41 results about "Head tracking" patented technology

In some embodiments, a method comprises executing, by a head-tracked audio system, a first algorithm configured to dynamically update a forward head angle and a spatial orientation in response to a detected head movement, and a second algorithm configured to adjust a recentering filter based on the detected head movements, and maintaining, by the head-tracked audio system through execution of the first algorithm and the second algorithm, a spatial audio placement relative to a wearer during the detected head movements.

The invention discloses a pedestrian cross-border head tracking method and system based on multi-modal dynamic feature fusion, belongs to the technical field of computer vision, and aims to solve the technical problem of how to improve the accuracy and efficiency of pedestrian detection and the stability of cross-border head tracking. By adopting an advanced backbone network, a self-adaptive anchor frame mechanism, cross-scale feature fusion and other technologies, the detection capability of small targets and high-shielding-rate pedestrian targets is improved; an intelligent caching strategy and a model fusion method are adopted, so that repeated calculation of instance segmentation is reduced, and the efficiency of dynamic pedestrian segmentation is improved; through combination of multiple feature extraction and enhancement technologies, including optimized Mama, Transform and multi-granularity feature fusion, the purity and discrimination of the features and the adaptability to shielding and view angle changes are enhanced.

A media system and a method of using the media system to reproduce spatial audio based on head-to-torso orientation, are described. The method includes determining a head-to-source orientation and a head-to-torso orientation based on head orientation data generated by a head tracking device. Determining the head-to-torso orientation includes determining torso movements based on movements of the head. The torso can be determined to move when the head movements meet a head movement condition, such as a predetermined angle of movement or pattern of movement. A binaural audio filter that is based on a head-related transfer function corresponding to both the head-to-source orientation and the head-to-torso orientation is applied to an audio input signal to generate an audio output signal. The audio output signal is played to accurately recreate spatial audio having sounds emitted to the user by a sound source. Other aspects are also described and claimed.

Example technologies described herein relate to spatial audio on wearable playback devices, such as headphone and earbuds. Such technologies may include forms of binaural rendering of audio, which is played back on the wearable playback devices. These technologies may create or enhance an immersive listening experience which, to the listener, does not sound like you are listening on a wearable device, but are instead listening to a well-tuned, well-place, three-dimensional audio system of loudspeakers in a particular listening environment, such as the listener's actual living room.

The invention provides a target position positioning device and method. In the device, a display unit is configured to be in a transparent mode and is located right in front of the eyes of an operator; when the to-be-rescued target is located in the center of the display unit, the marking assembly marks and confirms the to-be-rescued target and sends a distance measurement instruction to the head tracker; a head tracker is worn on the head of the operator, and when the head tracker receives a distance measurement instruction, the direction of a to-be-rescued target is determined based on the rotation direction of the head of the operator, the distance between the to-be-rescued target and the head tracker is measured, and the direction and the distance are sent to a signal processing unit; the signal processing unit determines the position of the to-be-rescued target according to the orientation and the distance sent by the head tracker, and sends the position of the to-be-rescued target to the display unit; the display unit displays the position of the to-be-rescued target and the area where the to-be-rescued target is located, and positioning and indicating of the position of the to-be-rescued target can be achieved on ocean ships, rescue airplanes, lifeboats and the like.

The invention relates to a bar continuous rolling mill area blank information tracking method, and belongs to the technical field of metallurgical production control methods. According to the technical scheme, blank information is stored with rolling numbers as indexes, a rolling area is divided into tracking areas, and rolling number information of the head of a rolled piece is tracked and memorized; and the actual tracking area crossing time of the rolled piece is compared with a crossing time threshold value, and when the actual tracking area crossing time of the rolled piece is larger than or equal to the crossing time threshold value, an abnormal rolling condition is judged, and rolling number information of an abnormal rolling area is deleted. According to the method, automatic and accurate tracking of the key information of the blank in the area is realized by utilizing the characteristic that the running direction of the continuous rolling blank of the bar is single and adopting a rolled piece head tracking memory, abnormal state information deletion and affiliated information table look-up method which takes the blank information rolling plan number as an index, and the method has extremely high popularization and application value in the industry.

The invention discloses an image seeker tracking performance test method based on a simulated moving target, which comprises the following steps of: generating a simulated target and a moving track through a target simulation computer, projecting the simulated target and the moving track to a curtain, and tracking the simulated target on the curtain by an image seeker to realize the tracking speed precision and the maximum tracking speed test; then the size of the target under the tracking distance is obtained through calculation, the target simulation computer generates a simulation target and a motion trail and projects the simulation target and the motion trail to the curtain, the image seeker tracks the simulation target on the curtain through the reflective collimator, and tracking distance testing is achieved. A dynamic simulation target is provided for image seeker tracking, meanwhile, external field environment factors such as target definition, light intensity and target shielding are introduced, and the method has the advantages that the testing method is simple, the testing environment is easy to build, and online tracking debugging and synchronous testing are facilitated.

A method of rendering a stereoscopic image of an object is described. The stereoscopic image comprises a left image and a right image. The method comprises initialising a computer model of the object (200) and a texture mapping for rendering the computer model with a texture. The method comprises the steps of receiving a first image of the object from a first image sensor (14a), receiving a second image of the object from a second image sensor (14b), receiving head tracking data of the observer (360), determining one or more render camera viewpoints relative to the computer model based on the head tracking data, and rendering the stereoscopic image based on the computer model and the texture mapping using the one or more render camera viewpoints, wherein the left image of the stereoscopic image is rendered using the first image as the texture and the right image of the stereoscopic image is rendered using the second image as the texture.

The application relates to a rolling piece head tracking method for a hot rolling and coiling production line, the hot rolling and coiling production line comprising a rolling channel for conveying a rolling piece, pinch rolls matched with the rolling channel, and detection elements arranged directly above the rolling channel, and the method comprises the following steps: acquiring a head signal of the rolling piece, starting tracking and recording first tracking data S1; acquiring a signal that the rolling piece reaches the pinch rolls, stopping tracking; acquiring a horizontal installation interval L between the detection elements and the pinch rolls, and correcting the first tracking data S1 to S1=L; the method does not need to additionally increase the detection elements, reduces the cost of rolling piece head tracking, can reduce error correction caused by error signals of the increased detection elements, and guarantees the accuracy and reliability of rolling piece head position tracking; the correction means is not referenced by light signals, and can effectively avoid the influence of interference sources such as water vapor, fog, light pollution and the like in the field environment.

A control device for spatial sound effect of a headphone and a control method thereof are provided. The control device includes a receiving unit, a head tracking unit, at least three equalizers, a switch and a controller. The at least three equalizers are configured to process an original sound signal according to a head direction to obtain at least a first adjusted sound signal, a second adjusted sound signal, and a third adjusted sound signal. The switch is configured to output the first adjusted sound signal according to the head direction. If the head direction has changed to a first expected rotation direction, the controller controls the switch to output the second adjusted sound signal; and if the head direction has changed to a second expected rotation direction, the controller controls the switch to output the third adjusted sound signal.

One example method includes joining, from a client device, a virtual meeting hosted by a virtual meeting provider, the virtual meeting comprising a plurality of participants, displaying the virtual meeting on the display of the client device, receiving a plurality of head tracking signals from a head tracking sensor, the head tracking signals associated with a first user of the client device; determining, based at least in part on the head tracking signals, a movement of the of first user's head in relation to the display on which the first user is focused; and varying the volume of a first audio stream of a plurality of audio streams associated with the virtual meeting based at least in part on the movement of the first user's head.

An audio processing method includes: performing spatial analysis on binaural signals to estimate the level difference and phase difference of binaural filters characterizing the binaural signals; and performing object extraction on the binaural audio signals using the estimated level difference and phase difference to generate left / right principal component signals and left / right residual component signals. The system can perform different processing on the left / right principal components and left / right residual components using different object processing parameters, such as repositioning, equalization, compression, upmixing, channel remapping, or storage, to generate processed binaural signals, thereby providing an improved listening experience. Repositioning can be based on head-tracking sensor data.

Methods, systems, and apparatus, including computer programs encoded on computer storage media relate to a method for head tracking for video communications in a virtual environment. The system may provide a video conference session in a virtual environment. The system may provide a digital representation of the video conference participant in the virtual environment. The system may display one or more views of the virtual environment in the video conference. The system may track movement of the video conference participant to generate user movement information and may display movement of the video conference participant on the digital representation.

A head tracking system HTS, configured to determine a head position and a head orientation of a user to which display images are configured to align with the outside world scene and are configured to be presented, the HTS comprising: one or more optical sensors generating an optical measurement; and a number of inertial sensors generating an inertial measurement; a processor configured to determine the head position and the head orientation from one or both of the one or more optical sensors and the number of inertial sensors and configured to: determine an optical tracking state from the optical measurement and an inertial tracking state from the inertial measurement; when both the optical tracking state and the inertial tracking state are valid, flagging / asserting HTS operation as normal; when both the optical tracking state and the inertial tracking state are invalid, flagging / asserting HTS failure; when the optical tracking state and the inertial tracking state are valid comparing the optical measurement and the inertial measurement to determine if the HTS can operate safely based on a predetermined tracking performance required by the system.

A device and method for providing spatialized audio by dynamic head tracking includes, in a static phase, providing a user with a spatialized acoustic signal that is perceived to originate from a virtual sound stage at a first position, and, when it is determined that one or more predetermined conditions are met, which may include whether or not the user's head has crossed an angular boundary, rotating the virtual sound stage to track the user's head movement.

The application discloses a pedestrian cross-border head tracking method and system based on multi-modal dynamic feature fusion, belongs to the technical field of computer vision, and aims to solve the technical problem of how to improve the accuracy and efficiency of pedestrian detection and the stability of cross-border head tracking. By adopting advanced backbone networks, an adaptive anchor box mechanism and cross-scale feature fusion technology, the detection capability for small targets and high occlusion rate pedestrian targets is improved. Intelligent caching strategies and model fusion methods reduce the repeated calculation of instance segmentation and improve the efficiency of dynamic pedestrian segmentation. The combination of various feature extraction and enhancement technologies, including optimized Mamba, Transformer and multi-granularity feature fusion, enhances the purity, discriminability and adaptability to occlusion and view angle changes of features.

The invention provides a head motion tracking method and device, computer equipment and a storage medium. The method comprises the steps that reference prediction state data are determined according to user head tracking data collected by at least one sensor at the current moment, and the reference prediction state data comprise reference prediction speed data; determining a target gain parameter according to the reference prediction speed data; according to the target gain parameter and reference prediction state data of at least one previous moment, performing dynamic smoothing processing on the reference prediction state data at the current moment to obtain target prediction state data; and generating a prediction picture according to the target prediction state data, and presenting the prediction picture to a user. According to the scheme, the more stable picture can be generated, and the stable virtual object is presented to the user, so that the user can interact with the virtual object, and the effect of improving the use experience of the user is achieved.

The application relates to an airborne mixed reality display system and method, which comprises a laser positioning base station for sending horizontal-axis laser rays and vertical-axis laser rays; a first laser positioning sensor fixedly arranged on a cabin; a second laser positioning sensor arranged on a head-mounted device; an inertial measurement sensor arranged on the head-mounted device; and a computer for fusing first position information and a motion track with second position information through a Kalman filtering algorithm to obtain real-time position of the head-mounted device; the head-mounted device is used for unifying the real-time position of the head-mounted device, current pose information of the cabin and world coordinates of a virtual target in the same coordinate. The laser positioning result and the IMU positioning result are fused through the Kalman filtering technology, so that real-time and accurate positioning of the mixed reality head-mounted device is realized. The error existing in head tracking of the airborne AR is reduced.

The utility model relates to a kind of head tracking spatial audio sound field restoration circuit, including main control chip, loudspeaker unit, ear detection sensor and motion sensing unit, the main control chip is the main control chip U1 of built-in MCU and bluetooth chip, it is used for wireless connection mobile terminal;It further includes the first power supply circuit for the power supply of ear detection sensor, the enable end of the main control chip U1 connection first power supply circuit to control whether first power supply circuit supplies power to ear detection sensor;It is higher in the degree of integration, and circuit structure design is simple, greatly reduce the manufacturing cost of this product;Enhance the anti-interference ability of ear detection sensor, avoid interference sensor weak capacitance signal, and, also, can control the switch of ear detection sensor in time by controlling first power supply circuit.

In some embodiments, a method comprises executing, by a head-tracked audio system, a first algorithm configured to dynamically update a forward head angle and a spatial orientation in response to a detected head movement, and a second algorithm configured to adjust a recentering filter based on the detected head movements, and maintaining, by the head-tracked audio system through execution of the first algorithm and the second algorithm, a spatial audio placement relative to a wearer during the detected head movements.

The invention relates to a computer-implemented method for modifying the rendering of a region of a 3D scene in an immersive environment, characterized in that the region is computed based on the 3D position of a head tracking device (HED) of the user and the 3D position of at least one hand tracking device (HAD1, HAD2) of the user.

The utility model discloses a single-head tracking edge trimmer. The single-head tracking edge trimmer comprises a translation device, a lifting device, a propelling device, a guide device and an edge trimming device, the translation device drives the lifting device to move in the length direction of the plate; the lifting device drives the propelling device to move in the thickness direction of the plate; the trimming device is driven to move in the width direction of the plate; the translation device, the lifting device and the propelling device are arranged, the trimming device is arranged on the propelling device, and the trimming device can accurately move in a three-dimensional space through combined movement of the three axial directions, so that trimming can be completed in the length direction, the width direction and the thickness direction of a plate, separate and independent machining is not needed, and the production efficiency is improved. Plates do not need to be rotated, and the machining efficiency is high; compared with multi-head trimming equipment, the design of the single trimming device has the advantages that the mechanical interference risk is reduced, the core working parts are concentrated, the daily maintenance is simpler and more convenient, and the operation and maintenance cost is lower.

The invention provides a delay measurement system and method for a head movement tracking spatial audio algorithm, and the method comprises the steps: arranging an artificial head model above a rotating device, arranging a loudspeaker on the outer surface of the artificial head model, and arranging a first microphone at a position close to the loudspeaker, a to-be-tested device with a head movement tracking space audio algorithm is plugged in the ear of the artificial head model, a second microphone is arranged in the ear where the to-be-tested device is plugged, the second microphone records test sound emitted by the to-be-tested device, the loudspeaker emits contrast sound when the artificial head model starts to rotate, and the contrast sound is compared with the test sound when the artificial head model starts to rotate. And the first microphone receives the comparison sound, and then the delay time is calculated according to the initial change time of the frequency response amplitude of the test sound and the first receiving time of the comparison sound, so that the end-to-end delay generated after the head rotation of each piece of to-be-tested equipment (various types of to-be-tested earphones) can be accurately obtained.

The invention discloses a 3D stereoscopic vision multi-normal-form visual angle control method and visual angle control system, and relates to the field of virtual simulation teaching, and the method comprises the steps: responding to an observation target switching instruction or an observation range zooming instruction, taking a current observation target as a reference point, calculating the target relative position and the target orientation of a camera, and calculating the target relative position and the target orientation; driving a camera to move to the target relative position and the target orientation, and adjusting parameters of the camera to enable the target to be in a visual field; acquiring head posture data of a user, and generating a camera visual angle offset according to the head posture data; and in response to a control instruction input by the user, controlling the camera to rotate or move around the observation target according to the camera visual angle offset. Through multi-normal-form control of automatic view angle optimization, head tracking fine tuning and keyboard navigation, view angle automatic following and smooth switching are realized, the manual operation frequency is reduced, the 3D space observation efficiency and immersion can be integrally improved, visual fatigue can be reduced, and automobile practical training teaching intelligence can be realized.

This invention discloses a spatial soundscape adaptive control method with head tracking, relating to the fields of spatial audio processing and human-computer interaction. The method includes: acquiring head posture data and performing time alignment and filtering to obtain a head state sequence; based on the head state sequence, performing multi-scale decomposition within a preset time window to obtain a multi-scale behavioral feature set; constructing a perceptual factor vector representing the head motion state based on the multi-scale behavioral feature set; constructing a spatial perceptual stable potential field based on the perceptual factor vector and the current head posture; and constraining the sound source parameters in the spatial soundscape within the sound image change tolerance range defined by the spatial perceptual stable potential field to generate a target soundscape parameter set. By distinguishing between conscious rotation and unconscious jitter, dynamic adaptive control is achieved, balancing sound image stability and response sensitivity, enhancing the immersive experience, and is computationally efficient.

The invention discloses a steel biting signal judgment method based on head and tail position tracking of each rack, and belongs to the technical field of hot continuous rolling automatic control. The method comprises a steel biting signal judgment step and a steel throwing signal judgment step; wherein the steel biting signal judgment step comprises the following steps: after each rack bites steel, respectively calculating a head tracking position; after the upstream rack bites steel, if the rolling force reaches the steel biting threshold and the strip steel reaches the steel biting range, the current rack triggers a steel biting signal; the step of judging the steel throwing signal comprises the following steps of: for the current rack, calculating a tail tracking position after an upstream rack throws steel; and if the rolling force reaches the steel throwing threshold and the strip steel reaches the steel throwing range, the current rack resets a steel biting signal. By adopting the steel biting signal judgment method based on head and tail position tracking of each rack, the problems of mistaken steel biting and mistaken steel throwing caused by load and speed fluctuation can be effectively avoided, and the production stability and the control precision are improved.

The present application relates to a kind of multi-channel immersive sound space linkage decoding playing method and system, by the time-frequency domain joint feature extraction of multi-channel PCM frame sequence, generate five-dimensional acoustic feature vector and input distilled optimization lightweight Transform encoder, infer the semantic role probability distribution of each sound channel by position coding and multi-head attention mechanism.Combined with the preset auditory saliency rule, construct dynamic weight migration decision logic unit, realize the resource adaptive tilt strategy for the sound channel with speech enhancement or motion prediction demand.Combined with system real-time computing power monitoring, according to the demand of resource availability dynamically scheduling computing load to key sound channel, and through HRTF adaptive filtering and head tracking compensation optimization space rendering effect.Finally, multi-channel audio stream with high-precision spatial positioning characteristics is formed.The scheme realizes the adaptive efficient allocation of audio rendering resources, effectively enhances the immersive listening experience and system operation efficiency.

A method of head tracking of a subject in a hearing system comprising a first hearing device and a second hearing device is disclosed. The method comprises obtaining first accelerometer data from a first accelerometer of the first hearing device. The method comprises obtaining second accelerometer data from a second accelerometer of the second hearing device. The method comprises determining, based on the first accelerometer data and the second accelerometer data, a head parameter indicative of a position and / or movement of a head of the subject. The method comprises providing an output indicative of the head parameter.

A ride system may include a ride vehicle that supports a passenger and an attention tracker to determine a current direction of attention of the passenger. The ride system may also include a control system for maintaining an environment of the passenger. Maintaining the environment may include determining a set of content to be incorporated into the environment based at least in part on the current direction of attention as well as a future direction of attention that is determined utilizing a machine learning algorithm.

Disclosed are systems and methods for rendering personal sound zones (PSZs) with head tracking using multiple loudspeakers, utilizing a Spatially Adaptive Neural Network (SANN) to dynamically generate and update audio filters that create acoustically bright and dark zones based on the listener head positions. First, the SANN encodes listener head coordinates and outputs corresponding PSZ filters as either time-domain impulse responses or frequency domain complex -valued coefficients. Then, acoustic transfer functions (ATFs) corresponding to the rendering loudspeakers and control points within PSZs are simulated at random room acoustics conditions and optionally measured in a specific rendering environment. The combined ATFs along with a unified loss function that incorporates multiple PSZ design objectives, are utilized in training the SANN for randomly sampled listener positions within the rendering area. Finally, the trained SANN is used for generating PSZ filters in real-time given a stream of head position data from a head tracking device.