High-altitude falling detection method and system based on mobile terminal multi-sensor fusion

Abstract

The invention provides a high-altitude falling detection method based on mobile terminal multi-sensor fusion, and the method comprises the steps: collecting the multi-sensor data of a mobile terminal, and carrying out the preprocessing of the multi-sensor data; processing the preprocessed multi-sensor data to obtain key features of high-altitude falling detection; and based on the high-altitude falling detection key features, high-altitude falling is detected. Through the method disclosed by the invention, whether the high-altitude operation personnel fall can be effectively monitored and identified, an intelligent safety guarantee means is provided for personnel in remote or dangerous environments such as high-altitude operation, field investigation, field exploration, field travel and the like, the response time after an accident occurs is shortened, and the safety of the personnel is improved. Therefore, the life safety of personnel is effectively guaranteed. The method is high in detection accuracy and has portability, usability and real-time performance.

Description

Technical Field

[0001] This invention relates to the field of attitude detection technology, and in particular to a method and system for detecting falls from heights based on multi-sensor fusion of mobile terminals. Background Technology

[0002] In field operations such as geological surveys, field collection, mineral exploration, and outdoor travel, personnel are often in isolated, remote, or dangerous environments. In the event of an accident such as a fall or loss of consciousness, timely detection and accurate location for rescue are crucial. Traditional fall detection methods rely on physical protective equipment such as safety belts and safety nets. However, these devices may be improperly worn or damaged due to aging, making it impossible to monitor the actual condition of workers in real time and issue timely warnings.

[0003] With the widespread adoption of smart mobile terminals, especially smartphones, their built-in high-precision sensors, such as accelerometers, gyroscopes, barometers, and satellite positioning sensors, provide technical support for safety monitoring of field personnel. These sensors can acquire users' movement status and geographical location data in real time. Currently, the common approach is to monitor health or record general movement status using smartphones or fitness trackers, but there is a lack of solutions that utilize the built-in sensors of smart mobile terminals to monitor whether field personnel have fallen from heights and whether they have lost consciousness after a fall. To address these issues, this invention proposes a fall detection algorithm based on the fusion of data from multiple sensors on a smart mobile terminal. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes a method and system for detecting falls from heights based on multi-sensor fusion of mobile terminals.

[0005] In a first aspect, embodiments of the present invention provide a method for detecting falls from heights based on multi-sensor fusion of mobile terminals, including:

[0006] Collect multi-sensor data from the mobile terminal and preprocess the multi-sensor data;

[0007] The preprocessed multi-sensor data is processed to obtain key features for fall detection from height;

[0008] Based on the aforementioned key features for detecting falls from heights, falls from heights are detected.

[0009] Furthermore, the multi-sensor data includes at least accelerometer data, gyroscope data, barometer data, and satellite positioning sensor data.

[0010] Furthermore, the multi-sensor data is preprocessed, specifically including filtering and denoising preprocessing of the multi-sensor data, using a first-order low-pass filter, the formula of which is as follows:

[0011]

[0012] Where y[i] is the current filter output value, x[i] is the current sample value, and y[i-1] is the previous filter output value. The formula shows that the current filter output value is the weighted average of the current sample value and the previous filter output value, where the weights are α and 1-α, respectively, and α is the filter coefficient, which is between 0 and 1.

[0013] Furthermore, the key features for fall detection from height include composite acceleration, composite angular velocity, change in height and rate of change, and rate of change in position; wherein, the formula for calculating composite acceleration is:

[0014]

[0015] For the synthesis acceleration, , , These represent the accelerations of the accelerometer along the x, y, and z axes, respectively.

[0016] The formula for calculating the resultant angular velocity is:

[0017]

[0018] For the synthesis acceleration, , , These are the angular velocities of the accelerometer along the x, y, and z axes, respectively.

[0019] Furthermore, barometer data is continuously monitored, and the change in altitude and rate of change are calculated in real time based on the change in air pressure; the change in position and rate of change are calculated based on satellite positioning sensor data.

[0020] Furthermore, based on the aforementioned key features for detecting falls from heights, the detection of falls from heights is performed, specifically including the following steps:

[0021] Set a fall detection threshold, which includes a weightlessness detection threshold, an impact detection threshold, a posture change detection threshold, and a height change detection threshold;

[0022] The synthesized acceleration is compared with a weightlessness detection threshold to obtain the duration during which the synthesized acceleration is less than the weightlessness detection threshold. If the duration is greater than a preset duration threshold, the current state is determined to be weightlessness.

[0023] Once a weightlessness state is detected, the composite acceleration is further evaluated. If the composite acceleration exceeds the impact detection threshold within a preset time, the current state is determined to be an impact state.

[0024] After the impact state detection is completed, the gyroscope data is used to compare the synthesized angular velocity value with the attitude change detection threshold during weightlessness and impact. When the synthesized angular velocity value is greater than the attitude change detection threshold, the current state is determined to be an attitude change state.

[0025] After the attitude change detection is completed, the air pressure at the beginning of weightlessness and at the end of weightlessness are obtained using barometer data. The air pressure rise during weightlessness is calculated and compared with the altitude change detection threshold. If the air pressure rise is greater than or equal to the altitude change detection threshold, it is determined that the current state is an altitude change state.

[0026] When weightlessness, impact, attitude change, and altitude change are detected simultaneously, the current state is detected as a fall from a height.

[0027] Furthermore, the detection of falls from heights includes the following specific steps:

[0028] After detecting that the current state is a fall from a height, the system will also detect the static state. Based on the real-time satellite positioning data, the system compares the current sampled positioning coordinates with the previous sampled positioning coordinates. When there is no significant change in position, the system obtains the cumulative time during which the position does not change. When the cumulative time is greater than a preset time, the system determines that the current state is a static state after a fall from a height.

[0029] Furthermore, when a fall from a height is detected, an alarm mechanism will be triggered, and precise location information will be sent to a preset emergency contact using satellite positioning data.

[0030] Secondly, embodiments of the present invention disclose a high-altitude fall detection system based on multi-sensor fusion of a mobile terminal, comprising a multi-sensor data preprocessing unit, a key feature acquisition unit, and a high-altitude fall detection unit; wherein:

[0031] A multi-sensor data preprocessing unit is used to collect multi-sensor data from a mobile terminal and preprocess the multi-sensor data.

[0032] The key feature acquisition unit is used to process the preprocessed multi-sensor data to obtain key features for fall detection from height.

[0033] A fall from height detection unit is used to detect falls from height based on the aforementioned key features of fall from height detection.

[0034] Thirdly, an electronic device, characterized in that it comprises:

[0035] One or more processors;

[0036] Memory, used to store one or more programs;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the detection method.

[0038] This invention provides a method for detecting falls from heights based on multi-sensor fusion on a mobile terminal. The method involves collecting multi-sensor data from a mobile terminal, preprocessing the data, further processing the preprocessed data to obtain key features for fall detection, and then detecting falls based on these key features. This method effectively monitors and identifies whether workers at heights have fallen, providing an intelligent safety measure for personnel in remote or dangerous environments such as those working at heights, conducting field surveys, exploring the wilderness, or traveling in the wild. It reduces reaction time after an accident, thereby effectively protecting personnel's lives. This invention features high detection accuracy, portability, ease of use, and real-time performance. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating a high-altitude fall detection method based on multi-sensor fusion of a mobile terminal, provided in an embodiment of the present invention.

[0040] Figure 2 This is a structural block diagram of a high-altitude fall detection system based on multi-sensor fusion of a mobile terminal, provided in an embodiment of the present invention.

[0041] Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0042] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0043] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0044] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0045] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0046] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0047] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0048] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides a method for detecting falls from heights based on multi-sensor fusion of mobile terminals.

[0049] This embodiment discloses a high-altitude fall detection method based on multi-sensor fusion of mobile terminals, such as... Figure 1 ,include:

[0050] S100. Collect multi-sensor data from the mobile terminal and preprocess the multi-sensor data; in this embodiment, the multi-sensor data includes at least accelerometer data, gyroscope data, barometer data, and satellite positioning sensor data.

[0051] Specifically, the sensor management objects built into the smart mobile terminal (such as SensorManager in Android and CMMotionManager in iOS) can monitor and acquire sensor data such as accelerometers, gyroscopes, and barometers in real time according to the set frequency. The location management objects (such as LocationManager in Android and CLLocationManager in iOS) can acquire the location information of satellite positioning sensors in real time according to the set frequency.

[0052] Accelerometer data is a ternary array of acceleration [x, y, z] along the x, y, and z axes. It can detect changes in the phone's acceleration along these three axes, helping to measure the phone's instantaneous acceleration or deceleration. The sensor data increases as the phone moves in any direction, and remains stable when the phone is stationary. With the phone flat on a table, the x-axis is 0, the y-axis is 0, and the z-axis is 1g (9.81 m / sec^2). When the phone is in free fall, in the weightless phase, the acceleration is 0. During the impact phase, a very large peak impact acceleration is generated in a very short time (milliseconds), generally much greater than 1g, reaching tens or even hundreds of g.

[0053] The gyroscope provides angular acceleration data along the x, y, and z axes [x, y, z]. It measures the angular velocity of an object rotating around the X, Y, and Z axes, thereby determining the phone's rotation status. It can accurately measure rotation and deflection movements (rotation and changes in direction).

[0054] The barometer data is the instantaneous air pressure value, and the altitude can be calculated based on the air pressure value.

[0055] Satellite positioning sensors achieve user location by receiving satellite information. Satellite positioning data mainly includes geographic coordinates (latitude, longitude), altitude, speed, azimuth, etc.

[0056] Typically, sensor data such as accelerometer data obtained through the phone's system API has been filtered by its built-in low-pass filter. This effectively reduces false alarms caused by noise, making the sensor data more stable and reliable, and improving the accuracy of drop detection algorithms. However, for data that has not undergone low-pass filtering or requires secondary filtering, manual filtering can be performed using a first-order low-pass filter formula. For example, satellite positioning data often has significant positional offsets, and barometric pressure data is frequently affected by various noise interferences. Secondary filtering can more effectively remove high-frequency noise and outliers, reduce systematic and random errors, improve data quality, and make the data smoother and more stable, which is especially important for applications requiring high-precision data.

[0057] In this embodiment, the multi-sensor data is preprocessed, specifically including filtering and denoising preprocessing. The filtering is performed using a first-order low-pass filter, the formula of which is as follows:

[0058]

[0059] Where y[i] is the current filtered output value, x[i] is the current sampled value, and y[i-1] is the previous filtered output value, the formula shows that the current filtered output value is a weighted average of the current sampled value and the previous filtered output value, with weights of α and 1-α, respectively. α is the filtering coefficient, ranging from 0 to 1. A smaller α value will smooth the signal more strongly, but may also cause a slower signal response; a larger α value will retain more high-frequency components. Users can customize this value according to their actual needs.

[0060] S200. The preprocessed multi-sensor data is processed to obtain key features for fall detection from height; in this embodiment, the key features for fall detection from height include synthetic acceleration, synthetic angular velocity, change in height and rate of change, and rate of change in position.

[0061] The composite acceleration is calculated based on continuously monitored triaxial acceleration data from the accelerometer. The formula for calculating the composite acceleration is as follows:

[0062]

[0063] For the synthesis acceleration, , , These represent the accelerations of the accelerometer along the x, y, and z axes, respectively.

[0064] The formula for calculating the resultant angular velocity is:

[0065]

[0066] For the synthesis acceleration, , , These are the angular velocities of the accelerometer along the x, y, and z axes, respectively.

[0067] In this embodiment, continuously monitored barometer data is used to calculate the change in altitude (Δh) and the rate of change (dh / dt) in real time based on the change in air pressure (Δp). Altitude can be estimated based on the air pressure reference value of 1013.25 hPa at sea level and the air pressure after impact. The change in position (Δs) and the rate of change (ds / dt) are calculated based on continuously monitored positioning coordinate information.

[0068] S300. Based on the aforementioned key features for detecting falls from heights, fall detection is performed. In this embodiment, the specific steps for detecting falls from heights based on the aforementioned key features include:

[0069] S301. Set a fall detection threshold, wherein the fall detection threshold includes a weightlessness detection threshold, an impact detection threshold, a posture change detection threshold, and a height change detection threshold;

[0070] S302. Compare the synthesized acceleration with the weightlessness detection threshold to obtain the duration during which the synthesized acceleration is less than the weightlessness detection threshold. If the duration is greater than a preset duration threshold, then it is determined that the current state is weightlessness.

[0071] Specifically, the synthetic acceleration 'a' is continuously monitored. If 'a' remains below the threshold 'FREE_FALL_ACC' (0.4g) for a period of time 'FREE_FALL_MIN_DURATION' (600 milliseconds), it is considered a possible state of weightlessness. This is a necessary condition for determining that a fall has occurred.

[0072] When the initial weightlessness time (a) is less than 0.4g, record the weightlessness start time (freeFallStartTime) and set the weightlessness state activation to true.

[0073] When 'a' is detected to be greater than 0.4g, it indicates the end of the weightlessness state. If the weightlessness state activation is true at this time, the free fall time difference freeFallDuration = Date.now() - freeFallStartTime is calculated. If freeFallDuration is greater than or equal to the minimum weightlessness duration threshold FREE_FALL_MIN_DURATION (600 milliseconds), then weightlessness is determined to have occurred, and the weightlessness counter is incremented by 1.

[0074] S303. After detecting a weightless state, continue to judge the composite acceleration. If the composite acceleration is greater than the impact detection threshold within a preset time, it is judged that the current state is an impact state. Specifically, after the weightless state ends, if the value of a is detected to be greater than the impact acceleration threshold (3.5g) in a very short time (a few milliseconds to tens of milliseconds), it is considered that an impact has occurred and the impact flag is set to true.

[0075] S304. After the impact state detection is completed, the synthesized angular velocity value is compared with the attitude change detection threshold using gyroscope data during weightlessness and impact. If the synthesized angular velocity value is greater than the attitude change detection threshold, the current state is determined to be an attitude change state.

[0076] Specifically, using gyroscope data, the amplitude and pattern of angular velocity changes of the phone / human body during weightlessness and impact are calculated. When the detected composite angular velocity b is greater than the rotational speed threshold ROTATION_SPEED (5.0 rad / s), it is determined that the device is rotating violently.

[0077] S305. After the attitude change detection is completed, the barometer data is used to obtain the air pressure at the beginning of weightlessness and the air pressure at the end of weightlessness, and the air pressure rise value during weightlessness is calculated. The air pressure rise value is compared with the altitude change detection threshold. If the air pressure rise value is greater than or equal to the altitude change detection threshold, it is determined that the current state is an altitude change state.

[0078] Specifically, the air pressure value is continuously monitored. The start of weightlessness is marked as pressureStart, and the end of weightlessness is marked as pressureEnd. During the freeFallDuration of the fall, the air pressure rise Δp = pressureEnd - pressureStart. If Δp is greater than or equal to the air pressure rise threshold PRESSURE_DROP (0.8 hPa), it is determined that the equipment height has decreased significantly and rapidly.

[0079] In addition, the altitude before and after the fall and the change in altitude Δh can be calculated using the following formula:

[0080] H = 44300 * (1 - (P / P0)^(1 / 5.256))

[0081] Where: H—altitude, P0=atmospheric pressure (0℃, 101.325kPa)

[0082] S306. When weightlessness, impact, attitude change, and altitude change are detected simultaneously, the current state is determined to be a fall from a height. Specifically, the delay trigger function `setTimeout()` is started to determine whether an impact occurred immediately after the free fall, i.e., within the impact detection window time threshold `IMPACT_WINDOW_AFTER_FREE_FALL` (500 milliseconds). If an impact occurred, i.e., the impact flag is set to true, subsequent barometric pressure detection and rollover status checks are performed; if no impact occurred, it is considered a false alarm, and subsequent barometric pressure detection and rollover status checks are not performed. Afterward, the impact flag is set to false.

[0083] In this embodiment, the multi-sensor fusion is ANDed with the logic "AND", meaning that multiple conditions such as weightlessness, strong impact, violent rotation, and sudden increase in air pressure must be met simultaneously for a fall to be determined.

[0084] If weightlessness and impact occur simultaneously with a rapid and significant increase in air pressure and violent rotation, it is considered a high-confidence fall event, and an emergency response is initiated. If either a rapid and significant increase in air pressure or violent rotation occurs, it is considered a medium-confidence fall event, requiring manual confirmation. If neither occurs, and only weightlessness and impact are present, it is considered a low-confidence event, which may be a false alarm.

[0085] In some preferred embodiments, the detection of falls from heights further includes the following steps:

[0086] After detecting that the current state is a fall from a height, the system will also detect the static state. Based on the real-time satellite positioning data, the system compares the current sampled positioning coordinates with the previous sampled positioning coordinates. When there is no significant change in position, the system obtains the cumulative time during which the position does not change. When the cumulative time is greater than a preset time, the system determines that the current state is a static state after a fall from a height.

[0087] Among these, static detection is a crucial factor in identifying whether a person has fallen. After a real fall impact, sensor data typically enters a relatively static or abnormal state (injury), while after a phone drop or jump, the user quickly regains activity. Based on real-time acquired satellite positioning data, the latest positioning coordinates (latitude, longitude) are compared with the previously memorized coordinates. When there is no significant change in position, time t is accumulated. When t is greater than or equal to STATIONARY_TIME (1,800,000 ms), it is determined that the person is severely injured or unconscious, rendering them unable to move.

[0088] In some preferred embodiments, machine learning models can be used to collect a large amount of sensor data from normal activities and simulated falls, and to train classification models (such as SVM, random forest, deep learning RNN / LSTM) to learn to distinguish complex patterns between falls and various false alarm scenarios, which can effectively improve accuracy.

[0089] In some preferred embodiments, upon detecting a fall or loss of consciousness, an alarm mechanism is triggered, and precise location information is sent to a preset contact person or emergency service using satellite positioning data. For example:

[0090] After the impact and rollover are completed, an alarm will be automatically triggered, emitting a sharp alarm sound in a loop.

[0091] Once the location is confirmed to be stationary, it will automatically dial emergency contacts and send a distress message containing its location.

[0092] Terminals equipped with BeiDou modules can also send distress messages and receive responses via BeiDou short messages, accurately determining the user's location and providing technical support for search and rescue operations.

[0093] This embodiment provides a fall detection method based on multi-sensor fusion of mobile terminals. The method involves collecting multi-sensor data from a mobile terminal, preprocessing the data, further processing the preprocessed data to obtain key features for fall detection, and then detecting falls based on these key features. This method can effectively monitor and identify whether workers at heights have fallen. It provides an intelligent safety measure for personnel working at heights, conducting field surveys, exploring the wilderness, or traveling in remote or dangerous environments, reducing reaction time after an accident and effectively protecting their lives. This invention offers high detection accuracy and is portable, easy to use, and real-time.

[0094] Based on the same inventive concept, embodiments of the present invention also provide a high-altitude fall detection system based on multi-sensor fusion of mobile terminals, such as... Figure 2 It includes a multi-sensor data preprocessing unit, a key feature acquisition unit, and a fall detection unit; among which:

[0095] A multi-sensor data preprocessing unit is used to collect multi-sensor data from a mobile terminal and preprocess the multi-sensor data.

[0096] The key feature acquisition unit is used to process the preprocessed multi-sensor data to obtain key features for fall detection from height.

[0097] A fall from height detection unit is used to detect falls from height based on the aforementioned key features of fall from height detection.

[0098] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the detection methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0099] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0100] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0101] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0102] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the detection methods described in the above embodiments. The computer-readable storage medium may be volatile or non-volatile.

[0103] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described detection method.

[0104] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0105] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0106] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0107] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0108] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0109] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0110] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0111] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0113] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A fall detection method from a height based on multi-sensor fusion of a mobile terminal, characterized by, The method comprises the following steps: Collecting mobile terminal multi-sensor data, and preprocessing the multi-sensor data; Processing the preprocessed multi-sensor data to obtain high-fall detection key features; Detecting high fall based on the high-fall detection key features.

2. The detection method according to claim 1, characterized in that, The multi-sensor data at least includes accelerometer data, gyroscope data, barometer data and satellite positioning sensor data.

3. The method of claim 1, wherein, The preprocessing of the multi-sensor data specifically includes filtering and denoising preprocessing of the multi-sensor data, and filtering processing is performed by using a first-order low-pass filter, wherein the formula of the first-order low-pass filter is as follows: ； Wherein, y[i] is the current filtering output value, x[i] is the current sampling value, y[i-1] is the previous filtering output value, and the formula shows that the current filtering output value is the weighted average of the current sampling value and the previous filtering output value, wherein the weights are α and 1-α, respectively, and α is a filtering coefficient between 0 and 1.

4. The detection method according to claim 2, characterized in that, The high-fall detection key features include synthetic acceleration, synthetic angular velocity, height change, change rate and position change rate; wherein the synthetic acceleration calculation formula is: ； to synthesize the acceleration, , , respectively, are the accelerations of the accelerometer in the x, y, z three axes; The synthetic angular velocity calculation formula is: ； to synthesize the acceleration, , , are angular velocities of the accelerometer in x, y, z three axes, respectively.

5. The method of claim 2, wherein, Continuously monitoring the barometer data, and calculating the height change and change rate in real time according to the barometric change; calculating the position change and position change rate according to the satellite positioning sensor data.

6. The method of claim 2, wherein Detecting high fall based on the high-fall detection key features, the specific steps comprising: Setting high-fall detection threshold, the high-fall detection threshold including weightlessness state detection threshold, impact detection threshold, attitude change detection threshold, height change detection threshold; Comparing the synthetic acceleration with the weightlessness state detection threshold to obtain the duration that the synthetic acceleration is less than the weightlessness state detection threshold, and when the duration is greater than a preset duration threshold, it is judged that the current is in a weightlessness state; After detecting the weightlessness state, continue to judge the synthetic acceleration, and when the synthetic acceleration is greater than the impact detection threshold within a preset time, it is judged that the current is in an impact state; After the impact state detection is completed, the synthetic angular velocity value is compared with the attitude change detection threshold by using the gyroscope data during the weightlessness and impact, and when the synthetic angular velocity value is greater than the attitude change detection threshold, it is judged that the current is in an attitude change state; After the attitude change detection is completed, the barometric pressure at the beginning of weightlessness and the barometric pressure at the end of weightlessness are obtained by using the barometer data, and the barometric pressure rise value in the weightlessness process is calculated, and the barometric pressure rise value is compared with the height change detection threshold, and when the barometric pressure rise value is greater than or equal to the height change detection threshold, it is judged that the current is in a height change state; When the weightlessness state, impact state, attitude change state and height change state are detected at the same time, it is detected that the current is in a high-fall state.

7. The detection method according to claim 6, characterized in that, The method for detecting high fall further comprises the following steps: When detecting that the current state is a high place falling state, a stationary state is also detected, and according to real-time satellite positioning data, a current sampling positioning coordinate is compared with a previous sampling positioning coordinate, when there is no obvious change in position, an accumulated time when the position is unchanged is obtained, and when the accumulated time is greater than a preset time, it is judged that the current state is a stationary state after a high place falling.

8. The detection method according to claim 7, characterized in that, When detecting that the current state is a high place falling state, an alarm mechanism is also triggered, and accurate position information is sent to a preset emergency contact person by using satellite positioning data.

9. A high fall detection system based on mobile terminal multi-sensor fusion, characterized in that, The method comprises a multi-sensor data preprocessing unit, a key feature acquisition unit and a high place falling detection unit, wherein: The multi-sensor data preprocessing unit is used for collecting mobile terminal multi-sensor data and preprocessing the multi-sensor data; The key feature acquisition unit is used for processing the preprocessed multi-sensor data to obtain high place falling detection key features; The high place falling detection unit is used for detecting high place falling based on the high place falling detection key features.

10. An electronic device, comprising: The method comprises: One or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the detection method as claimed in any one of claims 1 to 8.

Images