A fall detection algorithm, control device, terminal equipment and storage medium

Abstract

The present application provides a fall detection algorithm, a control device, a terminal device and a storage medium, wherein a fall detection algorithm is based on the change of foot parameters, and the algorithm includes the following steps: first, the minimum value of the plantar pressure area during normal activities is preset as a first threshold, and the plantar pressure area value is collected in real time; then, when it is determined that the plantar pressure area value collected in real time is less than the first threshold, the double foot roll angle value is collected in real time; secondly, the minimum value of the double foot roll angle during normal activities is preset as a second threshold, and the minimum value of the double foot roll angle collected in real time is obtained; finally, when the minimum value of the double foot roll angle collected in real time is less than the second threshold, it is determined that this is a fall state; the algorithm only needs to collect experimental data of normal activities to complete the setting of the threshold, which is more convenient for the elderly to use; the accuracy of fall detection can be guaranteed without collecting fall data.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and specifically to a fall detection algorithm, a control device, a terminal device and a storage medium. Background Art

[0002] As the aging population in my country continues to increase, how to ensure the safety of the elderly has become an important social issue; among the many factors that threaten the safety of the elderly, falls have become one of the important causes of injury or even death among the elderly. After a fall, many elderly people will lie on the ground for a long time and cannot recover or call for help, missing the best time for treatment, which may lead to injury or even death; in response to the above problems, fall detection has become a recent research hotspot, and the algorithms related to fall detection are mainly divided into three categories: machine learning methods, threshold methods, and a combination of the two; machine learning methods require the participation of fall data in their training sets, so this is unrealistic for the elderly, while threshold-based methods are relatively simple and have a fast response speed. Similarly, their training sets also require fall data; therefore, under the premise that fall data is not considered in the training set, designing a fall detection method with a fast response speed is a feasible solution. Summary of the invention

[0003] In view of the above-mentioned defects or deficiencies in the prior art, the present application aims to provide a fall detection algorithm, a control device, a terminal device and a storage medium.

[0004] In a first aspect, the present application provides a fall detection algorithm based on foot parameter changes, comprising the following steps:

[0005] S100: Preset the minimum value of the plantar pressure area under normal activity as a first threshold value, and collect plantar pressure area values ​​in real time;

[0006] S101: When the plantar pressure area value collected in real time is less than the first threshold, collecting the double-foot roll angle value in real time;

[0007] S102: Presetting the minimum value of the bipedal rolling angle during normal activities as a second threshold, and acquiring the minimum value of the bipedal rolling angle collected in real time;

[0008] S103: When the minimum value of the two-foot rolling angle acquired in real time is less than the second threshold, it is determined that the state is a fall.

[0009] According to the technical solution provided in the embodiment of the present application, after obtaining the minimum value of the bipedal rolling angle collected in real time, the following steps are also included:

[0010] S200: when the minimum value of the bipedal rolling angle acquired in real time is greater than or equal to the second threshold, acquiring the maximum value of the bipedal rolling angle acquired in real time;

[0011] S201: The maximum value of the double-foot rolling angle during normal activities is preset as a third threshold value. When the maximum value of the double-foot rolling angle acquired in real time is greater than the third threshold value, it is determined that the state is a fall.

[0012] According to the technical solution provided in the embodiment of the present application, after acquiring the maximum value of the double-foot rolling angle in real time, the following steps are also included:

[0013] S300: When the maximum value of the bipedal roll angle acquired in real time is less than or equal to the third threshold, the bipedal pitch angle value is acquired in real time;

[0014] S301: Presetting a minimum value of the pitch angle of both feet during normal activities as a fourth threshold, and obtaining the minimum value of the pitch angle of both feet collected in real time;

[0015] S302: When the minimum value of the pitch angles of the two feet acquired in real time is less than the fourth threshold, it is determined that the state is a fall.

[0016] According to the technical solution provided in the embodiment of the present application, after obtaining the minimum value of the bipedal pitch angle collected in real time, the following steps are also included:

[0017] S400: When the minimum value of the pitch angle of the two feet collected in real time is greater than or equal to the fourth threshold, obtaining the maximum value of the pitch angle of the two feet collected in real time;

[0018] S401: The maximum value of the pitch angle of both feet during normal activities is preset as a fifth threshold value. When the maximum value of the pitch angle of both feet acquired in real time is greater than the fifth threshold value, it is determined that the state is a fall.

[0019] According to the technical solution provided in the embodiment of the present application, after obtaining the maximum value of the pitch angle of the two feet collected in real time, the following step is also included: when the maximum value of the pitch angle of the two feet collected in real time is less than or equal to the fifth threshold, it is judged as normal activity and the real-time collection of the plantar pressure area is repeated.

[0020] According to the technical solution provided in the embodiment of the present application, the real-time acquisition of the plantar pressure area value includes the following steps:

[0021] S600: Initializing the plantar pressure area value and the number of cycles;

[0022] S601: Preset the number of pressure points on the sole of the foot as a first preset value, and the digital value of each pressure point as a sixth threshold;

[0023] S602: Acquire the number of cycles, and when the number of cycles is less than the first preset value, acquire the digital value of the pressure point at this time;

[0024] S603: When the digital value of the pressure point obtained is greater than or equal to the sixth threshold, the plantar pressure area value is increased by 1, and at the same time, the number of cycles is increased by 1;

[0025] S604: Repeat steps S602-S603 until the number of cycles is equal to the first preset value;

[0026] S605: Output the final plantar pressure area value.

[0027] According to the technical solution provided in the embodiment of the present application, after obtaining the digital value of the pressure point at this time, repeating steps S602-S603 until the number of cycles is equal to the first preset value, also includes: when the digital value of the pressure point obtained is less than the sixth threshold value, the plantar pressure area value remains unchanged, and the number of cycles is increased by 1.

[0028] In a second aspect, the present application proposes a control device for a fall detection algorithm, comprising:

[0029] A first processing module, the first processing module is configured to preset a minimum value of the plantar pressure area of ​​normal activities to a first threshold value, and collect plantar pressure area values ​​in real time;

[0030] a first acquisition module, wherein the first acquisition module is configured to acquire a double-foot roll angle value in real time when the plantar pressure area value acquired in real time is less than the first threshold value;

[0031] A second processing module, the second processing module is configured to preset the minimum value of the bipedal rolling angle during normal activities as a second threshold value, and obtain the minimum value of the bipedal rolling angle collected in real time;

[0032] The first judgment module is configured to judge that the person is in a falling state when the minimum value of the double-foot rolling angle acquired in real time is less than the second threshold value.

[0033] In a third aspect, the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned fall detection algorithm when executing the computer program.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium has a computer program, and wherein the computer program implements the steps of the above-mentioned fall detection algorithm when executed by a processor.

[0035] In summary, the present application proposes a fall detection algorithm, a control device, a terminal device and a storage medium, wherein a fall detection algorithm is based on the change of foot parameters, and the algorithm includes the following steps: first, the minimum value of the plantar pressure area during normal activities is preset as a first threshold, and the plantar pressure area value is collected in real time; then, when it is determined that the plantar pressure area value collected in real time is less than the first threshold, the double foot roll angle value is collected in real time; secondly, the minimum value of the double foot roll angle during normal activities is preset as a second threshold, and the minimum value of the double foot roll angle collected in real time is obtained; finally, when the minimum value of the double foot roll angle collected in real time is less than the second threshold, it is determined that this is a fall state; the present algorithm only needs to collect experimental data of normal activities to complete the threshold setting, which is more convenient for the elderly to use; the accuracy of fall detection can be guaranteed without collecting fall data. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flow chart of a fall detection algorithm provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of the structure of a fall detection algorithm control device provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] Example 1

[0042] As mentioned in the background technology, in response to the problems in the prior art, this application proposes a fall detection algorithm based on the change of foot parameters. In certain specific scenarios, this solution relies on a foot inertial sensor and a plantar pressure insole. The data collected by the foot inertial sensor is processed and then the fall state is judged. The foot inertial sensor is arranged in the plantar pressure insole, and the foot parameters are used to judge whether a fall has occurred. It has strong privacy, is applicable to various occasions, and has low cost. Figure 1 As shown, the algorithm includes the following steps:

[0043] S100: Preset the minimum value of the plantar pressure area under normal activity as a first threshold value, and collect plantar pressure area values ​​in real time;

[0044] Specifically, the user performs a number of normal activities according to his / her own needs and habits, and the normal activities include but are not limited to common human movements such as upright walking, sitting, squatting, jumping, etc.; the set S of the plantar pressure area of ​​a normal activity is calculated according to formula (1): i , calculate the minimum value of the plantar pressure area of ​​the activity according to formula (2), and calculate A of all normal activities according to formula (3) i The minimum value of is taken as th1 (first threshold);

[0045]

[0046] A i =min(S i ) (2)

[0047] th1=min(A i ) (3)

[0048] In formula (1), formula (2) and formula (3), represents the mth plantar pressure area of ​​the ith normal experimental activity; N ADL Represents the type number of normal activities, which can be 1.0KM / h walking, 2.0KM / h walking, 3KM / h running, sit-up, squat-up, jumping, etc.; MAX represents the number of plantar pressure areas collected in this activity;

[0049] S101: When the plantar pressure area value collected in real time is less than the first threshold, the double-foot roll angle value is collected in real time; wherein, although the plantar pressure area in normal activities is generally not less than the first threshold, it may be less than the first threshold in some special activities, so when the plantar pressure area value collected in real time is less than the first threshold, it is necessary to further determine whether it is a fall state through the foot angle; the plantar pressure insole is provided with the foot inertia sensor, which can collect the double-foot roll angle value in real time;

[0050] S102: Presetting the minimum value of the bipedal rolling angle during normal activities as a second threshold, and acquiring the minimum value of the bipedal rolling angle collected in real time;

[0051] According to formula (4), the set R of the bipedal rolling angles of a normal activity is obtained: i , and then according to formula (5) to find the minimum value R of the double-foot rolling angle of this activity imin Finally, according to formula (6), the threshold th2 (second threshold) of the bipedal rolling angle is solved;

[0052]

[0053] R imin =min(R i ) (5)

[0054] th2=min(R imin ) (6)

[0055] In formula (4), formula (5) and formula (6), represents the mth bipedal rolling angle of the ith normal experimental activity; N ADL Represents the type number of normal activities, which can be 1.0KM / h walking, 2.0KM / h walking, 3KM / h running, sit-up, squat-up, jump, etc.; MAX represents the number of bipedal roll angles collected in this activity;

[0056] S103: when the minimum value of the two-foot rolling angle acquired in real time is less than the second threshold, determining that the state is a fall;

[0057] Specifically, the minimum value of the double-foot roll angle values ​​collected in real time by the foot inertial sensor is obtained and compared with the second threshold value. Since the double-foot roll angle will not be less than the second threshold value during normal activities, when the minimum value of the double-foot roll angle values ​​collected in real time is less than the second threshold value, it can be determined that this is a fall state. In this solution, the threshold setting can be completed by collecting only the experimental data of normal activities, which is more convenient for the elderly to use. The accuracy of fall detection can be guaranteed without collecting fall data.

[0058] In certain specific scenarios, the priority of the plantar pressure area detection is higher than the foot angle information detection, considering that the foot angle may change greatly under normal gait, and once the human body falls, the plantar pressure may decrease sharply or even approach 0, and the change is large and easy to detect; the judgment of the double-foot roll angle can effectively screen out gait movements such as jumping that cause excessive changes in the foot pressure area, thereby improving the accuracy of determining whether it is a fall state.

[0059] Furthermore, after obtaining the minimum value of the bipedal rolling angle collected in real time, the following steps are also included:

[0060] S200: when the minimum value of the bipedal rolling angle acquired in real time is greater than or equal to the second threshold, acquiring the maximum value of the bipedal rolling angle acquired in real time;

[0061] In certain specific scenarios, it is normal for the minimum value of the bipedal rolling angle to be greater than or equal to the second threshold value during normal activities, so it is necessary to further determine whether the current maximum value of the bipedal rolling angle is within the normal range;

[0062] S201: Preset the maximum value of the bipedal rolling angle during normal activities as a third threshold value, and when the maximum value of the bipedal rolling angle acquired in real time is greater than the third threshold value, determine that the state is a fall;

[0063] First, according to formula (7), the set R of the foot roll angle of a normal activity is obtained: i , then, according to formula (8), the maximum roll angle R of this activity is calculated imax Finally, the rolling angle threshold th3 (third threshold) is solved according to formula (9);

[0064]

[0065] R imax =max(R i ) (8)

[0066] th3=max(R imax ) (9)

[0067] In formula (7), formula (8) and formula (9), represents the mth bipedal rolling angle of the ith normal experimental activity; N ADL Represents the type number of normal activities, which can be 1.0KM / h walking, 2.0KM / h walking, 3KM / h running, sit-up, squat-up, jump, etc.; MAX represents the number of bipedal roll angles collected in this activity;

[0068] Specifically, the maximum value of the double-foot roll angle values ​​collected in real time by the foot inertial sensor is obtained and compared with the third threshold value. Since the double-foot roll angle will never be greater than the third threshold value during normal activities, when the maximum value of the double-foot roll angle values ​​collected in real time is greater than the third threshold value, it can be determined that the condition is a fall.

[0069] Furthermore, after acquiring and collecting the maximum value of the bipedal rolling angle in real time, the method further includes the following steps:

[0070] S300: When the maximum value of the bipedal roll angle acquired in real time is less than or equal to the third threshold, the bipedal pitch angle value is acquired in real time;

[0071] In certain specific scenarios, it is normal that the maximum value of the bipedal roll angle in normal activities is less than or equal to the third threshold value, so it is necessary to further determine whether the current bipedal pitch angle collected in real time by the foot inertial sensor is within the normal range;

[0072] S301: Presetting a minimum value of the pitch angle of both feet during normal activities as a fourth threshold, and obtaining the minimum value of the pitch angle of both feet collected in real time;

[0073] First, according to formula (10), the set P of the bipedal pitch angles in a normal activity is obtained: i , and then, according to formula (11), the minimum value P of the bipedal pitch angle of this activity is obtained: imin Finally, the threshold th4 (fourth threshold) of the bipedal pitch angle is solved according to formula (12);

[0074]

[0075] P imin =min(P i ) (11)

[0076] th4=min(P imin ) (12)

[0077] In formula (10), formula (11) and formula (12), represents the mth bipedal pitch angle of the ith normal experimental activity; N ADL Represents the type number of normal activities, which can be 1.0KM / h walking, 2.0KM / h walking, 3KM / h running, sit-up, squat-up, jump, etc.; MAX represents the number of bipedal pitch angles collected in this activity;

[0078] S302: When the minimum value of the pitch angles of the two feet acquired in real time is less than the fourth threshold, it is determined that the state is a fall;

[0079] Specifically, the minimum value of the pitch angle values ​​of the two feet collected in real time by the foot inertial sensor is obtained and compared with the fourth threshold value. Since the pitch angle of the two feet will never be less than the fourth threshold value during normal activities, when the minimum value of the roll angle values ​​of the two feet collected in real time is less than the fourth threshold value, it can be determined that the state is a fall.

[0080] Furthermore, after obtaining the minimum value of the bipedal pitch angle collected in real time, the following steps are also included:

[0081] S400: When the minimum value of the pitch angle of the two feet collected in real time is greater than or equal to the fourth threshold, obtaining the maximum value of the pitch angle of the two feet collected in real time;

[0082] In certain specific scenarios, it is normal for the minimum value of the bipedal pitch angle in normal activities to be greater than or equal to the fourth threshold value, so it is necessary to further determine whether the current maximum value of the bipedal pitch angle collected in real time by the foot inertial sensor is within the normal range;

[0083] S401: Preset the maximum value of the pitch angle of both feet during normal activities as a fifth threshold value, and when the maximum value of the pitch angle of both feet acquired in real time is greater than the fifth threshold value, determine that the state is a fall;

[0084] First, according to formula (13), the set P of the bipedal pitch angles in a normal activity is obtained: i , and then, according to formula (14), the maximum value P of the pitch angle of the two feet in this activity is obtained imax Finally, the threshold th5 (fifth threshold) of the bipedal pitch angle is solved according to formula (15);

[0085]

[0086] P imax =max(P i ) (14)

[0087] th5=max(P imax ) (15)

[0088] In formula (13), formula (14) and formula (15), represents the mth bipedal pitch angle of the ith normal experimental activity; N ADL Represents the type number of normal activities, which can be 1.0KM / h walking, 2.0KM / h walking, 3KM / h running, sit-up, squat-up, jump, etc.; MAX represents the number of bipedal pitch angles collected in this activity;

[0089] Specifically, the maximum value of the pitch angle values ​​of both feet collected in real time by the foot inertial sensor is obtained and compared with the fifth threshold value. Since the pitch angle of both feet will never be greater than the fifth threshold value during normal activities, when the maximum value of the roll angle values ​​of both feet collected in real time is greater than the fifth threshold value, it can be determined that the condition is a fall.

[0090] Furthermore, after obtaining the maximum value of the pitch angles of the two feet collected in real time, the following steps are also included: when the maximum value of the pitch angles of the two feet collected in real time is less than or equal to the fifth threshold, it is determined to be a normal activity and the real-time collection of the plantar pressure area is repeated; in certain specific scenarios, it is normal for the maximum value of the pitch angles of the two feet to be less than or equal to the fifth threshold during normal activities, so it can be determined that this is a normal activity and there is no fall state;

[0091] In addition, during the specific execution of the algorithm, the maximum and minimum values ​​of the bipedal roll angle or the bipedal pitch angle are compared with the set corresponding thresholds, rather than comparing each bipedal roll angle and bipedal pitch angle with the corresponding thresholds, thereby saving the execution time of the program.

[0092] Furthermore, the real-time acquisition of plantar pressure area values ​​comprises the following steps:

[0093] S600: Initializing the plantar pressure area value and the number of cycles; in certain specific scenarios, during the initialization phase, the plantar pressure area value is set to 0, and the number of cycles is the number of effective pressure points of the plantar pressure insole, which is also set to 0 during the initialization phase;

[0094] S601: The number of pressure points on the sole of the foot is preset as the first preset value, and the digital value of each pressure point is the sixth threshold value; in certain specific scenarios, the sole pressure insole collects a total of 198 sole pressure points, so the first preset value is 198; in addition, the sole pressure insole is provided with a sole pressure film sensor, and due to the sole zero drift, if there is no pressure, the data of the sole pressure film sensor will not be 0, so it is necessary to consider the zero drift to set the digital value of each pressure point, that is, the sixth threshold value; in this solution, after a large number of experiments and calculations, the value of the sixth threshold value is set to 5;

[0095] S602: Obtain the number of cycles. When the number of cycles is less than the first preset value, obtain the digital value of the pressure point at this time. Specifically, first determine whether the value of the number of cycles is less than the corresponding number of pressure points of the plantar pressure insole. If it is less than 198, enter the area calculation stage to obtain the digital value of the pressure point at this time.

[0096] S603: When the digital value of the pressure point obtained is greater than or equal to the sixth threshold, the plantar pressure area value is increased by 1, and at the same time, the number of cycles is increased by 1; wherein, when it is determined that the digital value of the pressure point obtained is greater than or equal to 5, the pressure point is determined to be a valid pressure point, so the plantar pressure area and the number of cycles are both increased by 1;

[0097] S604: Repeat steps S602-S603 until the number of cycles is equal to the first preset value;

[0098] S605: Outputting the final foot pressure area value;

[0099] Specifically, after the number of cycles is increased by 1, the process is re-entered to determine whether the value of the number of cycles is less than 198 and whether the digital value of the pressure point obtained is greater than or equal to 5; and steps S602-S603 are repeated until the number of cycles is equal to 198, and the accumulated plantar pressure area value at this time is output.

[0100] Further, after obtaining the digital value of the pressure point at this time, the steps S602-S603 are repeatedly performed until the number of cycles is equal to the first preset value, and further includes: when the digital value of the pressure point obtained is less than the sixth threshold value, the plantar pressure area value remains unchanged, and the number of cycles is increased by 1; in certain specific scenarios, when there is no pressure, the digital value of the pressure point will not be less than 5, so when the digital value of the pressure point obtained is less than 5, it is determined that the pressure point is an invalid point at this time, so it is not accumulated in the plantar pressure area value, and the number of cycles is increased only once;

[0101] Specifically, the plantar pressure area is calculated by the valid point set collected by the plantar pressure film sensor. The method of ignoring invalid points can also ensure faster calculation speed and eliminate the error caused by the zero point drift of the plantar pressure film sensor.

[0102] Example 2

[0103] Based on Example 1, the present application proposes a control device for a fall detection algorithm, such as Figure 2 As shown, including:

[0104] A first processing module, the first processing module is configured to preset a minimum value of the plantar pressure area of ​​normal activities to a first threshold value, and collect plantar pressure area values ​​in real time;

[0105] a first acquisition module, wherein the first acquisition module is configured to acquire a double-foot roll angle value in real time when the plantar pressure area value acquired in real time is less than the first threshold value;

[0106] A second processing module, the second processing module is configured to preset a minimum value of the bipedal rolling angle during normal activities as a second threshold value, and obtain a maximum value of the bipedal rolling angle collected in real time;

[0107] A first judgment module, wherein the first judgment module is configured to judge that the person is in a falling state when the maximum value of the bipedal rolling angle acquired in real time is greater than the second threshold value;

[0108] Example 3

[0109] This embodiment 3 provides a terminal device based on the embodiments 1 and 2, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: when the processor executes the computer program, the steps of the above-mentioned fall detection algorithm are implemented;

[0110] like Figure 3 As shown, it shows a schematic diagram of the structure of a computer system 700 of a terminal device or server suitable for implementing an embodiment of the present application;

[0111] The computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703; various programs and data required for the operation of the system 700 are also stored in the RAM 703; the CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704; an input / output (I / O) interface 705 is also connected to the bus 704;

[0112] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc.; the communication section 709 performs communication processing via a network such as the Internet; a drive 710 is also connected to the I / O interface 705 as needed; a removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed;

[0113] In particular, according to the embodiments of the present application, the above reference Figure 1 The described processes may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising a computer program for executing Figure 1 in such an embodiment, the computer program may be downloaded and installed from a network via the communication section 709, and / or installed from a removable medium 711;

[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention; in this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, and the module, program segment, or a portion of a code contains one or more executable instructions for implementing the specified logical functions; it should also be noted that in some alternative implementations, the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings; for example, two boxes represented in succession may actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved; it should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0115] Example 4

[0116] The fourth embodiment of the present application also provides a computer-readable storage medium, which has a computer program, and is characterized in that when the computer program is executed by a processor, the steps of the above-mentioned fall detection algorithm are implemented; the computer-readable storage medium can be the computer-readable storage medium included in the device described in the above embodiment; it can also be a computer-readable storage medium that exists independently and is not assembled into the device; the computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the steps of the fall detection algorithm described in Example 1.

[0117] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and its core ideas of this application. The above is only the preferred implementation method of this application. It should be pointed out that due to the limitations of textual expression and the objective existence of infinite specific structures, ordinary technicians in this technical field can make several improvements, modifications or changes without departing from the principles of the present invention, and can also combine the above technical features in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the inventive concept and technical solution to other occasions without improvement, should be regarded as the scope of protection of this application.

Claims

1. A fall detection algorithm based on foot parameter changes, characterized in that: The algorithm consists of the following steps: S100: Preset the minimum value of the plantar pressure area under normal activity as a first threshold value, and collect plantar pressure area values ​​in real time; S101: When the plantar pressure area value collected in real time is less than the first threshold, collecting the double-foot roll angle value in real time; S102: Presetting the minimum value of the bipedal rolling angle during normal activities as a second threshold, and acquiring the minimum value of the bipedal rolling angle collected in real time; S103: when the minimum value of the two-foot rolling angle acquired in real time is less than the second threshold, determining that the state is a fall; According to formula (1), the set Si of the plantar pressure area of ​​the normal activity is calculated, according to formula (2), the minimum value of the plantar pressure area of ​​the activity is calculated, and according to formula (3), the minimum value of Ai of all normal activities is calculated as the first threshold th1; ， ， （1） （2） （3） In formula (1), formula (2) and formula (3), It represents the mth plantar pressure area of ​​the ith normal experimental activity; Represents the type number of normal activities; MAX represents the number of plantar pressure areas collected during this activity; According to formula (4), the set Ri of the bipedal rolling angles of the normal activity is obtained, and then according to formula (5), the minimum value Rimin of the bipedal rolling angles of the activity is obtained, and finally according to formula (6), the second threshold value th2 of the bipedal rolling angle is obtained; ， ， （4） （5） （6） In formula (4), formula (5) and formula (6), It represents the mth bipedal rolling angle of the ith normal experimental activity; Represents the type number of normal activities; MAX represents the number of bipedal roll angles collected in this activity; The minimum value of the bipedal rolling angle is compared with a set corresponding threshold value instead of comparing each bipedal rolling angle with a corresponding threshold value, thus saving program execution time.

2. The fall detection algorithm according to claim 1, characterized in that: After obtaining the minimum value of the bipedal rolling angle collected in real time, the following steps are also included: S200: when the minimum value of the bipedal rolling angle acquired in real time is greater than or equal to the second threshold, acquiring the maximum value of the bipedal rolling angle acquired in real time; S201: The maximum value of the double-foot rolling angle during normal activities is preset as a third threshold value. When the maximum value of the double-foot rolling angle acquired in real time is greater than the third threshold value, it is determined that the state is a fall.

3. The fall detection algorithm according to claim 2, characterized in that: After acquiring the maximum value of the bipedal rolling angle in real time, the following steps are also included: S300: When the maximum value of the bipedal roll angle acquired in real time is less than or equal to the third threshold, the bipedal pitch angle value is acquired in real time; S301: Presetting a minimum value of the pitch angle of both feet during normal activities as a fourth threshold, and obtaining the minimum value of the pitch angle of both feet collected in real time; S302: When the minimum value of the pitch angles of the two feet acquired in real time is less than the fourth threshold, it is determined that the state is a fall.

4. The fall detection algorithm according to claim 3, characterized in that: After obtaining the minimum value of the bipedal pitch angle collected in real time, the following steps are also included: S400: When the minimum value of the pitch angle of the two feet collected in real time is greater than or equal to the fourth threshold, obtaining the maximum value of the pitch angle of the two feet collected in real time; S401: The maximum value of the pitch angle of both feet during normal activities is preset as a fifth threshold value. When the maximum value of the pitch angle of both feet acquired in real time is greater than the fifth threshold value, it is determined that the state is a fall.

5. The fall detection algorithm according to claim 4, characterized in that: After obtaining the maximum value of the pitch angles of the two feet collected in real time, the following step is also included: when the maximum value of the pitch angles of the two feet collected in real time is less than or equal to the fifth threshold, it is judged as normal activity and the real-time collection of the plantar pressure area is repeated.

6. The fall detection algorithm according to claim 5, characterized in that: The real-time acquisition of plantar pressure area values ​​comprises the following steps: S600: Initializing the plantar pressure area value and the number of cycles; S601: Preset the number of pressure points on the sole of the foot as a first preset value, and the digital value of each pressure point as a sixth threshold; S602: Acquire the number of cycles, and when the number of cycles is less than the first preset value, acquire the digital value of the pressure point at this time; S603: When the digital value of the pressure point obtained is greater than or equal to the sixth threshold, the plantar pressure area value is increased by 1, and at the same time, the number of cycles is increased by 1; S604: Repeat steps S602-S603 until the number of cycles is equal to the first preset value; S605: Output the final plantar pressure area value.

7. The fall detection algorithm according to claim 6, characterized in that: After obtaining the digital value of the pressure point at this time, repeating steps S602-S603 until the number of cycles is equal to the first preset value, further includes: when the digital value of the pressure point obtained is less than the sixth threshold value, the plantar pressure area value remains unchanged, and the number of cycles is increased by 1.

8. A control device for a fall detection algorithm, characterized in that: include: A first processing module, the first processing module is configured to preset a minimum value of the plantar pressure area of ​​normal activities to a first threshold value, and collect plantar pressure area values ​​in real time; a first acquisition module, wherein the first acquisition module is configured to acquire a double-foot roll angle value in real time when the plantar pressure area value acquired in real time is less than the first threshold value; A second processing module, the second processing module is configured to preset the minimum value of the bipedal rolling angle during normal activities as a second threshold value, and obtain the minimum value of the bipedal rolling angle collected in real time; a first judgment module, wherein the first judgment module is configured to judge that the falling state is in progress when the minimum value of the two-foot rolling angle acquired in real time is less than the second threshold value; According to formula (1), the set Si of the plantar pressure area of ​​the normal activity is calculated, according to formula (2), the minimum value of the plantar pressure area of ​​the activity is calculated, and according to formula (3), the minimum value of Ai of all normal activities is calculated as the first threshold th1; ， ， （1） （2） （3） In formula (1), formula (2) and formula (3), It represents the mth plantar pressure area of ​​the ith normal experimental activity; Represents the type number of normal activities; MAX represents the number of plantar pressure areas collected during this activity; According to formula (4), the set Ri of the bipedal rolling angles of the normal activity is obtained, and then according to formula (5), the minimum value Rimin of the bipedal rolling angles of the activity is obtained, and finally according to formula (6), the second threshold value th2 of the bipedal rolling angle is obtained; ， ， （4） （5） （6） In formula (4), formula (5) and formula (6), It represents the mth bipedal rolling angle of the ith normal experimental activity; Represents the type number of normal activities; MAX represents the number of bipedal roll angles collected in this activity; The minimum value of the bipedal rolling angle is compared with a set corresponding threshold value instead of comparing each bipedal rolling angle with a corresponding threshold value, thus saving program execution time.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the fall detection algorithm according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, the computer-readable storage medium having a computer program, characterized in that: When the computer program is executed by a processor, the steps of the fall detection algorithm according to any one of claims 1 to 7 are implemented.

Images