273 results about "Hand position" patented technology

The invention relates to the technical field of electromagnetic valves, in particular to an intelligent control faucet and a faucet body, the faucet carries a control system, and the system comprises an environment interference suppression module, a gesture recognition processing module, an electromagnetic hysteresis compensation module, a multi-parameter coupling optimization module and a residual magnetism elimination control module. According to the method, the infrared compensation proportion is dynamically adjusted by fusing the environment light intensity and the hand position information, the interference suppression capability is improved, the recognition stability under complex illumination is enhanced, the action consistency is extracted in combination with the gesture track waveform and the dynamic response feature, and the recognition accuracy is improved; electromagnetic hysteresis is dynamically corrected based on real-time current and displacement deviation combined with a temperature factor, motion feedback precision is improved, multi-parameter coupling is fused with multi-physical field data to construct a stable control reference, system sensitivity is enhanced, a reverse pulse sequence is designed by capturing a current attenuation waveform, residual magnetism interference is effectively eliminated, and system performance is improved. And multi-dimensional improvement of identification precision, control stability and response efficiency is integrally realized.

The invention discloses a video stream-based hand hygiene qualified behavior subject identification method for a hand hygiene behavior. The method comprises the following steps of: acquiring a gait, posture and hand action feature image frame sequence; hand position detection and tracking are performed through a target detection model and an optical flow method; classifying hand actions in each image frame through a fine-grained feature extraction model; the effectiveness of the action classification result is judged through a sliding window method, and a final action classification sequence is output; user identity recognition is carried out by fusing the gait, the posture and the hand action features through an identity recognition network, and user identity information is obtained; and finally, counting a comprehensive score of the hand hygiene process in combination with the action classification sequence and the related time, associating the score with the user identity information, and screening out a hand hygiene behavior subject with a qualified evaluation result. According to the invention, high-precision and real-time hand hygiene behavior detection and user identity information identification can be realized, and a more comprehensive scheme is provided for hand hygiene evaluation and management.

To more stably determine the position and attitude of a hand gripping a target object.An information processing device includes: a position / attitude estimation unit that, taking each of points included in point cloud data generated based on a sensing result for a target object as contact points, estimates, for each of the points, candidates for a position and an attitude of a hand that grips the target object; a target object shape estimation unit that estimates a shape of the target object based on a distribution of the candidates for the position and the attitude estimated for each of the points; and a position / attitude determination unit that determines the position and the attitude of the hand gripping the target object based on the shape of the target object estimated.

An extended Reality (XR) system is provided for providing a user interface in an XR environment. The XR system detects a position and an orientation of a hand of a user. The XR system determines a user view of the hand using the detected position and orientation. In response to determining the user view is of a dorsal surface of the hand, the XR system causes display of a hand-centric user interface using a set of dorsal surface user interface elements. In response to determining the user view is of a palmar surface of the hand, the XR system causes display of the hand-centric user interface using a set of palmar user interface elements. The XR system detects, using the set of tracking sensors, a user input based on an interaction with the hand-centric user interface. The XR system then performs an action based on the detected user input.

An extended Reality (XR) system is provided for providing a user interface in an XR environment. The XR system detects a position and an orientation of a hand of a user. The XR system determines a user view of the hand using the detected position and orientation. In response to determining the user view is of a dorsal surface of the hand, the XR system causes display of a hand-centric user interface using a set of dorsal surface user interface elements. In response to determining the user view is of a palmar surface of the hand, the XR system causes display of the hand-centric user interface using a set of palmar user interface elements. The XR system detects, using the set of tracking sensors, a user input based on an interaction with the hand-centric user interface. The XR system then performs an action based on the detected user input.

The invention provides an MR training system based on gesture tracking. The MR training system comprises a head-mounted display device, a gesture tracking module, an environment sensing module, a virtual-real fusion engine, a training evaluation module and a multi-channel feedback module. The head display device is integrated with a binocular RGB camera, an infrared ToF depth sensor and a millimeter wave radar array, the RGB camera tracks and positions a hand position through a skeleton and collects a hand image at the same time, the millimeter wave radar array captures submillimeter displacement data of hand micro-motion, and the submillimeter displacement data is transmitted to the head display device through the infrared ToF depth sensor. Transmitting the acquired hand image and displacement data to a virtual-real fusion engine; the infrared ToF depth sensor directly calculates the distance between a target object and the sensor by emitting a modulated near-infrared light pulse and measuring the time difference of light reflected to the sensor, and generates a pixel-by-pixel depth map; a skeleton model of 21 joint points of a hand is constructed, the angle variation of the associated joints is calculated in real time, holding, rotating and pressing operation actions are recognized, and the operation actions are tracked and optimized according to image data and displacement data collected by head display equipment.

1. Name of the designed product: waterproof mobile phone shell (with buckle hand position). 2. Use of the designed product: for waterproof mobile phone shell. 3. Design points of the designed product: in shape. 4. Pictures or photos that best show the design points: perspective view 1. 5. Other circumstances that need to be explained: A and B are transparent surfaces.

The invention provides a sewing action recognition method and system, a medium and a terminal. The method comprises the following steps: acquiring a sewing machine working area image when a turner performs sewing operation; acquiring a cloth contour and a hand position in the working area image of the sewing machine; acquiring sewing action information of the sewing machine; the sewing action information comprises the sewing needle number, the presser foot lifting state and the thread trimming frequency; and obtaining a sewing action recognition result according to the cloth contour, the hand position and the sewing action information. According to the sewing action recognition method and system, the medium and the terminal, accurate recognition of the sewing action is achieved through fusion of multi-modal data, and rapidness and high efficiency are achieved.

The invention provides an unhooking robot, and belongs to the technical field of compartment unhooking, the unhooking robot specifically comprises a chassis and a mechanical arm, the mechanical arm is connected with a manipulator, and the manipulator is used for carrying out unhooking operation on a compartment; the mechanical arm is connected with the manipulator and used for adjusting the position of the manipulator. The chassis is used for bearing the mechanical arm, and the chassis is arranged on the side of the carriage and can move in the same direction as the carriage; a telescopic positioning device is arranged on the chassis, and the two ends of the telescopic positioning device are connected to the chassis and the compartment respectively. Compared with the prior art, the time for unhooking operation through the mechanical arm is short, other preparatory work is completed before the compartment stops, namely the chassis is driven to move through movement of the compartment, in this way, in the compartment deceleration process, the mechanical arm can be controlled to move, and operation such as alignment of the mechanical arm and a hook handle is completed; and therefore, when the carriage stops, quick unhooking operation can be carried out through the manipulator.

The invention relates to the technical field of robots, and discloses a finger capturing device and method for reinforcement learning of a humanoid robot, and the device comprises finger modules which are disposed on each finger of the humanoid robot, and each finger module comprises an IMU sensor, an LED lamp, a touch sensor, and a processing module; the IMU sensor is used for collecting motion state data of fingers; the LED lamps are used for carrying out ID identification on each finger through a flicker sequence of the LED lamps; the processing module is used for processing data acquired by the IMU sensor and controlling the LED lamp; the touch sensor is used for sensing the contact state of the finger and an external object; the camera is used for acquiring two-dimensional image data of the hand position of the humanoid robot in multiple directions; and the analysis center is used for identifying and obtaining the spatial position coordinates of each finger according to the two-dimensional image data in the multiple directions, and judging the hand posture according to the spatial position coordinates of each finger and the contact state and motion state data of the finger and the external object, so that the anti-interference performance and the accuracy of optical motion capture are improved.

The invention relates to the technical field of data anomaly detection, in particular to a monitoring video data anomaly behavior detection method based on deep learning. The method comprises the following steps: acquiring a figure video image of any figure in real time, detecting the figure video image, marking the figure video image as a target image when the front position information of the figure cannot be detected, and acquiring continuous multi-frame target images to obtain a target image set; according to the head position information and the hand position information of any person in each frame of target image in the target image set, acquiring a motion coefficient, and identifying whether any person has a suspected abnormal behavior; and if any person has the suspected abnormal behavior, determining an abnormal behavior detection result of any person according to the smoke concentration data in the target place and the pixel value difference of the pixel points in each frame of target image in the target image set. According to the invention, the abnormal behaviors of the employees in the target place can be accurately identified.

Systems and processors associated with an electronic keyboard are described. An example system includes an electronic keyboard with a threshold number of keys extending across a first width; and a display positioned above the electronic keyboard, the display extending at least as wide as the first width. The display provides real-time visual prompts aligned with each key, including the partially covered edge keys, and hosts an Al-driven user interface. A camera may capture a player's posture, hand position, gaze, and facial expressions. Transformer-based models may process inputs to generate adaptive feedback, emotion-aware coaching, and / or gamified scoring. Haptic key actuators, synchronized LEDs, and audio cues reinforce the feedback, while on-device encrypted inference and differential-privacy may filter and secure all biometric data.

An object detection method, electronic apparatus and gesture detection system are provided. A processor is configured to implement the following steps, including: executing an object detection module to detect an original image, and obtaining a first position information, a second position information and a third position information related to the same human body object from the original image through the object detection module; setting a valid determination range based on at least one of the first position information and the second position information; obtaining a hand position in the original image based on the third position information; in response to the hand position being within the valid determination range, executing a gesture recognition module; and in response to the hand position not being within the valid determination range, not executing the gesture recognition module.

The invention discloses an immersive sound effect VR sound console space positioning method and a related device, which can be used in the field of virtual reality, and the method comprises the steps: collecting the hand motion information of a user in real time, and determining the hand position; generating tactile feedback parameters based on the hand motion information; based on the tactile feedback parameters, establishing a space mapping relation between the hand and the virtual control, and calculating to obtain a coherence index of a motion trail of the virtual control; adjusting the vibration parameter based on the coherence index, and rendering the roughness corresponding to the texture parameter in real time based on the adjusted vibration parameter to obtain an optimized tactile feedback parameter; based on the optimized tactile feedback parameter, generating an audio parameter adjustment instruction and updating a visual display effect of the virtual control; and outputting an audio parameter regulation and control signal based on the visual display effect, the optimized tactile feedback parameter and the audio parameter regulation instruction. Therefore, the continuity of sensing the spatial position of the virtual control by the user is improved, and the user interaction experience is improved.

A method (100) for automatically positioning a display (52) relative to an occupant (56) interacting with the display (52) in a vehicle (10), comprising: Identifying (104) user preferences for a position of the display (52) relative to the occupant (56) in the vehicle (10) with a system controller (34A); Monitoring (106) the posture, hand position, hand movements, head movements and gaze of the occupant (56) with an occupant monitoring system (50) within the vehicle (10) and in communication with the system controller (34A); Receiving (108) a verbal input from the occupant (56) with the system controller (34A) via a microphone (58) in communication with the system controller (34A); Determining (110), with the system controller (34A), based on the data received from the occupant monitoring system (50) and the microphone (58), that the occupant (56) is performing one of the following: Reaching towards the display (52); or Viewing the display (52); when the system controller (34A) determines that the occupant (56) is reaching for the display (52), automatically moving (112) the display (52) to a first position optimal to facilitate physical interaction of the occupant (56) with the display (52); and when the system controller (34A) determines that the occupant (56) is viewing the display (52), automatically moving (114) the display (52) to a second position that is optimal for the occupant (56) to view the display (52), characterized in that identifying (104) user preferences for a position of the display (52) relative to the occupant (56) in the vehicle (10) with the system controller (34A) further includes at least one of the following: Receiving a real-time input from the occupant (56) with the system controller (34A); and Accessing, with the system controller (34A), a machine learning model (60) of the occupant's (56) preferences based on previous interactions.

The present invention provides a DJ system for processing audio data, comprising an audio input unit for receiving audio data representing a piece of music, an audio processing unit for processing the audio data, an audio output unit for playing the audio data, and a gesture detecting apparatus for detecting a hand position, which is a position in space of a hand of a user of the system, and wherein the gesture detecting apparatus is configured to detect a turntable approach gesture or a transport control gesture.

The utility model relates to the field of electric vehicle accessories, and discloses an electric vehicle head vertical handle with an embedded design, which comprises a transverse handle main body and a vertical pipe, a handle stem is arranged in the middle of the transverse handle main body, the transverse handle main body is connected to the vertical pipe through the handle stem, grips are symmetrically connected to two sides of the handle stem, and an instrument display screen is mounted on the top surface of the handle stem. A car lamp button and a horn button are installed on one grip, a shift-up button, a shift-down button and an instrument setting button are installed on the other grip, a speed regulator is further arranged on one side of the instrument setting button, and a protective layer is arranged on the outer side of the grip. Due to the highly-integrated control function, a rider can complete operation without frequently shifting the sight line or the hand position, and riding safety and convenience are improved; due to the embedded design, water can be prevented from entering, the situation of damage caused by collision is reduced, and the durability of the product is improved; and in combination with an intelligent management system, more personalized and convenient use experience is provided for a rider.

This teaching device comprises: a camera position / attitude calculation unit that, on the basis of data of a three-dimensional model of a camera-equipped hand and data of a three-dimensional model of a camera attached to the camera-equipped hand, calculates the position and attitude of the three-dimensional model of the camera, using the three-dimensional model of the camera-equipped hand as a reference; and a hand position / attitude calculation unit that, on the basis of the calculated position and attitude of the three-dimensional model of the camera using the three-dimensional model of the camera-equipped hand as a reference and calibration data obtained by mounting the camera-equipped hand on a robot and calibrating the camera, calculates the position and attitude of the three-dimensional model of the camera-equipped hand using a three-dimensional model of the robot as a reference, such calculation being for the purpose of attaching the three-dimensional model of the camera-equipped hand to the three-dimensional model of the robot.

A photographing system (101) according to an aspect of the present disclosure includes a photographing means (11), a guiding means (12), and a photographing range adjustment means (13). The photographing means (11) photographs a hand of a user. The guiding means (12) displays a guiding image serving as a mark for the user for guiding a position of his / her hand. Further, the guiding means (12) moves a position at which the guiding image is displayed. The photographing range adjustment means (13) adjusts a photographing range of the photographing means (11) to a range corresponding to the position at which the guiding image is displayed.

While a view of an environment is visible, a computer system detects that attention of a user is directed toward a location of a hand of the user, and in response: in accordance with a determination that the attention of the user is directed toward the location of the hand while first criteria are met, wherein the first criteria include a requirement that the hand is in a respective pose and oriented with a palm of the hand facing toward a viewpoint of the user in order for the first criteria to be met, the computer system displays a control corresponding to the location of the hand; and in accordance with a determination that the attention of the user is directed toward the location of the hand while the first criteria are not met, the computer system forgoes displaying the control.

The embodiment of the utility model belongs to the technical field of blister trays. The utility model further relates to a plastic uptake tray structure which comprises a plastic uptake tray body, a plurality of storage portions are arranged on the plastic uptake tray body, each storage portion comprises a module containing groove formed in the plastic uptake tray body, and the plastic uptake tray body is provided with a second hand position communicated with the module containing grooves and a first hand position communicated with the second hand position. And an avoiding groove corresponding to the second hand position is formed in the bottom of the blister tray main body. According to the plastic uptake tray, the first hand position and the second hand position are arranged, the second hand position is located between the first hand position and the module containing groove, and the setting depth of the second hand position is smaller than that of the first hand position, so that an avoiding groove corresponding to the second hand position in position can be formed in the bottom of the plastic uptake tray body; the arrangement of the avoiding grooves can ensure that the blister tray main body positioned on the upper layer is not in contact with the module bulge area in the blister tray main body positioned on the lower layer in the carrying or transporting process, so that the phenomenon of crush injury or collision injury caused by accidental collision is reduced.

A method and system for monitoring a user during an educational activity in an extended reality (XR) environment are disclosed. An educational activity is presented in an XR environment using XR hardware, and one or more sensors associated with the XR hardware monitor physical characteristics or movements of the user during the activity. A deviation detection module determines that a physical deviation event has occurred based on a deviation from an expected physical parameter associated with the educational activity. In response to the physical deviation event, a notification is generated to an instructor system, enabling real-time or post-activity review of the user’s XR experience. The monitoring may include eye tracking, head orientation tracking, hand position tracking relative to defined boundary regions, and correlation of multiple sensor inputs.

The utility model relates to the technical field of automatic liquid taking of cleaning agents, in particular to a pressure pump mechanism of an automatic liquid taking device, which comprises a support, a photoelectric sensor arranged at the top of the support and an electric control pressing mechanism. The electric control pressing mechanism comprises a guide cylinder arranged at the top of the support, a clamping sleeve arranged on the peripheral side of the guide cylinder, a coil arranged in the clamping sleeve and a magnetic control pressing block arranged in the guide cylinder. The hand position of a user is detected through the photoelectric sensor, then detection information of the photoelectric sensor is sent to the controller, and then the magnetic control pressing block in the guide cylinder is pushed out through a magnetic field generated in the center of the coil after the coil is powered on. And the lowest end of the cleaning agent bottle extrudes the pressing pump head to spray the cleaning agent in the cleaning agent bottle onto the hand of a user, so that automatic liquid taking is completed, and cross infection caused by pressing between hands is avoided.

The utility model provides a fixing device for breast radiotherapy, and belongs to the technical field of medical instruments. Comprising a bottom plate, the outer wall of the bottom plate is fixedly connected with a plurality of arm supporting rods, the outer walls of the arm supporting rods are fixedly connected with hand holding rods, rod bodies of the hand holding rods are slidably connected with grips, and the top ends of the grips are fixedly connected with two rotating plates. A bottom plate is arranged, the outer wall of the bottom plate is fixedly connected with a plurality of arm supporting rods, the outer walls of the arm supporting rods are fixedly connected with hand holding rods, rod bodies of the hand holding rods are slidably connected with grips, and the top ends of the grips are fixedly connected with two rotating plates; and the clamping hand assembly is used for improving the clamping effect on the hand body position of the patient, and the clamping hand assembly is connected with the rotating plate.

The invention relates to a children learning machine which is used for helping children to identify clock indications and natural interestingness related to time and learn interestingness knowledge containing time concepts by shifting an hour hand and a minute hand with hands. Comprising a dial plate substrate with time and minute scale values, a rear cover plate, an hour hand and a minute hand, the rear end of the hour hand passes through a main control circuit board and is engaged with an hour hand positioning disc, and an hour hand conductive elastic sheet on the hour hand positioning disc is in conductive contact with a time point conductive matrix; the inner end of the minute hand passes through the hour hand positioning disc and is fixedly connected with the minute hand positioning disc. A minute hand conductive elastic sheet on the minute hand positioning disc is in conductive connection with the minute point conductive matrix. The watch dial, the hour hand, the minute hand and the voice playing module are combined, convenience is provided for children to learn and recognize time points pointed by the hour hand and the minute hand of the clock respectively, and in addition, anecdotes related to some special time points can be learned through the voice playing module.

The invention relates to the technical field of reading exhibition, and particularly discloses an immersive reading interaction method and system for an exhibition scene. The method comprises the following steps: obtaining house type arrangement data, carrying out initialization virtual arrangement, and constructing a virtual reading exhibition scene comprising a plurality of virtual bookshelves; carrying out real-time camera shooting positioning, carrying out position mapping in the virtual reading exhibition scene, and determining a target bookshelf; performing signal positioning, acquiring a real-time hand position, and selecting a target book; and starting virtual reading of the target book, and performing book preference optimization on the plurality of virtual bookshelves. A virtual reading exhibition scene can be constructed, a target bookshelf is determined and a target book is selected through position mapping of camera positioning and book selection of signal positioning, and reading recording and book preference optimization are performed, so that home reading exhibition is realized, and all-people and popularization reading popularization is promoted; and the problems of space congestion and disorder of offline reading exhibition are solved, and the comfort and immersion experience of reading exhibition are effectively improved.

The invention relates to a tower clock (1) comprising - a time display unit (2) with a dial (3) and at least two hands, - a stepper motor (4) which is connected to the first pointer (Z1) via a first clock shaft (W1), - an accelerometer configured as a 2D accelerometer or as a 3D accelerometer (5) which is attached to the first pointer (Z1) or to the first clock shaft (W1), - a reading unit (6) for reading the accelerometer (5), and - a control computer (7) coupled to the reading unit (6) and to the stepper motor (4), which is configured to receive a time signal (ZS), to receive a pointer position signal (PS) read by the reading unit (6) from the accelerometer (5) and to control the stepper motor (4) depending on the time signal (ZS) and the pointer position signal (PS). Furthermore, the invention relates to a method for operating the tower clock (1).

The invention relates to a device of a vehicle (1) with detection units (E11 to E1n, E21 to E2m) for detecting a person in the vicinity of the vehicle (1), wherein an evaluation and control unit (3) is configured to identify a person as a vehicle user (2) based on an accompanying identification element (4). According to the invention, it is provided that - the evaluation and control unit (3) is designed to determine the position of the vehicle user (2) relative to the vehicle (1) by means of communication between one of the first detection units (E11 to E1n) and the identification element (4), - the evaluation and control unit (3) is designed to analyze a gaze direction and / or a body posture and / or a hand position in order to recognize an intention of the vehicle user (2), whereby an algorithm is used to recognize, based on the gaze direction and / or the body posture and / or the hand position, whether the vehicle user (2) is looking for something in the vehicle (1) and / or the vehicle user (2) intends to communicate with an occupant and - the evaluation and control unit (3) is designed to automatically activate interior lighting and / or move vehicle seats, and / or reduce the output volume of an infotainment system and / or open a vehicle window when a search is detected, in order to enable communication between the vehicle user (2) and the occupant.

The present invention discloses a method for identifying qualified hand hygiene behavior subjects based on video streams, comprising: obtaining a sequence of gait, posture, and hand movement feature image frames; performing hand position detection and tracking through a target detection model and an optical flow method; classifying the hand movements in each image frame through a fine-grained feature extraction model; judging the validity of the action classification results through a sliding window method, and outputting a final action classification sequence; performing user identity identification through an identity recognition network fusing gait, posture, and hand movement features to obtain user identity information; finally, combining the action classification sequence and related time statistics to comprehensively score the hand hygiene process, and associating the score with the user identity information to screen out qualified hand hygiene behavior subjects. The present invention can achieve high-precision, real-time hand hygiene behavior detection and user identity information identification, providing a more comprehensive solution for hand hygiene assessment and management.

The present disclosure discloses a handle arrangement and a method for controlling a handle arrangement, the handle arrangement comprising a base, a detection device, a handle, a detected component, and a control device. The base defines a base cavity. The detection device is arranged in the base. The handle is movable relative to the base. The detected component is arranged in the handle. The control device is communicatively connected to the detection device. The detection device is configured to detect a distance between the detected component and the detection device and to send a detected distance value to the control device, wherein the control device is configured to send different signals according to the distance value detected by the detection device.The handle arrangement of the present disclosure is capable of determining the current position of the handle from the positional relationship between the detection device and the detected device. Furthermore, the handle arrangement of the present disclosure is capable of simultaneously detecting the positions of the detected device and the hand, thereby controlling the handle. This helps the user to operate the handle without touching a handle body, thus improving usability.