108 results about "Head position" patented technology

The invention discloses a multi-person head posture estimation method and device based on multi-task loss balance. The method comprises the following steps: constructing a multi-person head posture estimation model based on a Mamba-YOLO network; training a multi-person head posture estimation model, and controlling the training process by using a loss function based on a dynamic weight in the training process, the loss function based on the dynamic weight is obtained by weighting the loss function of the head prediction probability learning task, the loss function of the head position detection learning task and the loss function of the head posture estimation learning task by using the dynamic weight, and the dynamic weight of each branch is determined according to the loss value of the corresponding task; and obtaining a to-be-detected picture, and inputting the to-be-detected picture into the trained multi-person head posture estimation model to obtain a detection result. According to the method, end-to-end multi-person head posture estimation based on multi-task loss balance can be realized, and the detection real-time performance is kept while the estimation precision is improved.

The invention relates to a long-gap discharge leader development speed measurement method based on radiated electromagnetic wave detection. The method comprises a set of high-frequency antennas and a high-speed oscilloscope and a long-gap discharge leader development speed calculating method. The method adopts a certain antenna arrangement form; long-gap discharge radiated electromagnetic wave pulse time is detected simultaneously through the plurality of antennas; leader head position is positioned according to time difference of a signal arriving at different antennas; and furthermore, the long-gap discharge leader development speed can be calculated. The method can effectively improve the measurement precision of the discharge leader development speed, and resolution reaches the level of 0.1 ns.

The utility model relates to the field of medical instruments, in particular to an abnormal head position detection device, which comprises a head-mounted frame, a sensor module, a display module and a power supply module, the head-mounted frame is used for bearing the sensor module, the display module and the power supply module; the sensor module is used for detecting the deflection angle of the head position, and the sensor module is connected with the display module; the display module is used for displaying the head position inclination angle detected by the data detected by the sensor module; the power supply module provides power for the sensor module and the display module. The head position monitoring device is convenient for a user to self-detect an abnormal head position condition, is simple in structure and convenient to use, can be used in various scenes, and has relatively high accuracy of a monitoring result; and the structural design is comfortable, so that the burden and discomfort of a user are reduced.

To provide a vertigo diagnostic device which automatically removes noise, such as eye blinking and the like, and tracks and quantifies purely eyeball movement so as to allow doctors to use the values in diagnosis.SOLUTION: The present invention relates to: a technique for tracking changes in eyeballs and a head position to diagnose vertigo, and more specifically, a vertigo diagnostic device and method using a deep learning model for tracking movement of the eyeball and the head of a patient from a video including a patient to diagnose vertigo on the basis of a deep learning model, and also relates to; a recording medium storing a program for achieving the vertigo diagnosis; and the computer program stored in the recording medium.SELECTED DRAWING: Figure 1

The invention relates to the technical field of TWS earphone low-delay audio processing methods, in particular to a TWS earphone low-delay audio processing method based on head motion prediction, which comprises the following steps: S1, collecting head motion parameters of a user, the head motion parameters comprising a head posture theta, a head rotation angular velocity omega, a head movement direction phi and a head movement velocity V; s2, establishing a relation model between the head motion parameters and the audio time delay; s3, predicting head motion parameters in a future time period based on a recurrent neural network; s4, according to the predicted head motion parameters, audio time delay is calculated, and audio rendering is carried out; s5, outputting the audio signal subjected to time delay compensation; wherein the steps from S2 to S5 are executed circularly so as to adjust audio output in real time; head motion prediction is carried out by using the recurrent neural network, and the head position and the motion trend of the user can be accurately estimated in a millisecond level, so that audio pre-rendering and accurate output are realized.

The invention provides an eye muscle derived compensatory head position auxiliary identification device based on instantaneous eye movement capture, and relates to the technical field of medical instruments, the eye muscle derived compensatory head position auxiliary identification device comprises a rotary video playing module, a skeletal muscle key point capture module, a capture module and a photo output module; the detected person watches the video, the video rotates in the reverse direction from the compensatory head position to the horizontal position, if the head position at the horizontal position is not improved, the video rotates towards the compensatory head position, in the rotating process, skeletal muscle key points capture the opposite sides of face and neck key points of the detected person and the head position is digitized, a capture module is started, photos are automatically captured, and eye position abnormity is analyzed through the photos; when eye position abnormity exists in the snapshot image, the snapshot image can be determined as an eye muscle source compensatory head position, and when the head position improvement is not obvious, one eye of the examiner is covered, and the other eye continues to watch the video. And the detected person watches the video, and after the video stops rotating, the head position and the fixation point are kept stable until the photo is automatically captured. When the head position of the snapshot image is improved, the head position can be clearly determined as the eye muscle-derived compensatory head position.

The invention relates to the technical field of ophthalmologic operations, and provides an intelligent head position recognition and correction system in ophthalmologic operations, comprising: an intelligent pillow which is designed according to human head engineering, is provided with a self-adaptive adjustment module, and is used for performing automatic fine adjustment according to head contours and body types of different patients to ensure that the heads of the patients are stably supported; the infrared eyeball tracker is installed on a mechanical arm beside an operating bed, the infrared eyeball tracker is composed of a high-sensitivity infrared emitter, a wide-view-angle receiver and a matched optical filter, and the infrared eyeball tracker can stably work in a complex light environment and accurately capture infrared signals reflected by eyeballs. Through the high-precision nine-axis inertial measurement unit integrated in the intelligent pillow, various fine actions such as translation, rotation and inclination of the head can be monitored accurately in all directions, and the measurement precision reaches the sub-millimeter level and the sub-degree level. Therefore, the system can timely and accurately obtain the head position change information, and a reliable basis is provided for subsequent judgment and processing.

The invention discloses a self-adaptive control method for a sound field of an in-vehicle sound box based on a head position, and the main design concept of the self-adaptive control method lies in that the dynamic optimization of the sound field in the vehicle is carried out by tracking the obvious change of the head position caused by the change of the sitting posture of a driver and passengers in real time, so as to adjust the output effect of a loudspeaker in the vehicle in a self-adaptive manner. Specifically, on the basis of real-time detection of the head position of a person in a vehicle, a control strategy is calculated according to a dynamic sound field: time delay is compensated to solve the time difference problem of sound wave propagation, and the dynamic accuracy of sound image positioning is ensured; through a gain compensation mode, sound pressure level differences of loudspeakers in a vehicle with dynamic different distances relative to the head of a user are balanced, and frequency response flatness is maintained; and through phase correction, phase interference generated by spatial position difference caused by head position change is eliminated, and sound field coherence is optimized. According to the invention, the follow-up adaptation effect of the person in the vehicle and the sound field in the vehicle is realized, and the acoustic quality in the vehicle is obviously improved.

The invention belongs to the technical field of medical instruments, and discloses a neurosurgery head frame capable of achieving image recognition and position adjustment and a using method, and the neurosurgery head frame comprises a supporting base, a head supporting ring and a plurality of fixing head nail suites; the top end of a vertical plate of the supporting base is provided with an arc-shaped groove sliding way which is arranged in an inwards-concave mode, a plurality of fixing head nail sets are detachably installed on one side face of the head supporting ring in the circumferential direction of the head supporting ring and can abut against and make contact with the head of a patient to fix the head, and the head supporting ring is installed on the arc-shaped groove sliding way in a sliding mode. The head supporting ring and the arc-shaped groove slide way are locked through a locking screw, the rotation angle of the head supporting ring in the arc-shaped groove slide way can be adjusted by unscrewing the locking screw, and then the head position rotation angle of the head is adjusted. The supporting base and the head supporting ring are provided with a plurality of identification point positions. The head frame can provide fixation of different head positions required by an operation, is suitable for various different head neurosurgery operations, and can quickly recognize the change of the head position through an image.

1. The name of the design product: the main body of the head limiter for sports training. 2. The use of the design product: the overall use of the product: the design product is a wearable sports training equipment and a sports performance improvement device. Specifically, it is a head positioning device for basketball and other sports training, which limits head movement in a physical way to prevent athletes from lowering their heads when dribbling. Local use of the product: main body of the head limiter. 3. The design points of the design product: the shape of the local part to be protected. 4. The picture or photo that best indicates the design points: perspective view.

The utility model discloses a head position adjusting device and a pillow, belongs to the technical field of head adjustment, and solves the problems that in the prior art, a user can still sleep on the back to adjust the backward leaning degree of the head to open an airway to slow down snoring, and the snore caused by airway blocking due to tongue root backward falling cannot be improved. The device comprises a bottom mat, a pressure sensor fixedly connected to the bottom mat, five large three-layer air bags evenly arranged on the bottom mat at intervals and an air control structure arranged on the bottom mat. The pneumatic control structure is communicated with the three layers of large air bags; the pressure sensor is coupled with a controller circuit board in the pneumatic control structure, and the controller circuit board is further coupled with a sound sensor. According to the snoring sound received by the sound sensor and the snoring pressure under the large three-layer air bags, the controller circuit board controls the opening and closing of the air pump and the first electromagnetic valve and the second electromagnetic valve, the five large three-layer air bags are switched among four states, the head of a user is adjusted, and airway blocking and snoring caused by the fact that the root of the tongue falls backwards are prevented.

A method for assessing hearing abilities of a human person having two cars, the method comprising: —providing two audio signals (S1, S2) to two respective car speakers (15, 16) at a person's corresponding cars; —measuring at least one value of at least one parameter (x15, y15, z15, x16, y16, z16) representative of the person's head position, adapting at least one of the two audio signals (S1, S2) based on the at least one measured value ((x15, y15, z15, x16, y16, z16), and repeating the measuring and adapting often enough for the sounds provided to the person to correspond to their actual head position; —detecting that the person has found their best perception of the two sounds; —calculating from the person's head position corresponding to the best perception an overall sensitivity value, a differential sensitivity value and / or a value of a latency shift of the person.

The present invention relates to methods, devices, and systems for dynamically adjusting mandibular advancement. In certain embodiments, the devices and systems employ actuator assemblies configured to allow a subject's lower jaw to be advanced by a minimum amount (e.g., trigged by obstructive sleep apnea (OSA) or associated significant oxygen saturations), but still allow the subject to move their jaw further forward, laterally, and open / close on their own. In some embodiments, the devices and systems employ an oxygen saturation measuring sensor linked to a motor control processor that: i) advances extending shafts forward when the oxygen saturation measuring sensor detects significant changes to oxygen saturation levels or other conditions that may signal OSA (e.g. a signal from another sleep monitoring device), and ii) retract the extending shafts backwards when the oxygen saturation measuring sensor detect normal oxygen saturation levels or other condition is met (e.g. elapsed time, head position, etc.).

A head tracking system HTS (100, 200) and associated method and head worn assembly, configured to determine a head position and / or a head orientation of a user, the HTS comprising: one or more optical sensors (112) producing optical measurements; and one or more inertial sensors (104) producing inertial measurements; a processor configured, when the optical sensors fail to provide optical measurements to determine the head location and the head orientation of a user, to operate in a coasting mode using the inertial measurements from the one or more inertial sensors to determine the head location and the head orientation of a user, the processor configured to further: determine a figure of merit FOM (346) for coasting errors based on a combination of one or more of errors in an estimated inertial sensor bias, a random drift and noise of the inertial sensor and the inertial sensor gain and alignment errors; compare (348) the FOM with a threshold to determine whether the inertial measurements provide a valid or invalid head location and / or head orientation; and determine a subsequent operation from a plurality of possible subsequent operations of the HTS based on whether the head location and / or head orientation is valid or invalid.

The invention relates to an interaction method and device, electronic equipment and a storage medium. The method comprises the following steps: displaying a broadcast control component and a relative pose locking option in an augmented reality space; the playing control component comprises a video playing window and a playing control option, and the video playing window is used for playing a video; in response to a selection operation on the relative pose locking option, setting the relative pose of the head of the user and the broadcast control component to be in a locking state; under the condition that the relative pose of the head of the user and the broadcast control assembly is in the locked state, the broadcast control assembly moves along with the head of the user, and the relative pose of the head of the user and the broadcast control assembly is kept unchanged all the time. By adopting the technical scheme provided by the invention, even if the head position and posture of the user are changed, the head angle does not need to be frequently adjusted to keep the video playing window in the visual field range, so that the fatigue feeling of the user when watching the video is relieved. In addition, the immersion state of the video watched by the user cannot be interrupted due to the change of the head position and posture.

Provided are a device and method for generating information on vertigo by tracking changes in eyes and head position, a computer-readable recording medium, and a computer program. More specifically, according to the device and method, movement of a patient's eyes and head is tracked in a video of the patient on the basis of a deep learning model to generate information on vertigo. The computer program for implementing the method is stored in the computer-readable recording medium.

Provided is an analysis system for analyzing the function of a semicircular canal under rotational stimulation, which includes a vestibular ocular reflex data acquisition element for acquiring first vestibular ocular reflex data obtained by dividing a rotational angle amount of a vestibular ocular reflex by a head position rotational angle amount, and second vestibular ocular reflex data obtained by dividing a residual rotational angle amount obtained by subtracting, from the head position rotational angle amount, a rotational angle amount based on a compensatory saccade (CUS), and analyzing the function of a semicircular canal based on the second vestibular ocular reflex data, or the first vestibular ocular reflex data and the second vestibular ocular reflex data.

The present invention discloses a head position self-calibration and self-positioning system for real person HRTF measurement, the system comprising: a real person head center calibration module, a module for calibrating the position of the head center inside the human head; a sound source spatial distribution sphere center calibration module, a module for calibrating the position of the virtual sphere center of the sound source spatial distribution in space; a self-calibration and self-positioning module, a module for the subject to calibrate and position the head center on the virtual sphere center. Also disclosed is a head position self-calibration and self-positioning method for real person HRTF measurement. By using the scheme of the present invention, the head position self-calibration and self-positioning of real person HRTF measurement can be conveniently and efficiently realized.

The present application provides a facial nerve motion data capture system and method, the system comprising: a head stabilizing device, a focusing and lighting device, a designated camera and a seat; the seat is arranged below the head stabilizing device and cooperates with the head stabilizing device to provide a seat for a patient with facial paralysis; the designated camera is arranged directly in front of the seat and faces the seat; the focusing and lighting device is symmetrically arranged on the left and right sides of the designated camera and faces the seat; the head stabilizing device is used to provide support for the head position of the facial paralysis patient and calibrate the head position of the facial paralysis patient when the facial paralysis patient sits on the seat; the focusing and lighting device is used to adjust the shooting environment for the facial paralysis patient to a shooting environment that meets the target shooting requirements; the designated camera cooperates with the focusing and lighting device to record the facial nerve motion image of the facial paralysis patient when the head position of the facial paralysis patient and the shooting environment are calibrated.

In a head-mounted device, a gaze-tracking sensor may measure a vergence angle associated with the user's eyes. The vergence angle may be used to determine the user's eye focus depth. Virtual content may be presented at a depth that is equal to the eye focus depth. When the depth of the virtual content is not equal to the eye focus depth, the virtual content may be shifted towards the eye focus depth. Once the depth of the virtual content is approximately equal to the eye focus depth, the depth of the virtual content may be locked. The depth of the virtual content may remain locked until one or more unlock criteria are met. The unlock criteria may be based on the vergence angle of the user's eyes, a head rotation, and / or a head position.

A device 1 for measuring the position of a head of a subject (2, fig 2) relative to a wall (3, fig 2) against which they are standing is positioned in contact with the wall 3 and includes at least two indicator zones 21, 22 for indicating whether the position of the tragus (7, fig 3A) of the subject 2 relative to the wall 3 corresponds to a normal head position (first indicator zone 21) or an abnormal head position (second indicator zone 22). The second indicator zone 22 may correspond to a forward head position. There may be a third indicator zone 23 corresponding to an extended neck position. The second and third indicator zones 22, 23 may be graded with numbers and / or colours 31-33, 41-43 to indicate the severity of the abnormal head position. The device 1 may include a base 10 with a wall abutment surface 8. The device may be used in a tragus to wall test (TWT) and may be used to generate a posture score.

The invention relates to the field of pediatric eye examination equipment, in particular to examination equipment and method for pediatric eye infectious diseases. The inspection equipment and method for the eye infectious diseases in the pediatric department have safety protection performance and inspection accuracy. The device comprises a base, a height adjusting assembly, an angle adjusting assembly and the like, the height adjusting assembly used for lifting the head of a patient is arranged on the rear side of the base, and the angle adjusting assembly used for finely adjusting the rotation amplitude of the head of the patient is arranged on the upper portion of the isolation hood. Under the isolation protection effect of the isolation cover, through cooperation of the height adjusting assembly and the angle adjusting assembly, the head of a patient with different body forms can be accurately limited, the rotation angle can be finely adjusted, a good examination view can be provided for medical staff, and the examination efficiency is improved. And the situation that the patient does not cooperate or the head of the patient is twisted at will in the examination process can be effectively avoided, and then the eye examination efficiency and safety protection performance of the patient can be improved.

1. The name of the design product: neck pillow (butterfly wings). 2. The use of the design product: the design product is used to fit the neck curve and provide support when sleeping or resting, relieve the pressure on the cervical spine by fixing the head position, and thus improve the quality of sleep. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

A method for using a mobile device and a mobile device for determining a person's viewpoint are provided. The method includes: determining the head position and pupil position of the person while they are looking at a target; and determining the viewpoint based on a surrogate of at least the eye portion of the person's head, the surrogate being set to the determined head and pupil positions. The method further includes generating the surrogate from the mobile device.

The invention discloses a method for judging jaw malformation based on facial soft tissue feature points, which comprises the following steps of: automatically positioning key feature points in a side face optical image by using a pre-trained neural network model, establishing a coordinate system, correcting the deviation of a head posture in the image, and pre-diagnosing the jaw malformation condition; in the model training stage, a face optical image and an X-ray image which are paired are used, common feature points are extracted to register soft tissue and a bony structure, a deep neural network is used for learning the space mapping relation of the face optical image and the X-ray image, a coordinate system error introduced by an optical photo posture is calculated, and a head position normalization neural network model is formed; in the application, only a single face optical image is input to the model, the pre-training model can automatically identify the feature points, posture calibration and space standardization are completed, and automatic classification and auxiliary diagnosis results of jaw malformation are output according to the posture calibration and the space standardization.

The present disclosure provides a method and a system for estimating the 3D head position of a driver in a vehicle. The method includes capturing an image of the driver and identifying an area of ​​interest focused on the driver's head within the image. Furthermore, a virtual camera perspective is created by generating a cropped image centered on the head position. The true coordinates of the head in the original image are then transformed to align with the perspective of the virtual camera. This alignment ensures that the coordinates in the virtual camera perspective accurately correspond to the driver's head position. Finally, a pre-trained estimation model is applied to the transformed, cropped image to determine the 3D position of the driver's head, enabling accurate, real-time monitoring of the driver's orientation and position.The method improves the accuracy of the estimation by standardizing head positioning in relation to the camera viewpoint, which is a basic requirement for driver assistance and safety systems.

The utility model discloses a medical prone position ventilation auxiliary device, and belongs to the technical field of medical instruments. The device mainly comprises a base and a head supporting assembly arranged on the base, a through hole is formed in the base, the base is an oval annular body, the head supporting assembly comprises two face supporting air bags arranged on the top face of the base, and a forehead supporting air bag is further arranged on the top face of the base. According to the medical prone position ventilation auxiliary device, the two faces of the human body are supported through the two face supporting air bags, the forehead part of the human body is supported through the forehead supporting air bag, and the positions of the faces on the two sides are adjusted by adjusting the amount of air in the face supporting air bags; the head is raised and lowered by adjusting the gas amount in the forehead supporting air bag, the situation that the face is pressed and hurt due to long-time face pressing is prevented, meanwhile, neck muscle strain caused by long-time fixing of the head position is avoided, the face supporting air bag and the forehead supporting air bag have a certain height, and sputum drainage is better facilitated.

A head tracking system (HTS) 200 and head worn assembly determines a user’s head position and / or orientation. The HTS comprises optical sensor(s) and inertial sensor(s) producing optical 210 and ine

The utility model discloses a head fixing assembly with damping and adjustable stroke, which comprises a fixing frame, and an adjusting connecting rod is sleeved on the fixing frame; the adjusting connecting rod comprises two fixing shells which are symmetrically arranged, the two fixing shells are arranged on the fixing frame in a sleeving mode, silica gel dampers are installed between the two fixing shells and the fixing frame, the silica gel dampers are arranged on the fixing frame in a sleeving mode, and the two fixing shells are jointly and rotationally connected with a hair clasp. The head-adjustable hair straightener is simple in structure and convenient to use, solves the problem that a detector is not easy to straighten the head position during detection, can adapt to faces with different lengths through the connecting rod, can assist the head to be fixed through the hair clasp, and can also straighten the hair on the face.

The present application discloses a head position detection method, device and digital photography equipment. In the digital photography equipment, the head rotation assembly can move the generator, and emit radiation from various angles to the flat-panel detector assembly for exposure and image acquisition; and when the generator moves, the photoelectric sensor on it can receive light passing through the light-transmitting holes on the code disk of the head rotation assembly. In response to the shooting instruction; the head rotation assembly is controlled to make the generator move from the initial position toward the designated shooting position corresponding to the shooting instruction; the number of pulses of the photoelectric sensor is counted once when the high-level signal returned by the photoelectric sensor becomes a low-level signal, then by monitoring the change in the number of pulses of the photoelectric sensor, the position change of the generator relative to each light-transmitting hole can be determined, and then the current angle and position of the generator can be obtained; when the generator reaches the designated shooting position, the generator is controlled to perform exposure to shoot the target image.