230 results about "Fall detection" patented technology

The invention discloses a tumble detection method, wearable equipment and a storage medium, relates to the technical field of tumble detection, and discloses a tumble detection method applied to the wearable equipment, the wearable equipment comprises an acceleration sensor and at least one other sensor except the acceleration sensor, the tumble detection method comprises the following steps: acquiring acceleration data acquired by an acceleration sensor based on a time sequence; if the acceleration data accord with the free falling acceleration performance in the first time period and accord with the impact rebound acceleration performance in the second time period, it is judged that a falling impact event is detected; in response to the falling impact event, obtaining a falling detection result determined based on detection data collected by other sensors; and if the tumble detection result is that the tumble event exists, triggering a tumble event response process. On the basis, when falling impact is detected, detection and identification are carried out based on other sensor parameters, so that the falling detection accuracy of impact caused by falling is improved.

The invention relates to the technical field of intelligent fall detection, in particular to an old people fall detection and early warning system based on multi-modal data fusion, which comprises a dynamic weight fusion unit, a precursor trigger unit, a multi-level decision unit and a verification feedback unit, the dynamic weight fusion unit collects three-axis acceleration, surface electromyographic signals and millimeter wave radar data, multi-source data association analysis is achieved through a double-variable attenuation model and dynamic threshold calibration, and the precursor trigger unit activates electromyographic high-frequency sampling and joint three-dimensional space included angle monitoring when the exercise intensity is abnormal. And the multi-level decision-making unit constructs a tumble probability algorithm based on a random forest model, and performs three-level verification in combination with acceleration standard deviation, ground contact point density and historical mode matching, thereby realizing accurate discrimination of tumble events, providing a high-reliability intelligent solution for safety protection of old people, reducing the risk of tumble injury, and improving the safety of the old people. And the first-aid response efficiency is improved.

The invention relates to the technical field of indoor old people safety monitoring, and discloses an indoor old people tumble detection system based on a hybrid mode, which comprises a video acquisition module, an audio acquisition module, an identity recognition module, a tumble detection module, an emotion recognition module and an alarm module. According to the method of the indoor old people tumble detection system based on the mixed mode, video and audio data are creatively fused, multi-dimensional monitoring of the state of the old people, capturing of action postures of the old people by the video acquisition module and obtaining of voice and environment sound information by the audio acquisition module are achieved, and the two complements each other; abnormal sound in the audio, such as collision sound of falling and shouting sound, can assist in judgment, the multi-dimensional data acquisition and analysis mode greatly reduces misjudgment and missed judgment caused by single data, the accuracy and reliability of detection are remarkably improved, and the safety of old people is comprehensively guaranteed.

The invention provides an anti-falling detection unit, a photovoltaic panel cleaning robot and an anti-falling detection method.The anti-falling detection unit comprises a substrate, an ultrasonic sensor and at least one laser sensor, the ultrasonic sensor is arranged on the substrate, and each laser sensor is arranged on the substrate; the at least one laser sensor and the ultrasonic sensor are arranged at intervals in the first direction. According to the anti-falling detection unit, the ultrasonic sensor and the laser sensor are used at the same time, the ultrasonic detection mode and the light wave detection mode are combined, comprehensive detection of the edge and the gap of the photovoltaic panel is achieved, the accuracy and the reliability of signals are improved, the problem of false alarm possibly caused by a single sensor is effectively avoided, and the detection efficiency is improved. The photovoltaic panel cleaning robot is simple in structure and convenient to operate, work interruption caused by signal abnormity can be reduced, the photovoltaic panel cleaning robot can be prevented from falling off and can cross gaps between different photovoltaic panels to complete cleaning work of the multiple photovoltaic panels, and the work efficiency of the photovoltaic panel cleaning robot is improved.

The invention belongs to the field of multi-modal data processing, and relates to an efficient multi-modal fall detection method in an intelligent medical environment, which comprises the following steps: collecting multi-modal data and inputting the multi-modal data into a trained multi-modal fall detection model to obtain a detection result; the training process of the tumble detection model comprises the steps of collecting multi-modal data and inputting the multi-modal data into the multi-modal feature extraction module to obtain multi-modal features; inputting the multi-modal features into a multi-modal time alignment module to obtain multi-modal time alignment features; inputting the time alignment feature into a depth fusion module to obtain a depth fusion feature; inputting the deep fusion features into a classification module to obtain a detection result; calculating a multi-task loss function value, and updating model parameters according to the multi-task loss function value until a trained fall detection model is obtained; alignment of the multi-modal data is achieved through modal contribution evaluation and dynamic time warping, multi-modal data fusion is achieved in combination with a key modal and a bottleneck mechanism, the detection precision and robustness can be improved, and the calculation complexity can be reduced.

The invention discloses a waistband type falling protection early warning device for old people living alone, and belongs to the technical field of intelligent wearable equipment. The problems that an existing device is single in early warning mode and cannot effectively guarantee the safety of old people living alone are solved, corresponding action results are matched for various data of the old people through the convolutional neural network and the lightweight decision tree model, and if a preliminary judgment result conforms to a normal mode, a judgment result is directly output; if not, triggering a secondary analysis mechanism to further judge whether the old people fall down or not; the GPS positioner is also used for analyzing whether falling behaviors occur at the same position for many times, and if a high-risk position is found, when the old people approach the high-risk position, the warning lamp and the alarm are used for reminding and paying attention to action behaviors; the fall detection accuracy is improved, the possibility of false alarm and missing alarm is reduced, the old people can be actively prevented from falling again in a high-risk area, and a more comprehensive safety guarantee is provided for the old people living alone.

The invention discloses a fall detection method based on an OEF-YOLO model, and is applied to the technical field of computer vision. Comprising the following steps: constructing a data set for training and detecting the performance of an OEF-YOLO model; the YOLOv8 model is improved, and an OEF-YOLO model used for tumble detection is obtained; s2, training an OEF-YOLO model through the data set constructed in the step S1; and the detection effect of the OEF-YOLO model is evaluated through the data set constructed in the step S1. According to the method, the YOLOv8 model is improved through the EMA attention mechanism module, the C2f-ODConv module and the loss function integrated with the Focal Loss, the reliability of fall detection in the indoor scene is improved, and reasonable balance is achieved in the aspects of light weight and high precision.

The invention discloses a tumble detection method and tumble detection equipment, and the method comprises the steps: determining whether a target object triggers a tumble detection instruction or not based on a radar echo signal of a target detection region; the target object is an object needing tumble detection; under the condition that a target object triggers a tumble detection instruction, fast Fourier transform of a distance dimension and fast Fourier transform of a Doppler dimension are respectively carried out on radar echo signals, and a multi-frame feature matrix is constructed; the feature matrix is used for representing distribution information of a radar detection target in a distance dimension and a speed dimension, and the radar detection target comprises a target object; and based on the multi-frame feature matrix, determining a tumble detection result of the target object through a tumble detection model. The tumble detection result of the target object can be more accurately determined, and the identification accuracy of the tumble behavior is improved.

The present invention discloses a computer vision-based indoor fall detection method, system, device, and medium, which solves the problem of how to accurately detect falls and promptly alarm; it belongs to the field of computer vision; it includes a device end deployed indoors: the device end uses the MoveNet algorithm to extract the position and confidence of human key points from low-resolution video frame images to form an effective key point sequence; the semantic segmentation network in the edge end identifies indoor scene objects in the high-resolution video frame images uploaded by the device end, marks the fall risk area, and classifies the posture of the key point sequence through the constructed deep learning neural network model. When the posture is classified as lying and the position of the human key point is in the fall risk area, the posture is detected as a fall, the posture is verified as a fall, and an alarm signal is generated. On the basis of ensuring user privacy, the present invention improves the accuracy of fall detection, reduces the incidence of false alarms and missed alarms, and buys more time for treatment after a fall.

A system for determining that a monitored person has fallen. The system includes sensors for measuring historic parameters that are indicative of a prior condition of the monitored person during a prior time interval, and for measuring current parameters that are indicative of a current condition of the monitored person. An analysis component determines statistical values based on the historic parameters, analyzes the current sensed parameter values relative to those statistical values, and determines whether the monitored person may fall or has fallen.

The invention relates to a tumble detection method and device, electronic equipment and a storage medium, the tumble detection method is applied to wearable equipment, the tumble detection method comprises the following steps: obtaining original motion data, the original motion data being used for representing a motion direction and a motion acceleration; in response to the original motion data meeting a preset signal strength condition, awakening a fall detection mode; and in the fall detection mode, determining a fall detection result based on the original motion data. According to the tumble detection method, the tumble detection mode is awakened only when the original motion data meets the preset signal intensity condition, pre-screening of the original motion data is achieved, and whether the tumble detection mode needs to be awakened to determine the tumble detection result or not can be judged according to the signal intensity; the power consumption of the device when the fall detection mode is not awakened is reduced, the endurance time of the device is ensured, and the user experience is improved.

The present invention provides a method for detecting human falls based on millimeter-wave radar. This method processes the echo signal of the millimeter-wave radar to obtain the height change parameter ΔH, aspect ratio Q, and Doppler spectrogram of the moving target in the area to be measured. It detects emergencies through the Doppler spectrogram. Once an emergency occurs, it acquires the spectrogram around the emergency, denoises the spectrogram, extracts three features: the extreme frequency amplitude, extreme frequency ratio, and event length of the spectrogram, and jointly inputs two features, the current height change parameter ΔH and aspect ratio Q, into a neural network for training and learning, and then detects falls. It has the advantages of a relatively wide coverage range, low code complexity, fast calculation speed, and low false positive and false negative rates for falls.

The present invention relates to a fall detection method and system based on millimeter-wave radar. The detection method comprises: S1, acquiring three-dimensional point cloud data detected by the millimeter-wave radar; S2, converting the three-dimensional point cloud data into the position and speed data of each target, and bringing the data into the Kalman cycle prediction to achieve a prediction for the next moment, matching the position of the target at the current moment with the predicted position of the target at the previous moment, and obtaining the ID of each target at the current moment; S3, performing fall detection and judgment based on the ID, position, and speed information of the target. The present application uses a Kalman filter to predict the state of a target at a certain moment, and further confirms the actual action of a low-speed fall by setting a speed threshold in the three-dimensional direction of the target.

The invention discloses a tumble detection method and system based on a multi-mode large model, a terminal and a storage medium, and the method comprises the steps: obtaining real-time video information, inputting the real-time video information to a tumble initial detection model, and obtaining a suspicious video frame; obtaining text prompt information, inputting the text prompt information and the suspicious video frame into a tumble recheck model, and outputting a behavior analysis report; and obtaining a tumble detection result according to the behavior analysis report. Two-stage detection of the tumble behavior is realized by constructing the tumble initial detection model and the tumble redetection model, the tumble initial detection model can quickly screen out the possible tumble behavior, the tumble redetection model can deeply analyze the possible tumble behavior, and then the tumble detection result is output. The fall behavior detection efficiency and the fall detection result output accuracy are effectively improved.

The invention discloses a hanging object tracking and falling detection method and device based on multi-sensor fusion. The method comprises the following steps: monitoring revolutions of a main winch and an auxiliary winch through an encoder to adjust a vertical rotation angle of a camera to ensure that a view angle covers a lifting hook and a lifted object; a six-axis sensor on the lifting hook is used for judging the motion state of the lifting hook, if the lifting hook is in motion, image SIFT feature point displacement is analyzed to calculate background displacement, a mean square error is used for dividing a background area and a motion area, and the positions of the lifting hook and a lifted object are determined in combination with encoder data; based on a visual judgment result and six-axis sensor information, PID control logic is applied to adjust the speed and angle of a camera in real time, so that the hanging object is kept at the center of a visual angle; when the tower crane moves and the hung object stops, the rotating speed of the camera is predicted and adjusted according to the movement law of the tower crane, continuous tracking of the hung object is achieved, and whether the hung object falls off or not is determined according to the multiple hung object positions. By implementing the method provided by the invention, accurate real-time tracking of the hung object can be realized, and the system can effectively work even in a dynamic environment or under an abnormal condition.

The invention discloses a fall detection and alarm system and method based on an acceleration sensor, and belongs to the technical field of wearable equipment and health monitoring. The method comprises the following steps: acquiring signals through various sensors in a multi-source data acquisition unit, transmitting the acquired signals to a signal processing unit, processing the signals through a three-stage signal processing assembly line in the signal processing unit, and inputting the processed signals to a hybrid verification unit for verification, and finally, the communication alarm unit judges whether to give an alarm according to a result output by the hybrid verification unit.

The invention provides a human body tumble detection method and device in a bathroom environment and a readable storage medium. The method comprises the following steps: extracting Doppler spectrum width features from a distance-Doppler spectrum corresponding to a bathroom radar echo signal; wherein the Doppler spectrum width feature is used for representing the breadth of speed distribution of the detection target; determining whether shower equipment in the current bathroom is in a working state or not based on the Doppler spectrum width features; if the current shower equipment is in the working state, generating a 4D point cloud image representing human body action information based on a distance-Doppler spectrum; and determining a detection result of the human body falling event according to the 4D point cloud image. Through the implementation of the scheme of the invention, the Doppler spectrum width features correspondingly extracted by the radar echo signals are utilized to judge the water flow condition of the shower head in the bathroom, the human body target and the water flow target are distinguished, the human body action is identified based on the 4D point cloud imaging technology, and high-precision detection of human body tumble can be realized.

The invention relates to a flying robot control method for monitoring and early warning the falling risk of old people, and the method comprises the steps: positioning the position of the old people in each room through an ultra-wideband positioning technology and the track of a flying robot, and carrying out the real-time data collection through combining a camera and a sensor; according to the collected multi-modal data, tumble detection is carried out through a tumble detection algorithm, and an alarm signal is sent out in time; a receiver is installed in each room, indoor navigation and path planning among the rooms are carried out, and the receivers in the rooms are parked for continuous monitoring and automatic charging; gait data is collected and analyzed for a long time based on the collected data, the falling risk is predicted, and personalized health suggestions are provided; and a health report is generated by combining cloud analysis and an artificial intelligence technology. Compared with the prior art, multiple innovative technologies such as the flight control technology, intelligent gait monitoring and falling alarm, automatic following and charging are integrated, and comprehensive monitoring, early warning and emergency response to the health of old people are achieved.

A method for determining a truthful label of a fall event is disclosed. The method comprises receiving signals from one or more sensors configured to measure from a distance signals indicative of characteristics of movement of a user, analyzing the received signals using a fall detection algorithm to determine a label indicative of a fall event by the user, initiating a first user interface interaction mode of a user interface, wherein in the first user interface interaction mode, the user interface is configured to receive a first input from the user indicative of a self-label of the fall event, receiving the first input and determining a level of mismatch between the self-label and the determined label. If the level of mismatch is above a threshold, the method further comprises switching the user interface to a second user interface interaction mode, wherein in the second user interface interaction mode, the user interface is configured to receive a second input from the user indicative of contextual information regarding the fall event, receiving the second input, and updating the self-label of the fall event based on the second input received.

The present invention relates to an indoor personnel fall detection method based on a millimeter-wave radar, which includes the steps of clustering point track data through a clustering algorithm to determine whether there is a target, and extracting relevant information of the target when there is a target; the point track data is the point track data in the geodetic coordinate system, which is converted from the point track data of the target output by the radar; the clustering steps are: (i) performing pre-clustering using velocity, calculating the absolute value of the difference between the velocities Vdi and Vdj of any two points, and clustering the points with this value less than the threshold deltaV into one class; (ii) performing clustering using distance, calculating the distance between any two points in the class obtained in step (i), and clustering the points with a distance less than the threshold Dist into one class; (iii) calculating the number of points in the class obtained in step (ii), and if the number is greater than the threshold Num, it is considered that there is a target; otherwise, it is considered that there is no target. The detection method of the present invention comprehensively considers multiple judgment factors and significantly improves the detection accuracy.

The invention relates to a fall detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a to-be-detected image corresponding to a current moment; a first moving state corresponding to a target object in the to-be-detected image is determined from multiple preset moving states, the previous moving state of the target object from a preset historical moment to the current moment is obtained, and the multiple preset moving states are determined according to the change condition of the body posture when the object falls down; and under the condition that the state change condition of the previous moving state and the first moving state meets a preset falling condition, determining that the target object falls. The method can improve the detection accuracy, and is suitable for more application scenes.

The utility model provides an electroencephalogram anti-falling detection cap which comprises an auxiliary fixing frame, two head sleeves, an anti-falling mechanism, a mounting assembly and an electrode slice, and the two head sleeves are oppositely arranged in the auxiliary fixing frame; the anti-falling mechanism comprises a threaded rod, a connecting cylinder, a pushing rod, a first elastic piece, a limiting chuck and a movable limiting assembly, the threaded rod is arranged on the auxiliary fixing frame in a penetrating mode and connected with the connecting cylinder, the connecting cylinder movably sleeves one end of the pushing rod, the other end of the pushing rod is connected with the outer side wall of the head sleeve, the first elastic piece is arranged in the connecting cylinder, and the limiting chuck is arranged in the connecting cylinder. One end of the first elastic piece is connected with the top push rod, the other end of the first elastic piece is connected with the connecting cylinder, the threaded rod is sleeved with the limiting chuck, the limiting chuck is provided with a plurality of clamping positions, the movable limiting assembly is movably and adjustably arranged on the auxiliary fixing frame, and the movable limiting assembly is clamped in one clamping position. The size of the head circumference space can be adjusted so as to adapt to the sizes of the head circumferences of different patients.

Various arrangements for performing fall detection are presented. A smart-home device may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person has occurred. Speech may then be output announcing that the fall has been detected via the speaker of the smart home device.

A fall detection device and method are provided. In at least some embodiments, the system can utilize sensing devices such as smartwatches or smartphones (e.g., using iOS, Android, or Pebble operating systems) to read a user's vital signs and apply algorithms to interpret these signs. If the patient is interpreted as having a fall, tremor, or seizure, a notification is sent to a designated caregiver via a reporting process. In at least some embodiments, a doctor or other party can log into a protected dashboard and review patient data in real time. Also in at least some preferred forms, the doctor or other party can analyze the patient's medical history. In at least some embodiments, the user / patient can also use the data to track the onset and progression of falls, tremors, or seizures. Embodiments of the invention can be applied, for example, to situations where the patient / user experiences a condition such as epilepsy that makes the patient / user susceptible to falls and related events.

The application discloses a fall detection method, device and equipment based on laser point cloud. The method comprises the following steps: acquiring multiple frames of point cloud data including current frame point cloud data; for each frame of point cloud data, identifying the key parts of a human body from the point cloud data, determining the key points of the key parts, calculating the displacement of the key points in the vertical direction within the time length of the multiple frames of point cloud data, and judging whether the displacement is greater than or equal to a threshold value; when the displacement is greater than or equal to the threshold value, it is determined that a fall event occurs, and a fall alarm is sent. The method can achieve non-sensing detection, is easy to be accepted by the elderly, and the point cloud data does not collect the biological characteristics of the human body, so there is no risk of privacy leakage. In addition, by identifying the key parts of the human body and judging whether a fall event occurs according to the displacement of the key points of the key parts in the vertical direction, the whole human body does not need to be modeled for the fall action, and the detection efficiency is improved.

A fall detection device (1) according to the present invention comprises a first detection unit (11) that detects a set of skeletal points of a person outside a vehicle traveling on a road from a first image captured by a first onboard camera mounted on the vehicle, a second detection unit (12) that detects a road area indicating the area of the road from the first image, and a determination unit (13) that determines whether or not the person is falling on the road on the basis of the positional relationship between the skeletal points and the road area. In particular, for the positional relationship, the determination unit (13) uses the distance from the ground to the skeletal points calculated from the position information of the skeletal points and the position information of the road area.

This invention discloses a fall detection method, apparatus, device, and medium. The method includes: determining target noise point detection information corresponding to the target radar detection information of a target person based on personnel radar detection information detected by millimeter-wave radar and noise point detection information detected by an acoustic detection device; determining the detection mode of the target person based on the target radar detection information, and determining target detection information from the target radar detection information and target noise point detection information based on the detection mode; wherein the detection mode includes an obstruction mode, a stationary mode, and a motion mode; and detecting the fall state of the target person based on the target detection information. This invention uses a combination of millimeter-wave radar and acoustic detection for fall detection, enabling continuous fall state detection even when the target person is obstructed by objects indoors, improving the accuracy and efficiency of fall detection; and since both millimeter waves and acoustic waves are invisible waves, user privacy can be effectively protected.

The invention relates to a neural network-based real-time human body tumble detection method suitable for an FPGA (Field Programmable Gate Array). The invention relates to the technical field of machine vision, and the method comprises the steps: shooting a falling video, intercepting and screening picture frames from the video, marking human body key points, randomly selecting pictures from a COCO2017 human body key point detection data set, and carrying out the preprocessing to make a human body key point fusion data set; a YOLOv8n pose human body key point detection model is established; and identifying the key points of the human body, preprocessing the identified key points, and sending the key points into a human body falling judgment network for falling judgment. According to the invention, the human body key point detection accuracy of the human body key point detection model under side tumbling and sheltered tumbling is improved, and the hardware resource consumption when the network model is deployed on the FPGA is reduced.

This invention discloses a human fall detection system based on Wi-Fi channel state information, belonging to the field of wireless sensing technology. It includes a Wi-Fi transceiver unit, a data preprocessing unit, a multi-dimensional feature extraction unit, an adaptive threshold judgment unit, a fall recognition inference unit, an early warning output unit, and a local storage unit. This invention eliminates the need for users to wear any devices or engage in any image acquisition, fundamentally eliminating the poor compliance and strong foreign body sensation associated with wearable solutions, as well as the privacy leakage risks of visual solutions. This allows the system to be safely applied in privacy-sensitive scenarios where the elderly frequently engage in activities such as bedrooms and bathrooms. Users can receive 24 / 7 protection without changing their lifestyle. The system effectively filters out static multipath interference from walls, furniture, etc., through static environmental baseline subtraction and extracts human spatial posture features using 2D AoA estimation, accurately distinguishing falls from similar daily actions such as bending over, sitting, and lying down.

The invention relates to the technical field of escalator, in particular to an escalator device with a human body anti-falling detection function, which comprises an escalator main body, a detection main body and a power supply main body, handrail guardrails are arranged on the front side and the rear side of the escalator main body, and handrail belts are arranged on the outer sides of the handrail guardrails; the escalator comprises an escalator main body, a handrail guardrail, a handrail belt, a rubber drawstring, a detection main body, a rubber plate and a deformation groove, the handrail belt is internally provided with rubber plates which are uniformly distributed, the rubber plates are internally provided with deformation grooves which are uniformly distributed, and one side of each rubber plate is provided with a power supply main body. The escalator main body, the handrail guardrail, the handrail belt, the rubber drawstring, the detection main body, the power supply main body, the rubber plates and the deformation grooves are arranged; the rubber drawstring can be grasped by hands, when falling occurs, the detection main body performs detection, running of the escalator is stopped in time, injury to pedestrians is reduced, deformation can be provided for the bottom of the power supply main body in the handrail belt conveying process through the rubber plate and the deformation groove, and the power supply main body is more stable in the handrail belt running process.