. When someone enters the room, the 4D millimeter-wave radar is then activated to work. When no one enters the room, the 4D millimeter-wave radar can be in a standby state. This can not only reduce the energy consumption of the device but also extend the service life of the device.

[0023] (S200) Generate a lateral observation radar point cloud map of the human body and an upward observation radar point cloud map of the human body using the radar data collected in step (S100), and calculate the velocity data V related to the human body 人 , where the velocity data includes the overall horizontal movement velocity V1 of the human body, the horizontal movement velocity V2 of the upper body of the human body, the horizontal movement velocity V3 of the lower body of the human body, the movement angular velocity ω1 of the upper body of the human body, and the movement angular velocity ω2 of the lower body of the human body.

[0024] When calculating the velocity data V related to the human body using the radar data collected in step (S100) 人 , the Doppler effect principle is used for calculation. Among them, the movement angular velocity ω1 of the upper body of the human body and the movement angular velocity ω2 of the lower body of the human body can be calculated using the horizontal displacement difference of two points in the vertical direction. As Figure 3 shown, assume that two points A and B on an object are in the same vertical direction and are separated by a distance L1. Within a time t, point A has a horizontal displacement of L2, and point B has a horizontal displacement of L3. Then the angular velocity ω of point B relative to point A A-B can be calculated by the following formula: Figure 3 Among them, the dashed line AB represents the initial position of the object, the solid line AB represents the position of the object after translation for time t, and θ represents the angle of rotation of B relative to A.

[0025] In the present invention, the angular velocity ω1 of the upper body and the angular velocity ω2 of the lower body can be calculated with the human foot as the center of the circle, or the angular velocity ω1 of the upper body and the angular velocity ω2 of the lower body can be calculated with the human waist as the center of the circle and the angular velocity ω2 of the lower body can be calculated with the human foot as the center of the circle. Preferably, the angular velocity ω1 of the upper body and the angular velocity ω2 of the lower body are calculated with the human foot as the center of the circle.

[0026] (S300) Using the human body side observation radar point cloud map, human body upward observation radar point cloud map and speed data V obtained in step (S200) 人 Analyze and judge the human body posture to determine whether someone has fallen. The specific judgment steps are as follows: (S310) First, determine the change of the human body posture according to the radar point cloud image of the side observation of the human body and the radar point cloud image of the upward observation of the human body obtained in step (S200). When the human body posture changes from upright to lying down or lying down, execute step (S320).

[0027] When the posture of a person changes, the shape and area of the point cloud obtained by the upward 4D millimeter-wave radar and the lateral 4D millimeter-wave radar after scanning the person may change, especially when the person changes from an upright position to a fallen position. However, when the shape and area of the point cloud obtained by the upward 4D millimeter-wave radar and the lateral 4D millimeter-wave radar after scanning the person changes like when a person falls, it does not mean that the posture of the person changes from upright to fallen. It is necessary to calculate the overall and local motion parameters of the person during the change of the posture, and confirm the change of the posture on this basis.

[0028] (S320) Counting the time t of the human body changing from standing to lying down or lying down 变 When the difference ΔV between the horizontal moving speed V2 of the upper body and the horizontal moving speed V3 of the lower body exceeds the threshold V0 and the angular moving speed ω1 of the upper body and the angular moving speed ω2 of the lower body both exceed the threshold ω0, a preliminary judgment result is given.

[0029] When the human body posture changes from an upright state to a lying or reclining state, by calculating the motion parameters of the whole body and local parts of the human body, such as the horizontal movement speed V2 of the upper body of the human body, the horizontal movement speed V3 of the lower body of the human body, the moving angular velocity ω1 of the upper body of the human body, and the moving angular velocity ω2 of the lower body of the human body, and then by comparing with the preset threshold values, a preliminary confirmation of the human body posture change is carried out. In this step, the final confirmation of the human body posture change is not carried out. The reason is that there are regular differences between the human body posture changes during conscious falls and unconscious falls. That is, when people perform conscious falls, during the process of the human body posture changing from upright to lying or reclining, the movements of the human body trunk and limbs have a certain regularity, and reflected on the radar point cloud map, the changes in the radar point cloud map also have a certain regularity. However, during unconscious falls, the movements of the human body trunk and limbs basically have no regularity, especially when the elderly fall. In the present invention, a conscious fall refers to a person actively falling, such as falling forward in a curled-up and rolling manner, and an unconscious fall refers to an accidental fall.

[0030] (S330) Analyze the regularity of the changes in the human body side-view radar point cloud map and the changes in the human body upward-view radar point cloud map within time t 变 When the changes in the human body side-view radar point cloud map and the changes in the human body upward-view radar point cloud map are both non-regular changes, then give the final judgment result, and judge that the situation where the human body posture changes from upright to lying or reclining within time t 变 belongs to a fall.

[0031] In this step, when analyzing the regularity of the changes in the human body side-view radar point cloud map and the changes in the human body upward-view radar point cloud map within time t 变 divide time t 变 into t 变1 and t 变2 and t 变1 : t 变2 is 10 to 5:1. Then, conduct a comparative analysis of the changes in the human body side-view radar point cloud map and the changes in the human body upward-view radar point cloud map within t 变1 and t 变2 The specific operation is as follows: (S331) Divide t 变1 into m time periods, and compare the human body side-view radar point cloud map and the human body upward-view radar point cloud map within the m time periods. When the similarity difference between the human body side-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold value SV1 or the similarity difference between the human body upward-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold value SV2, then it is considered that time t 变1The changes in the point cloud map of the human body's lateral observation radar and the changes in the point cloud map of the human body's upward observation radar are both non - regular changes. Among them, m is a natural number greater than or equal to 5, and preferably, m is 5; (S332)Divide t 变2 into n time periods, and compare the point cloud maps of the human body's lateral observation radar and the point cloud maps of the human body's upward observation radar within the n time periods. When the similarity difference between the point cloud maps of the human body's lateral observation radar in two consecutive adjacent time periods is greater than the threshold value SV3 or the similarity difference between the point cloud maps of the human body's upward observation radar in two consecutive adjacent time periods is greater than the threshold value SV4, it is considered that within time t 变2 the changes in the point cloud map of the human body's lateral observation radar and the changes in the point cloud map of the human body's upward observation radar are both non - regular changes. Among them, n is a natural number greater than or equal to 3, and preferably, n is 4.

[0032] During an unconscious fall, the time required for the human body posture to change from upright to lying down or prostrate is less than 1 s. During the fall process, the downward speed of the human body is slower in the early stage, but the shape changes of the point cloud maps of the human body's lateral observation radar and the point cloud maps of the human body's upward observation radar are relatively obvious. In the later stage of the fall, the downward speed of the human body is faster, but the shape changes of the point cloud maps of the human body's lateral observation radar and the point cloud maps of the human body's upward observation radar are relatively less obvious. The reason is that during an unconscious fall, when a person feels the loss of center of gravity, they will choose to grab something, and at this time, the upper limbs will show obvious irregular waving. When approaching a complete fall, people will choose to take protective measures, and at this time, the upper limbs will not wave irregularly but will look for the ground to seek support for the body. This will cause the shape changes of the point cloud maps of the human body's lateral observation radar and the point cloud maps of the human body's upward observation radar to be relatively obvious in the early stage of the fall process, and relatively less obvious in the later stage of the fall process. Therefore, the present invention divides t 变 into two time periods, and analyzes the shape changes of the radar point cloud maps within the two time periods to more accurately determine whether it is a fall.

[0033] The threshold values SV1, SV2, SV3, and SV4 can be obtained through fall simulation analysis, and then adjusted based on the actual application requirements on the basis of the threshold values obtained from the fall simulation analysis.

[0034] In addition, in view of the fact that the body of the elderly will swing greatly when walking, the radar point cloud map formed by radar scanning of the elderly will show a certain degree of change. Therefore, in step (S200), when the change amplitude of the vertical dimension of the point cloud map of the human body's lateral observation radar within the unit time T exceeds 10% or / and the change amplitude of the horizontal dimension of the point cloud map of the human body's upward observation radar exceeds 15%, calculate the speed data V related to the human body人 Conversely, the speed data V related to the human body is not calculated. 人 Among them, the unit time T is a preset parameter value greater than or equal to 10 ms and less than or equal to 50 ms. In this way, the computational burden on the data processing unit can be reduced. At the same time, people can set the size change amplitude threshold of the human body side-view radar point cloud map in the vertical direction and the size change amplitude threshold of the human body upward-view radar point cloud map in the horizontal plane according to needs, so as to adapt to actual requirements.

[0035] When a person is about to fall, the critical values of the forward tilt angle and the lateral tilt angle of the human body are both greater than the backward tilt angle. That is, when the human body tilts, it is easier to fall when tilting backward. Therefore, when judging whether it belongs to a fall, the common sense that the critical values of the forward tilt angle and the lateral tilt angle of the human body are both greater than the backward tilt angle should be considered. That is, when calculating the moving angular velocity ω1 of the upper body of the human body and the moving angular velocity ω2 of the lower body of the human body in step (S200), ω1 and ω2 are corrected according to the following strategy: (CL1) When the direction of ω1 is the same as the overall horizontal movement direction of the human body when the human body begins to tilt, then ω1 and ω2 are corrected using the following formula: In the formula, both σ1 and σ2 are parameters related to the forward tilt angle threshold α of the human body, and σ1 and σ2 are calculated by the following formula: (CL2) When the direction of ω1 is opposite to the overall horizontal movement direction of the human body when the human body begins to tilt, then ω1 and ω2 are corrected using the following formula: In the formula, both σ3 and σ4 are parameters related to the backward tilt angle threshold β of the human body, and σ1 and σ2 are calculated by the following formula: By correcting ω1 and ω2, it is possible to avoid misjudging a fall as a quick lying down or lying flat. The reason is that when falling forward, ω1 and ω2 will both increase rapidly when the center of gravity of the human body has already shifted forward. On the contrary, when falling backward, the center of gravity of the human body can only shift slightly backward, and ω1 and ω2 will first increase slowly and then increase rapidly. Moreover, for people with a relatively tall stature, there is no need to correct ω1 and ω2, and still an ω1 and ω2 exceeding the threshold can be obtained during a fall. However, for people with a relatively short stature, especially the elderly with a hunched body, when falling, it is possible that ω1 and ω2 exceeding the threshold cannot be measured by the radar. Therefore, in the present invention, the human body forward tilt angle threshold and the human body backward tilt angle threshold are used to correct ω1 and ω2 during forward and backward falls.

[0036] Since there are significant differences in the possible harm levels during forward, backward, and lateral falls (usually, the harm caused by backward falls is greater), when ω1 and ω2 are in the same direction, a first-level risk fall is marked in the final judgment result given in step (S330). Otherwise, a second-level risk fall is marked, where the harm level of the first-level risk fall is higher than that of the second-level risk fall.

[0037] And in order to remind the user to handle the situation according to the actual fall in a timely manner, in the present invention, in step (S300), using the human body lateral observation radar point cloud map, the human body upward observation radar point cloud map, and the speed data V obtained in step (S200) 人 When analyzing and judging the human body posture and determining that someone has fallen, the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map are used to analyze the direction of the human body's fall to judge the risk of the head being knocked, and it is marked in the final judgment result.

[0038] At the same time, still using the human body lateral observation radar point cloud map, the human body upward observation radar point cloud map, and the speed data V obtained in step (S200) 人 When analyzing and judging the human body posture and determining that someone has fallen, calculate the value of time t 变 and mark the fall risk level in the final judgment result according to the magnitude of the value of time t 变 of the numerical value.

[0039] Through the accurate discrimination of the fall situation, the present invention can effectively reduce the extra burden on caregivers or guardians caused by system misjudgment. At the same time, by predicting and marking the risks generated by the fall, it is beneficial for caregivers or guardians to take corresponding measures according to the risk level, such as quickly arriving at the scene, calling an emergency phone number, or selecting medical auxiliary tools, and it is also convenient for people to estimate and predict the possible dangers of the fallen person based on experience.

[0040] Obviously, the above embodiments are merely examples given for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to exhaustively list all implementation manners here. And the obvious changes or modifications derived therefrom still fall within the protection scope of the claims of this patent application.

Claims

1. An indoor human body detection method, characterized in that, It includes the following steps: (S100) Collect real-time radar data of the human body from above and the side; (S200) Generate a lateral observation radar point cloud map of the human body and an upward observation radar point cloud map of the human body using the radar data collected in step (S100), and calculate the velocity data V related to the human body 人 , where the velocity data includes the overall horizontal movement velocity V1 of the human body, the horizontal movement velocity V2 of the upper body of the human body, the horizontal movement velocity V3 of the lower body of the human body, the movement angular velocity ω1 of the upper body of the human body, and the movement angular velocity ω2 of the lower body of the human body; (S300) Use the human body lateral observation radar point cloud map, the human body upward observation radar point cloud map, and the velocity data V obtained in step (S200) 人 Analyze and judge the human body posture to determine whether someone has fallen. Among them, the specific judgment steps are as follows: (S310) First, judge the human body posture change according to the human body lateral observation radar point cloud map and the human body upward observation radar point cloud map obtained in step (S200). When the human body posture changes from standing upright to lying down or reclining, then execute step (S320); (S320) Statistically calculate the time t when the human body posture changes from upright to lying down or reclining 变 of the velocity data. If the difference ΔV between the horizontal movement velocity V2 of the upper body of the human body and the horizontal movement velocity V3 of the lower body of the human body exceeds the threshold value V0 and both the moving angular velocity ω1 of the upper body of the human body and the moving angular velocity ω2 of the lower body of the human body exceed the threshold value ω0, then a preliminary judgment result is given; Analyze the patterns of changes in the lateral observation radar point cloud map of the human body and the upward observation radar point cloud map of the human body within time t 变 When the changes in both the lateral observation radar point cloud map of the human body and the upward observation radar point cloud map of the human body are non - regular changes, a final judgment result is given, and it is judged that if the human body posture changes from upright to lying down or reclining within time t 变 the situation belongs to a fall.

2. The indoor human body detection method according to claim 1, wherein In step (S330), when analyzing the regularity of the changes in the human body side observation radar point cloud map and the changes in the human body upward observation radar point cloud map within time t 变 divide time t 变 into t 变1 and t 变2 and t 变1 :t 变2 is 10 to 5:

1. Then, conduct a comparative analysis of the changes in the human body side observation radar point cloud map and the changes in the human body upward observation radar point cloud map within t 变1 and t 变2 . The specific operation is as follows: (S331) Divide t 变1 into m time periods, and compare the human body side-view radar point cloud maps and the human body upward-view radar point cloud maps within the m time periods. If the similarity difference between the human body side-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV1 or the similarity difference between the human body upward-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV2, then it is considered that the changes in the human body side-view radar point cloud map and the human body upward-view radar point cloud map within the time t 变1 are both non-regular changes, where m is a natural number greater than or equal to 5; (S332) Divide t 变2 into n time periods, and compare the human body side-view radar point cloud maps and the human body upward-view radar point cloud maps within the n time periods. If the similarity difference between the human body side-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV3 or the similarity difference between the human body upward-view radar point cloud maps in two consecutive adjacent time periods is greater than the threshold SV4, then it is considered that the changes in the human body side-view radar point cloud map and the human body upward-view radar point cloud map within time t 变2 are both non-regular changes, where n is a natural number greater than or equal to 3.

3. The indoor human body detection method according to claim 1, characterized in that, In step (S200), when the change amplitude of the vertical dimension of the human body side observation radar point cloud map within the unit time T exceeds 10% or / and the change amplitude of the horizontal dimension of the human body upward observation radar point cloud map exceeds 15%, calculate the velocity data V related to the human body 人 , otherwise, do not calculate the velocity data V related to the human body 人 , where the unit time T is a preset parameter value greater than or equal to 10 ms and less than or equal to 50 ms 4. The indoor human body detection method according to claim 1, wherein When calculating the moving angular velocity ω1 of the upper body of the human body and the moving angular velocity ω2 of the lower body of the human body in step (S200), correct ω1 and ω2 according to the following strategy: (CL1) When the direction of ω1 is the same as the overall horizontal moving direction of the human body when the human body begins to tilt, then correct ω1 and ω2 using the following formula: In the formula, both σ1 and σ2 are parameters related to the anterior inclination threshold α of the human body, and σ1 and σ2 are calculated by the following formula: (CL2) When the direction of ω1 is opposite to the overall horizontal moving direction of the human body when the human body begins to tilt, then correct ω1 and ω2 using the following formula: In the formula, both σ3 and σ4 are parameters related to the posterior inclination threshold β of the human body, and σ1 and σ2 are calculated by the following formula:

5. The indoor human body detection method according to claim 1, characterized in that, When ω1 and ω2 are in the same direction, mark a first-level risky fall in the final judgment result given in step (S330). Otherwise, mark a second-level risky fall, where the harm degree of the first-level risky fall is higher than that of the second-level risky fall.

6. The indoor human body detection method according to claim 1, wherein, In step (S300), the lateral human observation radar point cloud map, the upward human observation radar point cloud map, and the velocity data V obtained in step (S200) are used. 人 When analyzing and judging the human body posture and determining that someone has fallen, the lateral human observation radar point cloud map and the upward human observation radar point cloud map are used to analyze the falling direction of the human body, so as to judge the risk of head bumping and mark it in the final judgment result.

7. The indoor human body detection method according to claim 1, characterized in that In step (S300), using the human body lateral observation radar point cloud map, the human body upward observation radar point cloud map, and the velocity data V obtained in step (S200) 人 When analyzing and judging the human body posture and determining that someone has fallen, calculate the value of time t 变 of the numerical value and based on the value of time t 变 mark the fall risk level in the final judgment result according to the numerical value size 8. A 5G electronic device using the indoor human body detection method according to any one of claims 1 to 7 for a human body detection method, characterized in that, It includes: A data acquisition unit for collecting radar data of the human body; The data acquisition unit includes an upward 4D millimeter-wave radar installed on the roof and a lateral 4D millimeter-wave radar installed on the upper half of the side wall; A data storage unit for storing the radar data collected by the data acquisition unit; A data processing unit for processing the radar data collected by the data acquisition unit; the data processing unit includes a radar point cloud map generation module, a speed calculation module for calculating the speed data V related to the human body, and an analysis module for analyzing the radar point cloud map generated by the radar point cloud map generation module and the speed data V calculated by the speed calculation module. 人 The speed calculation module and the speed data V calculated by the speed calculation module for generating the radar point cloud map generated by the radar point cloud map generation module. 人 For analysis; A 5G communication unit for sending an alarm message to a remote device, where the remote device includes a server, a handheld intelligent terminal, and a networked computer; An alarm unit for giving an alarm by sound; A front-end control unit for controlling the data acquisition unit, the data storage unit, the data processing unit, the 5G communication unit, and the alarm unit; The data acquisition unit is communicatively connected to the data storage unit, the data storage unit is communicatively connected to the data processing unit, the data acquisition unit, the data storage unit, the data processing unit, and the alarm unit are respectively communicatively connected to the front-end control unit, and the front-end control unit is communicatively connected to the remote device through the 5G communication unit.

9. The 5G electronic device according to claim 8, characterized in that, The alarm unit also provides an alarm by flashing an indicator light.

10. The 5G electronic device according to claim 8, wherein The data acquisition unit is communicatively connected to the data storage unit through a UWB communication module.

Images