325 results about "Motion sensing" patented technology

Techniques and apparatuses are described that perform audioplethysmography and motion-sensing data fusion. Fusing motion-sensing data with audioplethysmography expands the situations in which audioplethysmography can operate. In one aspect, audioplethysmography and motion-sensing data fusion can be used for motion-artifact filtering. With motion-artifact filtering, noise caused by motion of a user can be attenuated to improve sensitivity and accuracy for audioplethysmography. This performance improvement expands the ability of audioplethysmography to support use cases during situations in which the user engages in an activity. In another aspect, audioplethysmography and motion-sensing data fusion can expand a functionality of a hearable to include activity detection and / or activity classification. While activity detection and / or activity classification can provide additional contextual information for other use cases associated with audioplethysmography, either can also be used to control an operation of the hearable and / or a computing device.

The invention discloses a reference video object segmentation method based on semantic consistency and motion perception. The method comprises the following steps: 1, constructing semantic prompt information and video frame information of a reference video object segmentation data set; 2, preprocessing the reference video object segmentation data set; 3, establishing a reference video object segmentation model based on semantic consistency and motion perception: designing a double-branch decoupling strategy for decoupling feature information at semantic and visual levels so as to extract static and motion information of text description and visual features; a hierarchical motion sensing module is designed to capture and align motion information between different frames, and analyze short-term and long-term motion information, so that the model obtains a sensing ability for a long-term motion mode; the semantic consistency module is designed to align semantic description and video features, so that the accuracy of target selection and the integrity of masks are improved, and false detection of negative samples is avoided; a perceptual dynamic fusion mechanism is designed to be used for embedding text information into a visual feature space, so that visual features can obtain text semantic information, and the cross-modal understanding ability of the model is enhanced; 4, constructing a loss function, updating model parameters, setting training parameters, and training to obtain an optimal weight; and 5, detecting the test set image based on the optimal weight to obtain a final segmentation result. According to the method, static and dynamic information is effectively decoupled, the sensing ability to an object motion mode is enhanced, and the segmentation performance is improved.

The invention relates to the field of medical information monitoring, and discloses a doctor monitoring bracelet for receiving infusion information of a patient, comprising: a multispectral sensing module for collecting an original physiological light intensity signal of the wrist of the patient; the motion sensing module is used for collecting motion signals; the micro-electro-mechanical motion compensation module is configured on the multispectral sensing module; the processor is electrically connected with the multispectral sensing module, the motion sensing module and the micro-electro-mechanical motion compensation module; and the communication module is electrically connected with the processor. By integrating a high-sensitivity multispectral sensing module and a micro-electro-mechanical active motion compensation system and combining an advanced signal processing algorithm, the accuracy of real-time monitoring of key vital signs of a patient in a complex infusion scene is remarkably improved, more reliable patient infusion information is provided for a subsequent multi-head infusion intelligent switching control system, and the infusion safety of the patient is improved. High fidelity of a data source is ensured, and tedious work of medical staff is reduced.

Systems and methods for predicting problem behavior in individuals with developmental and behavior disabilities. A plurality of sensors are configured to collect multimodal data signals of a subject individual including a wearable upper body motion sensing device with a plurality of inertial measurement units (IMUs). An electronic controller is configured to receive output signals from each of IMUs and to model an upper body position of the subject individual based on the output signals from the IMUs. A trained machine-learning model is then applied by providing an input data set that includes multimodal signal data (e.g., including signal data from at least one IMU) and / or features extracted from the multimodal signal data. The machine-learning model is trained to produce as output an indication of whether a precursor to the problem behavior is detected and, in response to detecting the precursor, a notification (or alarm) is generated.

The disclosure provides devices, systems, and methods for physical therapy. Electrical signals are applied to a subject via electrodes in a device worn on the body part receiving the therapy. The device can be operated remotely. The device can use artificial intelligence to evaluate and design physical therapy routines using the electrodes.

Techniques and apparatuses are described that perform audioplethysmography and motion-sensing data fusion. Fusing motion-sensing data with audioplethysmography expands the situations in which audioplethysmography can operate. In one aspect, audioplethysmography and motion-sensing data fusion (202) can be used for motion-artifact filtering (206). With motion-artifact filtering (206), noise caused by motion of a user (106) can be attenuated to improve sensitivity and accuracy for audioplethysmography. This performance improvement expands the ability of audioplethysmography to support use cases during situations in which the user (106) engages in an activity. In another aspect, audioplethysmography and motion-sensing data fusion (202) can expand a functionality of a hearable (102) to include activity detection (208) and / or activity classification (210). While activity detection (208) and / or activity classification (210) can provide additional contextual information for other use cases associated with audioplethysmography, either can also be used to control an operation of the hearable (102) and / or a computing device.

The invention discloses an unmanned aerial vehicle autonomous landing system based on UWB and visual fusion, and the system comprises a ground unmanned vehicle and an unmanned aerial vehicle, and the ground unmanned vehicle is in communication connection with the unmanned aerial vehicle. The ground unmanned vehicle is further provided with a ground station, a landing mark and a main control module used for controlling movement output of the ground unmanned vehicle, the main control module is connected with a wireless remote control module, the main control module is further provided with a monitoring unit, and the ground station obtains flight information of the unmanned aerial vehicle for path planning; the unmanned aerial vehicle is further provided with an information collection module, a motion sensing module, a controller module and a power module, and the information collection module is used for collecting position information of the landing mark. Compared with the prior art, the unmanned aerial vehicle autonomous landing system and the unmanned aerial vehicle autonomous landing method based on UWB and vision fusion have the advantages that the unmanned aerial vehicle autonomous landing system and the unmanned aerial vehicle autonomous landing method are used by a combined navigation system formed by UWB and IMU for a scene of cooperative operation of an unmanned aerial vehicle and an unmanned vehicle.

The invention discloses an external hanging type motion sensing control system for shooting games and training. The external hanging type motion sensing control system comprises a data acquisition module, a data processing module, a power management module, an output display module, a personal area network interaction module and a cloud service module. The data acquisition module is used for acquiring data required for resolving the spatial attitude of a user through a sensor; the data processing module processes the collected sensor data, maps the sensor data into the actual state and operation of a user, and stores and manages user-defined control parameters; the power supply management module is used for supplying power to the somatosensory control equipment and managing the power supply of the somatosensory control equipment; the output display module is used for displaying the state information of the somatosensory control equipment; the personal area network interaction module is used for communication and information interaction; and the cloud service module is used for a user to customize sensor parameter mapping and equipment information management through a mobile phone. The invention further provides a somatosensory control method which has a wide application scene.

The invention relates to the technical field of data processing, and discloses a mobile robot voice data control method and system based on artificial intelligence. The method comprises the steps that three-channel voice data streams are collected through a multi-channel microphone array, and time synchronization processing is carried out on the three-channel voice data streams and robot motion state data; calculating a motion intensity value according to the motion state data, and performing motion compensation through an MSAP algorithm; inputting the compensated voice signal into a double-path convolutional neural network to extract motion sensing voice features; jointly coding the speech features and the motion state vectors through an MS-LSTM network, and obtaining a speech recognition text by adopting a CTC loss function; and carrying out cross-modal fusion on the text and the robot state information, and carrying out intention recognition through a hierarchical classifier to obtain a structured control instruction. The technical problem that the mobile robot is poor in voice instruction recognition accuracy and high in control delay in a dynamic environment is solved.

The invention discloses a teleoperation tactile feedback manipulator system which comprises a bionic manipulator, a somatosensory glove and a hand posture recognition module, the bionic manipulator is in wireless communication with the somatosensory glove, and the hand posture recognition module is in wireless communication with the bionic manipulator and the somatosensory glove. According to the teleoperated tactile feedback manipulator system, through cooperative work of the somatosensory glove and the bionic manipulator, an operator can visually and flexibly control the manipulator, the operation precision and efficiency are improved, the flexible pressure sensor is used for detecting the grabbing pressure in real time, and a pressure signal is fed back to the somatosensory glove; the motion sensing glove generates corresponding tactile feedback according to the pressure signal, so that an operator can sense the grabbing condition of the bionic manipulator, the object is prevented from being damaged or sliding off, the operation accuracy and reliability of the bionic manipulator are further improved, support is provided for fine operation in a complex environment, and the motion sensing glove is convenient to install and has good applicability.

The invention discloses a non-therapeutic-purpose hearing and perception training device for non-invasive free mouse training and auditory cortex plasticity stimulation. The device comprises a soundproof box, a training device body in the soundproof box and a processing control system located outside the soundproof box. The training device main body in the soundproof box comprises a training box body, a water and air supply device, an animal action sensing device, an animal position sensing device, a loudspeaker and an illuminating lamp; the training box body comprises an open box and a dark box, and the animal position sensing device is arranged at the relative position of the junction of the open box and the dark box and the relative position of the side wall of the dark box; the processing control system located outside the soundproof box comprises a water and gas control device, a power amplifier and a control computer. The invention further discloses a method and application of the training device in auditory cortex plasticity induction and auditory perception training, and the training device has wide application prospects.

The invention provides an intelligent simulation training bomb for ground attack of an unmanned aerial vehicle. The training bomb comprises a bomb body, a thrust reverser, a fairing, a mounting frame, a smoke tank and a control module. Wherein a gas cabin is arranged in the bomb body, and the thrust reverser is composed of an electromagnetic valve and a multi-way pipe. The mounting frame integrates a fuming tank, a control module and a motion sensing module, and the control module calculates the falling speed, the grounding time and the position coordinates in real time based on data of all sensors of the motion sensing module so as to control the electromagnetic valve to be opened, so that compressed gas in the gas cabin is ejected from a reverse thrust gas opening in the circumferential direction of the fairing through the multi-way pipe; in combination with deformation buffering of the fairing made of an elastic material, nondestructive recovery of the training bomb is achieved, and repeated use is facilitated. And meanwhile, the fuming tank is controlled to trigger and release tracing smoke, so that an impact point is marked, and parameters such as latitude and longitude during landing are sent to a ground guide training system to serve as an evaluation basis of throwing precision.

Motion-based management of a logistics container uses elements of a wireless node network including a container node associated with the logistics container and equipped with a motion sensor. The motion sensor detects a motion status (e.g., moving, stationary, accelerating, decelerating) for the logistics container. The container node compares the motion status to a prior motion status, and then identifies a changed motion condition for the logistics container based upon the comparison. In response to the changed motion condition, the container node alters a broadcast profile used by the container node in communicating with other nodes in the wireless node network. The container node may be deployed as an apparatus within a logistics container, be considered together with the logistics container as a motion sensing container node apparatus, and be considered with multiple package ID nodes as a motion-based management system for the logistics container.

The invention relates to the technical field of intelligent wearable equipment, and discloses a motion sensing shoe based on plantar pressure monitoring and a motion trend analysis method. According to the motion sensing shoe, various types of sensors can be adopted to work in a combined mode, state trajectory tracking and pressure change condition collection of the foot are achieved, the problem that the data size is limited due to a single sensor is effectively solved by means of multi-modal data of foot pressure and foot postures, and stability and robustness are improved; real-time data of all the modules are comprehensively analyzed, potential information in the exercise data is fully mined, analysis of the exercise trend is achieved, and therefore more valuable exercise guidance and health suggestions are provided for users.

The invention discloses remote control equipment, which comprises an equipment main body, a first detection component integrated on the equipment main body, a motion sensing module and a controller, the controller is programmed to execute the following logic: when the detection values of the first detection assembly and the motion sensing module jointly meet a preset cooperation condition, the first terminal is remotely controlled to execute a target operation. The remote control accuracy is improved through a dual verification mechanism, instructions such as song switching, volume adjustment and connection equipment switching can be triggered by combining actions such as inclined shaking and knocking when a user presses or touches, an interface is simplified, and functions are expanded. The design of the nested touch control and the optical sensor can distinguish finger operation from clothes mistaken touch, and the terminal switching mechanism of long pressing and knocking further reduces the risk of mistaken triggering. The device can be designed into a ring shape, and is small in size, high in customization and reliable in remote control experience.

The invention discloses a complex motion perception method based on human visual inspiration, and the method comprises the steps: firstly capturing an athlete image in a motion process, recognizing a key image region through evaluating the semantic and visual importance of an image region, and then dynamically processing the region features of the key image region. And then, for the dynamically processed region features, a low-rank active learning technology is adopted, an objective function is optimized, and an optimized image region is obtained. And finally, classifying the optimized image area by using a support vector machine (SVM) to obtain a motion sensing result. According to the method, the extracted key region can be ensured to have visual saliency while better calculation efficiency is ensured, and the performance in a complex motion environment is remarkably improved.

Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for advanced device naming and localization of Wi-Fi connected devices at a location. The disclosed framework operates to manage, control and / or manipulate devices on a Wi-Fi network, which provides intuitive mechanisms to select devices to name, group and / or locate in a WiFi app with WiFi motion and / or detected gesture(s) by leveraging voting and ranking mechanisms via a compiled cross-correlation matrix of channel frequency response (CFR) motion signatures and / or channel state information (CSI) motion signatures. Accordingly, motion signature information can be leveraged to control, enable and / or permit Wi-Fi connections among and / or between devices at a location.

The invention relates to the technical field of image recognition, in particular to an intelligent recognition and detection method for preceding vehicle starting. The method comprises the following steps: acquiring an image of an automobile data recorder, and judging whether an automobile is in a static or moving state; extracting a plurality of view angle regions and carrying out region separation according to texture density; detecting the area smoothness to determine a motion detection sensitivity; and according to the state and sensitivity of the vehicle, front vehicle starting identification is carried out on each area, starting early warning response is sent out based on an identification result, and the detection accuracy and real-time performance are improved. According to the method, the driving video and the motion sensing data are fused, and multi-view region segmentation, adaptive sensitivity adjustment and a dynamic early warning mechanism are combined, so that high-robustness and high-precision recognition of the starting behavior of the front vehicle under various illumination and working conditions is realized, and the method has good universality and compatibility.

An electronic device may use information about the location of nearby devices to make sharing with those devices more intuitive for a user. The electronic device may include control circuitry, wireless circuitry including first and second antennas, and motion sensor circuitry. The control circuitry may determine the location of a nearby electronic device by calculating the angle of arrival of signals that are transmitted by the nearby electronic device. To obtain a complete, unambiguous angle of arrival solution, the electronic device may be moved into different positions during angle of arrival measurement operations. At each position, the control circuitry may calculate a phase difference associated with the received signals. Motion sensor circuitry may gather motion data as the electronic device is moved into the different positions. The control circuitry may use the received antenna signals and the motion data to determine the complete angle of arrival solution.

The invention provides a self-generating wearable motion sensing device convenient for collecting motion information. The self-generating wearable motion sensing device comprises two hinged torsion arms, a rotating shaft of the one-way rotating disc assembly and a hinged shaft of the two torsion arms are coaxially arranged, a plurality of protruding parts are arranged in the circumferential direction of the one-way rotating disc assembly, and a plurality of piezoelectric triggering units are arranged on the rotating disc in the circumferential direction. The piezoelectric module comprises a piezoelectric cantilever, one end of the piezoelectric cantilever is fixed with one torsion arm, and the other end of the piezoelectric cantilever is matched with the piezoelectric trigger unit; the friction electricity module is connected with the other torsion arm and comprises two films, the two films are oppositely arranged, and the protruding part can be matched with the first film, so that the two films are close to or away from each other. According to the invention, the piezoelectric module is matched with the piezoelectric trigger unit, and the triboelectric module is matched with the lug boss, so that the legs are matched with the piezoelectric trigger unit and the triboelectric module respectively in two stages included in one walking period, and motion signals in different stages in the walking period are collected respectively; therefore, the accuracy of signal acquisition is improved.

The present disclosure relates to an optical fiber pressure sensor array or grid for location, vibration and / or motion sensing including:a plurality of receiving optical fibers, anda plurality of transmitting optical fibers,wherein said plurality of receiving optical fibers and said plurality of transmitting optical fibers are arranged in a planar array to define pressure sensors at respective points,wherein a mechanical structure is provided at one or both sides of each pressure sensor to enhance fiber bending when a pressure is applied to the pressure sensor, said mechanical structure including a first, internal layer contacting the optical fibers and made of a flexible, light-scattering material, and a second, external layer made of a rigid material,wherein said plurality of receiving optical fibers and / or said plurality of transmitting optical fibers is curved at the intersecting point defining the pressure sensor.

The invention discloses a spinal cord electrical stimulation control method and system based on tremor detection. The method comprises the following steps: acquiring motion sensing data of a user; extracting tremor signal features of the user according to the motion sensing data and a preset feature extraction algorithm; determining an electrical stimulation parameter corresponding to the tremor signal feature according to a preset electrical stimulation parameter determination rule; according to the electrical stimulation parameters, generating an electrical stimulation control instruction corresponding to electrical stimulation equipment arranged in a spinal cord area of the user; the electrical stimulation control instruction is used for indicating current output of the electrical stimulation equipment. Therefore, accurate nerve intervention control in combination with tremor monitoring and spinal cord electrical stimulation can be realized, the physical therapy inhibition effect of electrical stimulation physical therapy measures on the tremor of the user is improved, and more efficient and accurate nerve regulation and control service is provided for the user.

A low-power-consumption intelligent positioning safety helmet comprises a safety helmet body, a safety helmet main board is arranged on the safety helmet body, an MCU control module is arranged in the safety helmet main board, and the input end of the MCU control module is electrically connected with an accelerometer module and an ambient light sensing module. The output end of the MCU control module controls the satellite positioning module and the communication module to position the position of the safety helmet. A Beidou satellite positioning technology is adopted in an outdoor environment, a 4G base station positioning technology is adopted in an indoor environment, and multi-mode combined positioning and automatic switching can be realized. According to the intelligent safety helmet, a positioning mode is improved through a motion sensing circuit and an environment sensing circuit of the intelligent safety helmet, automatic power-on and power-off control over the Beidou positioning module and the 4G communication module is achieved, on-demand power supply of large-power-consumption units such as the positioning module is achieved, a power consumption management mechanism is optimized, power consumption of the whole helmet is reduced, and the endurance time is prolonged.

The invention relates to virtual pipetting. The method for generating the control program of the laboratory automation equipment comprises the steps that configuration data of the laboratory automation equipment are received, and the configuration data encode the positions of components in the laboratory automation equipment; generating a three-dimensional model of the assembly of the laboratory automation equipment according to the configuration data, wherein the three-dimensional model further comprises a virtual pipette; displaying the three-dimensional model by using a virtual reality headset; receiving movement data of a motion sensing controller controlled by a user wearing the virtual reality headset, the movement data indicating three-dimensional movement of the motion sensing controller in space; determining movement of the virtual pipette in the three-dimensional model according to the movement data and updating the three-dimensional model according to the movement; a control program for the laboratory automation device is generated on the basis of the movement data, and the control program moves a pipette-bearing pipette arm of the laboratory automation device relative to the assembly on the basis of the movement of the virtual pipette in the three-dimensional model.

The invention provides a pet emotion recognition method and device based on motion sensing, and the method comprises the following steps: 1, enabling motion sensors disposed at four limbs of a pet to obtain motion sensing signals; 2, performing Kalman filtering processing on the motion sensing signal, and calculating an amplitude change rate of the motion sensing signal; 3, respectively fusing the amplitude change rate signals obtained by the four motion sensors, and calculating second-order signals of the amplitude change rate signals; step 4, performing feature extraction on the second-order signal, wherein the extracted features comprise time domain features and frequency domain features; and step 5, judging the features of the feature extraction module, selecting the most suitable features to identify the limb movement of the pet, and identifying the emotion of the pet according to the limb movement. The method has the beneficial effects that the emotion of the pet is judged according to the motion state of the pet, and the method has the advantages of convenience in use, low cost, no environmental interference, high accuracy and the like.

The invention discloses a human body motion sensing method based on a three-dimensional mixed attention model and related equipment, and relates to the technical field of human body motion sensing, and the human body motion sensing method based on the three-dimensional mixed attention model comprises the steps: obtaining wireless signal spectrum data; feature processing is conducted on the wireless signal spectrum data according to a preset three-dimensional mixed attention model, human body action sensing features are determined, the three-dimensional mixed attention model firstly conducts feature compression on the wireless signal spectrum data, and then the human body action sensing features are determined on the basis of a non-local attention mechanism; according to the method, attention weights are calculated from three dimensions of time, frequency and subcarriers, three-dimensional attention feature maps are generated, finally, the three-dimensional attention feature maps are fused through cross attention, and human body action sensing features are output after dimension adjustment. And according to the human body action perception characteristics, determining a human body action perception recognition result. According to the invention, the recognition efficiency is improved by reducing the parameter quantity, so that the sensing technology is effectively deployed on small equipment.

A motion sensing mount apparatus for mounting to a building corner, tree, or the like and directing a camera toward a source of detected motion includes a structure mounting bracket which mounts to a support structure. A support module is removably coupled to and extending away from the structure mounting bracket. A camera is movably mounted atop the support module via a turntable or the like. Motion sensors detect motion and a direction from which the motion occurred relative to the camera. A drive mechanism is operable to rotate the turntable to direct the camera toward the source of the motion.

The invention relates to the technical field of ship hoisting control, in particular to a ship hoisting heaving active control system based on hydraulic compensation, and adopts the technical scheme as follows: precise advanced prediction of heaving motion of a ship in future 2-5 seconds is realized by integrating a motion sensing and prediction module and adopting a time sequence prediction model based on a long short-term memory network; a core control decision module adopts a model prediction control strategy fused with multi-source data to uniformly optimize multiple targets such as load stability, energy consumption and equipment wear; internal and external state changes of the system are sensed in real time through a system state monitoring and self-adaption module, control parameters are adjusted on line based on a fuzzy rule base, and the system is endowed with self-adaption capacity for coping with load changes, sea condition fluctuation and component performance degradation in the whole life cycle; a closed volume control scheme that a servo motor directly drives a two-way metering pump is adopted in the hydraulic execution and compensation module, throttling loss in a traditional valve control system is abandoned, and efficient conversion between hydraulic energy and mechanical energy is achieved.

A method for automated monitoring of a passenger transport system with a monitoring system. The monitoring system has a hazard analysis module and a motion-sensing module. The motion-sensing module is configured to capture real motion sequence recordings. The method comprises: receiving real motion sequence recordings and data of a digital double of the passenger transport system in the hazard analysis module, wherein the data comprise information relating to physical properties of the passenger transport system, which allow determination of a visual appearance of the passenger transport system; determining dynamic objects information on the passenger transport system with the hazard analysis module based on the received recordings and data; determining a current hazardous situation on the passenger transport system with the hazard analysis module based on an analysis of the determined dynamic objects; and outputting a warning with the hazard analysis module based on the current hazardous situation.

The invention relates to the technical field of education, in particular to a health education interaction system and method based on virtual reality and deep learning. The health education interaction system creatively integrates motion sensing games, VR video teaching, personalized reading and a body measurement motion module, and all-around and immersive learning experience is created; the system motivates the participation degree of a user through a motion sensing game, interactive learning is achieved through VR video teaching, personalized reading meets the requirements of the user, and the health state is monitored through motion measurement. The intelligent analysis module is used for deeply mining data and providing personalized health assessment and suggestions; the self-learning unit continuously optimizes a knowledge base and a recommendation algorithm, and constructs a dynamic health knowledge graph; the system breaks through the limitation of traditional health education, improves the knowledge propagation efficiency and acceptance, effectively promotes the formation and maintenance of health behaviors, and brings revolutionary change to the field of health education.