Indoor personnel falling perception method and device, electronic equipment and storage medium

Abstract

The application provides a kind of indoor personnel's perception method, device, electronic equipment and storage medium of falling, which can be applied to indoor positioning technical field.The moving speed of the personnel to be monitored is determined according to the topological information, and the topological information is obtained by identifying the backscattering tag arranged in the area to be monitored.If the moving speed is lower than the preset speed threshold, the falling detection is performed on the personnel to be monitored.If the falling detection result is confirmed as the falling state, the falling alarm signal is generated.The application realizes the monitoring of the target to be monitored in a certain area by deploying multiple backscattering tags in the indoor environment, and timely discovers the falling state of the target to be monitored and alarms, which has higher accuracy compared with the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of indoor positioning technology, and in particular to an indoor personnel fall perception method and device, electronic equipment and storage medium. BACKGROUND

[0002] Indoor personnel fall detection technology aims to monitor and identify personnel fall events in indoor environments in real time using sensors, cameras, algorithms, and machine learning methods. Current indoor personnel fall detection can be achieved through sensor technology, visual technology, and sound recognition technology. These technologies are usually combined with intelligent devices, Internet of Things (IoT) systems, or dedicated fall detection devices. They can provide real-time fall detection and alerts in indoor environments to take timely action and ensure people's safety.

[0003] However, current indoor personnel fall detection technology has some shortcomings, such as low accuracy and reliability, and high deployment costs.

[0004] In summary, the problems in the prior art need to be solved. SUMMARY

[0005] The present application provides an indoor personnel fall perception method, device, electronic equipment and storage medium to solve the problem of low fall detection accuracy in the prior art.

[0006] The present application provides an indoor personnel fall perception method, which includes:

[0007] According to the topological information, the moving speed of the personnel to be monitored is determined; the topological information is obtained by identifying the backscattering tags set in the monitoring area;

[0008] If the moving speed is lower than the preset speed threshold, the personnel to be monitored is detected for falling;

[0009] If the fall detection result is confirmed as a fall state, a fall alarm signal is generated.

[0010] According to the indoor personnel fall perception method provided by the present application, the moving speed of the personnel to be monitored is determined according to the topological information; the topological information is obtained by identifying the backscattering tags set in the monitoring area, and specifically includes:

[0011] According to the topological information collected by the backscattering tags set in the monitoring area, a three-dimensional model of the monitoring area is constructed;

[0012] According to the topological information collected by the backscattering tags set in the monitoring area, a three-dimensional model of the monitoring area is constructed;

[0013] performing grid division on the three-dimensional model to determine trajectory information of the to-be-monitored personnel based on the divided three-dimensional grid;

[0014] determining a moving speed of the to-be-monitored personnel according to the trajectory information.

[0015] According to the indoor personnel fall perception method provided by the application, after the three-dimensional modeling of the to-be-monitored region is constructed according to the topological information collected by the backscattering tags arranged in the to-be-monitored region, the method further comprises:

[0016] performing channel estimation according to the backscattering signals sent by the backscattering tags arranged in the to-be-monitored region to obtain channel state information;

[0017] when the phase fluctuation of the channel state information is greater than a preset threshold range, it is determined that the to-be-monitored personnel enters the to-be-monitored region.

[0018] According to the indoor personnel fall perception method provided by the application, if the moving speed is lower than a preset speed threshold, fall detection is performed on the to-be-monitored personnel, and specifically comprises:

[0019] determining the grid height and the grid length-width scale of the person grid model of the to-be-monitored personnel, the person grid model being composed of the three-dimensional grid;

[0020] if the grid height is lower than a preset height threshold and the grid length-width scale is higher than a preset length-width scale threshold, it is determined that the to-be-monitored personnel is in a fall state.

[0021] According to the indoor personnel fall perception method provided by the application, if it is confirmed that the fall detection result is a fall state, a fall alarm signal is generated, and specifically comprises:

[0022] if the fall detection confirms that the to-be-monitored personnel is in a fall state and the duration of the fall state is greater than a preset time threshold, a fall alarm signal is generated.

[0023] According to the indoor personnel fall perception method provided by the application, after the fall alarm signal is generated, the method further comprises:

[0024] obtaining vital sign information of the to-be-monitored personnel according to the channel state information.

[0025] The application further provides an indoor personnel fall perception device, comprising:

[0026] a moving speed obtaining module, configured to determine a moving speed of the to-be-monitored personnel according to topological information, the topological information being obtained by identifying backscattering tags arranged in a to-be-monitored region;

[0027] A fall detection module is used to detect falls in the person to be monitored if the moving speed is lower than a preset speed threshold.

[0028] The alarm generation module is used to generate a fall alarm signal if the fall detection confirms that the person to be monitored has fallen.

[0029] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the indoor person fall detection method as described above.

[0030] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the indoor person fall detection method as described above.

[0031] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the indoor person fall detection method as described above.

[0032] This invention provides a method, device, electronic device, and storage medium for detecting indoor falls. It determines the movement speed of the person to be monitored based on topological information, obtained by identifying backscatter tags placed within the monitored area. If the movement speed is lower than a preset speed threshold, fall detection is performed on the person. If the fall detection result confirms a fall, a fall alarm signal is generated. This invention achieves monitoring of the target within a certain area by deploying multiple backscatter tags in an indoor environment, enabling timely detection and alarm of falls. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0034] Figure 1 This is a flowchart illustrating the indoor occupant fall detection method provided by the present invention.

[0035] Figure 2 This is a schematic diagram of the relationship between the height and length and width of the person to be monitored standing posture, provided by the present invention.

[0036] Figure 3 This is a schematic diagram showing the relationship between the height and length / width of the person to be monitored in their sitting posture, provided by the present invention.

[0037] Figure 4 is a schematic diagram of the squat target height and length-width relationship of the person to be monitored provided by the present application;

[0038] Figure 5 is a schematic diagram of the person to be monitored receiving a signal when entering the area to be monitored provided by the present application;

[0039] Figure 6 is a schematic diagram of multiple tags in backscattering communication provided by the present application;

[0040] Figure 7 is a schematic diagram of horizontal target motion tracking based on Doppler shift provided by the present application;

[0041] Figure 8 is a grid schematic diagram of the fall state of the person to be monitored provided by the present application;

[0042] Figure 9 is a structural schematic diagram of the perception device for indoor personnel falling provided by the present application;

[0043] Figure 10 is a structural schematic diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0044] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0045] Passive sensing, also known as device-free sensing, is a sensing form without the active participation of the sensing object in the sensing process, and usually relies on detecting the impact of the target on the environment to achieve sensing. Dynamic environmental clutter signals in indoor environments bring great challenges to indoor positioning systems. The previous clutter removal methods either perform poorly in handling dynamic clutter environments or cannot distinguish target signals from environmental clutter when the target is stationary. Most of the schemes only collect a bunch of radar data in a laboratory environment, that is, it is assumed that the start and end times of each action can be perfectly captured, and then the next step is performed on the manually cropped signals. However, in actual situations, the capture of the start and end times of the action will greatly affect the system performance. In addition, the multipath effect of microwaves in the indoor environment cannot be ignored. The size of the room, and even the placement of furniture, will result in different multipath propagation paths.

[0046] In actual situations, the position of a person relative to the radar is also usually uncertain. This can result in different aspect angles of the reflection waves reflected by the human body relative to the radar. Different aspect angles can result in different micro-motion effects on the time-frequency graph.

[0047] Therefore, the indoor personnel fall detection technology has the following defects:

[0048] High false positive rate: Some technologies may incorrectly label non-fall events as falls, resulting in false positives. This can be caused by sensor errors, environmental interference, or imperfect algorithms.

[0049] High true negative rate: Some technologies may not accurately detect true fall events, resulting in false negatives. This can be caused by insufficient sensor sensitivity, inaccurate algorithms, or the inability to distinguish between falls and other activities.

[0050] Limited applicability: Different indoor environments and scenarios can affect the applicability of fall detection technology. For example, complex layouts, different floor types, or lighting conditions can interfere with the accuracy of the detection system.

[0051] To solve the above problems, the present application provides a method for sensing indoor personnel falls, a device, an electronic device and a storage medium, as shown in Figure 1 Figure 1 The present application provides a flowchart of the method for sensing indoor personnel falls, which includes but is not limited to steps 110-130:

[0052] Step 110, according to the topological information, the moving speed of the to-be-monitored personnel is determined; the topological information is obtained by identifying the backscattering tags arranged in the to-be-monitored area.

[0053] In step 110, the three-dimensional modeling of the to-be-monitored area can be established according to the topological information collected by the backscattering tags arranged in the to-be-monitored area, and then the three-dimensional modeling is logically gridded, and then the trajectory information of the to-be-monitored personnel is established with the target moving grid as the granularity, and then the moving speed of the to-be-monitored personnel is determined according to the trajectory information. It can be understood that the indoor furniture and furnishings are perceived by multiple tags, and usually the more complex the three-dimensional space relationship is, the more tags need to be arranged.

[0054] As a further optional embodiment, the backscattering tags (also known as passive RFID tags) in step 110 usually have two modes of listening (or passive) and responding.

[0055] ​Listen mode: In the listen mode, the backscatter tag is in standby state and does not actively send any information. It relies solely on the excitation signal sent by the external reader (also known as active device or reader) for power supply. When the excitation signal reaches the tag, the antenna in the tag receives the signal and uses its energy to activate the tag circuit. After activation, the tag begins to decode and store data in preparation for subsequent response.

[0056] Response mode: Once the backscatter tag is activated, it will reply to the reader in response mode. The internal circuit of the tag will re-modulate and reflect the signal sent by the reader, carrying the identification information and other data of the tag. After receiving the reflected signal of the tag, the reader will decode and process the data provided by the tag.

[0057] These two modes make the backscatter tag a low-power device without internal battery. They can be widely used in the fields of Internet of Things, logistics tracking, inventory management and identity recognition, providing a simple, economical and reliable automatic identification solution.

[0058] Multiple tags in the same area can be converted between the listen and response modes through pre-configuration, semi-static scheduling, or dynamic scheduling, etc., to obtain part or all of the topology information of the adjacent tags after a certain time.

[0059] In step 120, if the moving speed is lower than the preset speed threshold, a fall detection is performed on the person to be monitored.

[0060] It can be understood that when the person to be monitored falls, the moving speed of the person to be monitored will be significantly reduced. Therefore, in step 120, the moving speed of the person to be monitored is used as a prerequisite for fall detection. Specifically, the moving speed of the person to be monitored measured in real time in step 110 is compared with the preset speed threshold, and when the moving speed is lower than the preset speed threshold, a fall detection is performed on the person to be monitored.

[0061] In step 130, if the fall detection result is confirmed as a fall state, a fall alarm signal is generated.

[0062] In step 130, when the fall detection confirms that the person to be monitored is in a fall state, a fall alarm signal is generated. The fall alarm signal can be received by a perception control device and can be visually displayed by the perception control device. The perception control device is a terminal with a tag backscatter signal receiver deployed in the monitoring area, such as a smart phone, an end computing gateway or a device called CPE (Customer Premises Equipment).

[0063] The perception control device in the application has the ability to receive the tag signal in the indoor monitoring area, and has the ability to configure and schedule the tags with configurable ability. The perception control device receives the backscattering signal information of each tag in the current sensitivity range through the backscattering signal receiver module carried by itself. Since each tag can report the ID of the adjacent tag received in a listening window period to the perception control device after sorting the multiple adjacent tag IDs based on the average signal strength of the adjacent tag response, in theory, the perception control device can establish the topological position relationship of each positioning reference tag deployed in the room after a period of time. Here, the antenna of the backscattering signal receiver module of the perception control device will adopt a two-dimensional multi-antenna configuration and support angle of arrival estimation, DoA or AoA. While receiving the backscattering information of the specific tag in the room, the direction of each tag signal and the three-dimensional spatial position information are measured, and the three-dimensional modeling of the indoor tag is performed based on the aforementioned topological information.

[0064] As an optional embodiment, in order to avoid false alarms, the alarm can be performed when the to-be-monitored person enters the falling state and does not exit the falling state for a period of time.

[0065] As another optional embodiment, once it is detected that the to-be-monitored person exits the falling state, the falling alarm is released. It can be understood that the falling alarm can also be released by manual reset.

[0066] According to the perception method of the indoor personnel falling provided by the application, the moving speed of the to-be-monitored person is determined according to the topological information, and the topological information is obtained by identifying the backscattering tags arranged in the to-be-monitored area, and specifically includes:

[0067] The three-dimensional modeling of the to-be-monitored area is constructed according to the topological information collected by the backscattering tags arranged in the to-be-monitored area.

[0068] The three-dimensional model of the to-be-monitored area is constructed according to the topological information collected by the backscattering tags arranged in the to-be-monitored area.

[0069] The three-dimensional model is divided into grids, so as to determine the trajectory information of the to-be-monitored person based on the divided three-dimensional grids.

[0070] The moving speed of the to-be-monitored person is determined according to the trajectory information.

[0071] In the embodiment, a three-dimensional modeling of a to-be-monitored area needs to be established according to topological information collected by backscatter tags arranged in the to-be-monitored area, then logical grid division is performed on the three-dimensional modeling, then trajectory information of a to-be-monitored person is established with a target moving grid as a granularity, and then the moving speed of the to-be-monitored person is determined according to the trajectory information.

[0072] Specifically, the AoA angle of the perception control device and each tag and the distance information from the tag to the perception control device are calculated by using the MUSIC method. The channel characteristics of each tag to the perception control device in a steady indoor environment are established.

[0073] When the backscatter signal receiver module on the perception control device measures the tag signal inside the measurement room, the CSI and other channel characteristic information related to the backscatter signal of each tag are extracted at the same time. These information will be one dimension in the input variables of the subsequent target detection model. It needs to be noted that when there is a person in the room in a quiet state or no person, the parameters of the aforementioned indoor environment abstraction model are different, but it does not affect the judgment of the person falling information.

[0074] Suppose that the current indoor multi-tag wireless signal is in a steady state, that is, the signal backscattered from each tag to the perception control device is in a steady state after smoothing filtering processing capable of filtering environmental noise. At this time, the indoor perception network reaches a working state.

[0075] In a steady state environment, the perception control device measures the spatial angle of multiple tags by using the two-dimensional antenna array carried on the environmental backscatter signal receiver module, and obtains the direction of arrival information and channel information of each tag.

[0076] By filtering disturbance signals, an indoor environment abstraction model can be established by using the aforementioned multiple tags, and logical grid division can be performed. Here, SLAM and other tools can be used for modeling.

[0077] After completing the three-dimensional modeling, when a human-like moving target is detected to enter the detection area, first, trajectory information with a target moving grid as a granularity is established, and then the speed of the to-be-monitored person can be obtained according to the trajectory information.

[0078] According to the indoor person falling perception method provided by the application, after the three-dimensional modeling of the to-be-monitored area is constructed according to the topological information collected by the backscatter tags arranged in the to-be-monitored area, the method further comprises:

[0079] Channel estimation is performed according to the backscatter signals sent by the backscatter tags arranged in the to-be-monitored area, and channel state information is obtained.

[0080] When the phase fluctuation of the channel state information is greater than a preset threshold range, it is determined that the to-be-monitored person enters the to-be-monitored area.

[0081] In the embodiment, before the moving speed of the to-be-monitored person is acquired, it can be determined whether the to-be-monitored person enters the to-be-monitored area, and when it is determined that the to-be-monitored person enters the to-be-monitored area, subsequent steps are performed, so that energy consumption can be effectively saved. Specifically, in a steady state environment, the sensing control device performs channel estimation on each received tag backscattering signal, and when there is no person in the environment, the phase fluctuation of the channel state information (CSI) of the signal is small, and the change is relatively small after smoothing filtering.

[0082] The positioning tags use a pre-configuration or scheduling indication mechanism, sense the topological position relationship of adjacent tags and themselves, and report the topological position relationship to the sensing control device. When a person or a moving object enters the steady state area, the sensing control device can determine that an object enters the current monitoring area by observing the change of the incoming direction information and the channel information of the tag exceeding the threshold range.

[0083] When a person or an object enters the detection area, the phase of the channel state information (CSI) received by the sensing control device will change rapidly due to the influence of the moving object on the signals of each tag. By setting a threshold range, it can be determined that an object enters the detection area. The sensing control device has the ability to perform angle estimation on the backscattering signals of different tags, for example, for Tag A, the direction angle and the pitch angle of the backscattering signal of the tag can be obtained. For a standing person target, it is considered that the height of the target contour three-dimensional grid is greater than the length and width. For the target detection angle, the azimuth angle is less than the pitch angle, that is, According to this standard, it can be determined whether the target entering the monitoring area is a human-like target.

[0084] For a person in a standing, sitting or squatting posture, the height and length-width ratio and the direction angle and pitch angle range can be further distinguished by refinement, as shown in Figure 2 , Figure 3 and Figure 4 , Figure 2 is a schematic diagram of the height and length-width relationship of a to-be-monitored person in a standing posture provided by the application, Figure 3 is a schematic diagram of the height and length-width relationship of a to-be-monitored person in a sitting posture provided by the application, Figure 4 is a schematic diagram of the height and length-width relationship of a to-be-monitored person in a squatting posture provided by the application.

[0085] According to a method for detecting indoor falls provided by the present invention, if the moving speed is lower than a preset speed threshold, fall detection is performed on the person to be monitored, specifically including:

[0086] Determine the grid height and grid length and width dimensions of the person to be monitored grid model, wherein the person grid model is composed of the three-dimensional grid;

[0087] If the grid height is lower than a preset height threshold and the grid length and width are higher than preset length and width thresholds, then the person to be monitored is determined to be in a fallen state.

[0088] This embodiment of fall detection employs a multi-tag moving target merging method: when a person or other target enters the current indoor detection area, it will affect the channels from multiple indoor deployed tags to the sensing and control device, resulting in disturbances to the signals received by the sensing and control device. Figure 5 and Figure 6 For example, Figure 5 This is a schematic diagram illustrating the signal received when a person to be monitored enters the area to be monitored, as provided by the present invention. Figure 6 This is a schematic diagram of multiple tags providing this invention performing backscatter communication. Before a person enters the detection area, the angle of arrival of Tag A is denoted as θ. TagA When a person enters the detection area, their body reflects the backscattered signal from tag A. At the sensing and control device, the target scattered angle of arrival (θ), distinct from the tag's LOS path, can be estimated using AoA. TagA The angle is denoted as Since there are multiple tags within the detection area, let θ be the angle of arrival for Tag B. TagB The angle at which the signal of tag B is reflected by the person's body is recorded as follows: And so on.

[0089] After detecting a humanoid moving target entering the detection area, trajectory information is first established at the granularity of the target movement grid. Each scan of each tag signal requires obtaining target information in both the horizontal and vertical grid directions. Target recognition processing is performed in two stages:

[0090] In the first stage, when the detected target is moving horizontally and the speed is not lower than a threshold, only the target's horizontal motion information is analyzed; that is, only the target's horizontal motion state is tracked. Figure 7 As shown, Figure 7 This is a schematic diagram of horizontal target motion tracking based on Doppler frequency shift provided by the present invention.

[0091] When the target's horizontal movement speed decreases rapidly or stops at a certain grid position, such as Figure 8 As shown, Figure 8is a grid diagram provided by the application for monitoring the falling state of a person, starting the second stage analysis: and using the vertical grid information of the last few positions before the horizontal movement stops, analyzing whether the target has a sudden falling situation. In the application, the standard for judging falling is: the target height rapidly decreases to near the ground, and the target area length and width rapidly increase, the direction angle and the pitch angle of the corresponding target outline also change accordingly.

[0092] It can be understood that the falling condition in the embodiment mainly includes that the target stops horizontal movement in the determined position grid, and the target occupies the grid height below the set threshold, and the length and width scale of the target rapidly expand. These indicators are automatically set according to different target characteristics in proportion.

[0093] According to the indoor personnel falling perception method provided by the application, if it is confirmed that the falling detection result is a falling state, a falling alarm signal is generated, which specifically includes:

[0094] If the falling detection confirms that the person to be monitored is in a falling state and the duration of the falling state is greater than a preset time threshold, a falling alarm signal is generated.

[0095] In the embodiment, in order to avoid false alarms, the person to be monitored can enter a falling state and not exit the falling state for a period of time, and then an alarm is performed.

[0096] As another optional embodiment, once it is detected that the person to be monitored exits the falling state, the falling alarm is canceled. It can be understood that the falling alarm can also be reset by manual reset.

[0097] According to the indoor personnel falling perception method provided by the application, after the falling alarm signal is generated, it further includes:

[0098] According to the channel state information, the vital sign information of the person to be monitored is obtained.

[0099] In this embodiment, the vital sign information of the to-be-monitored person can be acquired through the channel state information. Specifically, the acquired channel state information is subjected to signal processing, and the change in phase is mainly focused on. The breathing causes slight movement of the environment around the target, thereby causing fluctuation of the CSI phase of the received signal. Then, the features related to the breathing movement of the target are extracted through analysis of the CSI data. These features can be the change frequency of the phase, the change in amplitude, etc. Subsequently, the extracted features are analyzed and classified using a machine learning algorithm or a pattern recognition method to detect and identify the breathing movement of the target. The breathing detection and tracking are achieved through pattern matching using the known breathing patterns through the trained algorithm. The vital sign information of the to-be-monitored person can be acquired according to the channel state information, and the real condition of the to-be-monitored person can be further understood.

[0100] Reference Figure 9 , Figure 9 is a structural schematic diagram of the indoor personnel fall sensing device provided by the present application. The indoor personnel fall sensing device provided by the present application is described below, and the indoor personnel fall sensing device described below can be correspondingly referred to the indoor personnel fall sensing method described above.

[0101] The moving speed acquisition module 910 is configured to determine the moving speed of the to-be-monitored person according to the topological information, wherein the topological information is obtained by identifying the backscattering tags arranged in the to-be-monitored area.

[0102] The fall detection module 920 is configured to perform fall detection on the to-be-monitored person if the moving speed is lower than the preset speed threshold.

[0103] The alarm generation module 930 is configured to generate a fall alarm signal if the fall detection confirms that the to-be-monitored person falls.

[0104] Figure 10 An example of an electronic device is shown in the structural schematic diagram of the electronic device as shown in Figure 10 The electronic device can include a processor 1010, a communications interface 1020, a memory 1030, and a communications bus 1040, wherein the processor 1010, the communications interface 1020, and the memory 1030 can communicate with each other through the communications bus 1040. The processor 1010 can invoke the logical instructions in the memory 1030 to execute the indoor personnel fall sensing method, which includes:

[0105] The moving speed of the to-be-monitored person is determined according to the topological information, wherein the topological information is obtained by identifying the backscattering tags arranged in the to-be-monitored area.

[0106] If the moving speed is lower than a preset speed threshold, the person to be monitored is subjected to a fall detection.

[0107] If the fall detection result is confirmed as a fall state, a fall alarm signal is generated.

[0108] In addition, the logical instructions in the memory 1030 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0109] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the perception method of indoor personnel fall provided by the above-mentioned methods, and the method comprises:

[0110] According to the topological information, the moving speed of the person to be monitored is determined; the topological information is obtained by identifying the backscattering tags arranged in the monitoring area;

[0111] If the moving speed is lower than a preset speed threshold, the person to be monitored is subjected to a fall detection.

[0112] If the fall detection result is confirmed as a fall state, a fall alarm signal is generated.

[0113] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the perception method of indoor personnel fall provided by the above-mentioned methods, and the method comprises:

[0114] According to the topological information, the moving speed of the person to be monitored is determined; the topological information is obtained by identifying the backscattering tags arranged in the monitoring area;

[0115] If the moving speed is lower than a preset speed threshold, a fall detection is performed on the person to be monitored.

[0116] If the fall detection result is confirmed as a fall state, a fall alarm signal is generated.

[0117] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0118] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software plus the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0119] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of sensing a fall of a person in a room, characterized by, The method comprises the following steps: determining the moving speed of the monitored person according to the topological information; the topological information is obtained by identifying the backscattering tags arranged in the monitored area; if the moving speed is lower than the preset speed threshold, the fall detection of the monitored person is performed; if the fall detection result is confirmed as the fall state, the fall alarm signal is generated; wherein, the topological information is obtained by identifying the backscattering tags arranged in the monitored area, and specifically comprising: constructing a three-dimensional model of the monitored area according to the topological information collected by the backscattering tags arranged in the monitored area; dividing the three-dimensional model into grids to determine the trajectory information of the monitored person based on the divided three-dimensional grids; determining the moving speed of the monitored person according to the trajectory information.

2. The method of claim 1, wherein, After constructing the three-dimensional model of the monitored area according to the topological information collected by the backscattering tags arranged in the monitored area, it further comprises: channel estimation is performed according to the backscattering signals sent by the backscattering tags arranged in the monitored area to obtain channel state information; if the phase fluctuation of the channel state information is greater than the preset threshold range, it is judged that the monitored person enters the monitored area.

3. The method of awareness of a fall of a person indoors according to claim 2, characterized in that, If the moving speed is lower than the preset speed threshold, the fall detection of the monitored person is performed, specifically comprising: determining the grid height and grid length-width scale of the person grid model of the monitored person, the person grid model being composed of the three-dimensional grids; if the grid height is lower than the preset height threshold and the grid length-width scale is higher than the preset length-width scale threshold, it is judged that the monitored person is in the fall state.

4. The method of awareness of a fall of a person indoors according to claim 3, characterized in that, If the fall detection result is confirmed as the fall state, the fall alarm signal is generated, specifically comprising: if the fall detection confirms that the monitored person is in the fall state and the duration of the fall state is greater than the preset time threshold, the fall alarm signal is generated.

5. The method of awareness of a fall of a person indoors according to claim 4, characterized in that, After generating the fall alarm signal, it further comprises: obtaining the vital sign information of the monitored person according to the channel state information.

6. A device for sensing a fall of a person in a room, characterized in that The method comprises the following steps: The moving speed acquisition module is used to determine the moving speed of the monitored person according to the topological information; the topological information is obtained by identifying the backscattering tags arranged in the monitored area; the fall detection module is used to perform the fall detection of the monitored person if the moving speed is lower than the preset speed threshold; the alarm generation module is used to generate the fall alarm signal if the fall detection confirms that the monitored person falls; the moving speed acquisition module is specifically used for: constructing a three-dimensional model of the monitored area according to the topological information collected by the backscattering tags arranged in the monitored area; dividing the three-dimensional model into grids to determine the trajectory information of the monitored person based on the divided three-dimensional grids; determining the moving speed of the monitored person according to the trajectory information.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the indoor personnel fall sensing method of any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, which is executed by a processor, implements the method for sensing a fall of a person indoors according to any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that, The computer program, which is executed by a processor, implements the method for sensing a fall of a person indoors according to any one of claims 1 to 5.

Images