534 results about "Posture correction" patented technology

The invention discloses a wearable human body gait detection self-localization method which comprises the following steps: (1) aiming at the motion of a human body, establishing a state transition model, and calculating a position, a speed and a posture of a strapdown inertial navigation system; (2) utilizing constraint conditions of human body behavior detection to capture and extract human body static gait features; (3) performing attitude error integration according to zero-speed, zero angular speed and posture correction; (4) utilizing an intelligent filter to perform error estimation; (5) utilizing evaluated error to correct the posture and position of the human body motion. According to the invention, in terms of indoor positioning, powerful support is provided for convenient level and accuracy.

Disclosed are methods and systems for monitoring and correcting sitting posture of a user and for discouraging sedentary behavior. The system comprises a processor, a portable seat cover with embedded pressure sensors and an angle sensor, a notification device, and a non-transitory storage medium for storing program code. The program code, when executed by the processor, causes the processor to initiate an idleness timer to count how long the user has been sitting, monitor the user's sitting posture by receiving real-time sensor measurements; identify a sitting posture by applying a posture identification rule, generate a posture correction notification through the notification device if the identified sitting posture is not ergonomically correct, determine whether a sedentary threshold has been reached and generate a stand notification if the sedentary threshold has been reached. Embodiments of the present invention help improve sitting posture and reduce sedentary behavior to minimize associated adverse health effects.

The invention provides a biopsy method for use in human face identification and belongs to the technical field of mode identification. The algorithm provided by the invention comprises: firstly, giving a 'please-face-the-camera-with-face' prompt to a user logging in regardless of the current posture of the user, finding the face and eye socket areas by using an Adaboost human face sorter during the posture correction of the user, determining upper and low eyelids and left and right eye corners by using differential projection and precisely framing the positions of the eye sockets; secondly, computing optical flow field of two adjacent frames in an input video sequence by using an LK algorithm; and thirdly, further processing obtained optical flow data to obtain an optical flow amplitude, acquiring the number of the pixels with high amplitude, computing the specific gravity of the pixels with high amplitude, and determining eye movement if the proportion is big. Experiments show that for a real human face, eye movement can be detected easily due to a heavy optical flow generated on the eyes in a posture correction and eye twinkling process, while for a picture, eyes only perform a micro movement no matter how the picture moves or translations. When the method is used for biopsy, a better effect can be obtained.

The present invention relates to a user-participating type fitness lecture system and a fitness training method using the same. More specifically, the present invention relates to a user-participating type fitness lecture system that provides direction for correcting a user's posture or motion by comparing the user's motions with user created contents (UCC). When the contents are played back for the user to emulate, correctness of the user's motion is grasped by detecting and comparing motions in the contents with the user's motion photographed through a camera, and providing the user with posture correction information in image or voice formats. In one embodiment, a user-participating type fitness lecture system according to the present invention comprises a user terminal for photographing a user and transmitting a moving image of the user while playing back a UCC selected by the user; and a posture correction server for providing the user terminal with the UCC selected by the user, receiving the moving image from the user terminal, comparing the moving image with the played back UCC, and directing correction of the user's posture in voice or image.

The invention discloses a human face payment authentication system and method. The human face payment authentication system comprises a human face original data binding module, a face quality evaluation module, a face posture correction module, a human face recognition module and a payment data intelligent treatment module, wherein the human face original data binding module uses standard user face information as original binding data; the face quality evaluation module is used for performing comprehensive quality evaluation of data collection faces and screening comparison data; the face posture correction module is used for correcting deviated postures on the premise that the face data is not lost; the human face recognition module is used for collecting information of human faces needing to be compared, extracting face feature information and comparing the face feature information with corresponding face feature information in a database so as to judge whether the feature information belongs to the same person; the payment data intelligent treatment module is used for performing comprehensive evaluation and judgment on human face information after human face payment authentication transaction is successful. The human face payment authentication system and method provided by the invention can be used for improving the safety and convenience of payment, and meanwhile, the recognition accuracy of the system is improved.

A posture adjustment system includes a set of sensors coupled to a chair on which a person may sit. The posture adjustment system gathers data from the set of sensors and generates a posture model that reflects a posture associated with the seated person. The posture adjustment system then determines corrections to the posture of the person that could, potentially, improve their posture. The posture adjustment system then indicates those corrections to the person, or, alternatively, applies a set of adjustments to the chair to cause the person to assume a new posture that reflects the posture corrections.

The invention provides a pedestrian re-identification method based on transfer learning and deep feature fusion. The pedestrian re-identification method comprises the following steps of pre-training,human body posture correction and segmentation, feature vector, deep feature fusion, model training, model testing and result identification. According to the invention, global and local features of pedestrians are extracted by using a deep convolutional neural network; deep fusion is carried out on the two features to obtain final pedestrian feature representation; then, in the training process of the deep convolutional neural network, a pedestrian re-identification network model with a better effect is obtained by adopting a transfer learning mode, and finally, features extracted by the pedestrian re-identification network model have stronger resolution capability, so that the purpose of improving the pedestrian re-identification accuracy is achieved.

A pose rectification method for rectifying a pose in data representing face images, comprising the steps of:A-acquiring a least one test frame including 2D near infrared image data, 2D visible light image data, and a depth map;C-estimating the pose of a face in said test frame by aligning said depth map with a 3D model of a head of known orientation;D-mapping at least one of said 2D image on the depth map, so as to generate textured image data;E-projecting the textured image data in 2D so as to generate data representing a pose-rectified 2D projected image.

The invention discloses an intelligent seat with a function of sitting posture correction. The intelligent seat comprises a backrest (1), a seat body (3) and chair legs (4), wherein pressure sensors (2) are arranged on the contact surface of the backrest (1); two alarm devices (6) are arranged at the two sides of the backrest (1); the top of the backrest (1) is provided with a man-computer interaction screen (8); pressure sensors (2) are arranged on the contact surface of the seat body (3); the bottom of the seat body (3) is provided with a processor and a timer; the pressure sensors (2), the man-computer interaction screen (8) and the timer are connected with the processor. When the sitting posture of a user is not correct, the intelligent seat shakes at a certain amplitude and an alarm is given to remind the user.

A posture correction brace for a person has a tightening mechanism that allows a user to pull a cord to pull down on the back of a pair of shoulder straps, thereby pulling the shoulders back to correct the person's posture. The front ends of the shoulder straps are typically also attached to the back of the wearer, to help the posture correction brace pull the shoulders back as the shoulder straps tighten.

The invention relates to a shooting action training method. The shooting action training method comprises the following steps: obtaining the shooting association data of a shooting action and a basketball moving state as well as shooting average by combining the basketball moving state information which is fed back by a basketball, the shooting actions of arms which are fed back by arm sleeves when the basketball is shot, and the shooting average which is fed back by a basket; comparing the shooting association data with a preset shooting action model which serves as a training standard, and finding and feeding back the difference between the shooting association data and the shooting action model to obtain training data, wherein the basketball moving state information comprises shooting trajectory, flying speed, rotating speed, and shooting angle; the shooting action comprises muscle power strength, power generating order, the postures of arms and fingers, and the action trajectory of the arms. The method is used for analyzing the coherent postures and muscle effectiveness of a basketball player in a shooting practice exercise, and giving posture correction and muscle power generation suggestions.

The invention is applied to the technical field of smart televisions, and provides a method and device for correcting the posture of a smart television user. The method comprises the following steps: obtaining a depth image in the front of a smart television, and dividing the depth image to obtain a depth image of a human body part; extracting skeleton data of the depth image of the human body part, and drawing according to the skeleton data to obtain a three-dimensional image of a human body skeleton; comparing joint node information of the three-dimensional image with joint node information of a preset three-dimensional skeleton template to obtain a matching degree of the human body skeleton and a preset skeleton gesture; and giving an alarm by the smart television if the matching degree of the human body skeleton and the preset skeleton gesture is beyond a preset threshold value range, such that the posture of the user is corrected. According to the method and device disclosed by the invention, the watching posture of the user while watching the smart television can be automatically detected; furthermore, the user is reminded to adjust the watching posture in time; and thus, the effective correction effect is ensured.

The present disclosure relates to a motion posture rectification method and apparatus. The motion posture correction method comprises: controlling a wearable device to acquire and store motion data of a user; extracting the motion data from the wearable device, and obtaining a motion track of the user according to the motion data; and comparing the motion track with a pre-stored standard motion track corresponding to a motion posture type, and obtaining difference information, so as to enable the user to rectify a motion posture according to the difference information. According to the motion posture correction method and apparatus provided by the embodiments of the present disclosure, rectification can be performed on different motion postures, the application range is wide, and the adaptability is high.

The invention discloses a miniature multifunctional human body posture intelligent detector and a detection method, and belongs to the field of human body posture detection. The detector comprises a posture sensing and detecting unit, an A / D converting unit, an information processing unit, a memory unit, an input unit, an output unit and a power supply unit, and is characterized in that: sensors adopted by the posture sensing and detecting unit are a horizontal accelerometer and a vertical accelerometer. The detector utilizes accelerometers as posture sensors, and provides kinematical parameters under partial motion states for examinees, wherein the motion states mainly include running, rapid walking, jumping and the like, and the parameters include running or walking frequency, kinematic velocity, jumping height and distance, and angle and speed of rising to jump. The detector can provide posture information in the maximum range for people in need of posture correction, comprises posture detection under various conditions such as relative rest, walking or taking a bus and the like of the examinees, and realizes prompt type active posture correction and good habit cultivation.

The invention discloses a human body posture correction device based on a Kinect sensor. The correction device comprises a skeleton information acquisition unit, a control unit and a warning unit, wherein the skeleton information acquisition unit comprises the Kinect sensor, a depth of field data acquisition module and a joint point information processing module; the control unit comprises a posture judging module and a warning signal transmitting module; the warning unit comprises a warning signal receiving module, a warning module, a warning message generating module and a 3G module. The human body posture correction device has the advantages of excellent expansibility, zero radiation, accurate information acquisition and no need of personnel wear.

The invention relates to a posture correction method based on depth information and skeleton information, and the method comprises the steps: (1), carrying out the effective skeleton point screening based on a user ID and a skeleton space coordinate depth value; (2), carrying out the smoothing of the skeleton information, and carrying out the coordinate standardization of skeleton points in a skeleton space coordinate system; (3), drawing skeleton vectors, and calculating a direction cosine value of each skeleton vector; (4), obtaining a training data set and a testing data set; (5), enabling the data sets to serve as the input of a Bayes regularization BP neural network, and carrying out the recognition of 25 skeleton points and 24 skeleton segments through the Bayes regularization BP neural network; (6), carrying out the analysis and processing of a result. The method irons out the defect that a color camera is liable to be affected by light, can accurately track a human body in a visual field, and also improves the naturalness of man-machine interaction.

The invention discloses a face posture correction method and a face posture correction device. The method comprises the following steps: getting a 2D face image to be corrected; detecting the 2D key points of the 2D face image to be corrected, and determining the 3D key points, corresponding to the detected 2D key points, on a 3D face model; updating the 3D key points through iterative calculation according to the determined 3D key points; and determining a posture-corrected 2D face image according to the updated 3D key points. According to the technical scheme of the invention, the 3D key points of the 3D face model are adjusted gradually and the geometric parameters of the 3D face model are updated in the process of face posture adjustment, and the face posture is corrected according to the final updated geometric parameters of the 3D face model, so the gap between the corrected 2D face image and an actual face front image is narrowed, and the performance of face authentication / recognition is improved.

The invention relates to an underwater moving object location and navigation method based on frequency spectrum transformation. In the method, (1) an onboard underwater sound transceiver transmits a symmetric triangle frequency modulation signal s(t) to an underwater moving object; (2) an underwater receiver array on an onboard measurement device receives echo signals; (3) the weight number of each array element in the underwater sound receiver array is adjusted by utilizing information of signals in the direction of an incoming wave; and (4) the onboard measurement device determines the coordinates of the underwater moving object in geodetic coordinates. An underwater moving object location and navigation device based on spectrum transformation mainly comprises the onboard measurement device, a shiphull posture correction device, an underwater sound transceiver on the underwater moving object, a water radio transceiver, an array signal processor, a GPS receiver and a microprocessor. The invention can not only track and locate the underwater object above water, seas on shore or in air, but also automatically locate and navigate underwater objects.

The invention discloses an agricultural machinery roll angle test method based on double antenna GNSS (global navigation satellite system) receiver / gyroscope information fusion. The white noise of the roll angle measured by a double antenna GNSS receiver is great, and the roll angle cannot be easily and directly used for agricultural machinery posture correction. The gyroscope output data is stable; the short-time stability is high, but the long-period precision is poor. A Kalman filter is used for performing fusion processing on the roll angle obtained by the double antenna GNSS receiver and the roll angular velocity obtained by a gyroscope; the precise estimation of the agricultural machinery roll angle is obtained. The method has the advantages that more continuous and stable agricultural machinery roll angle data can be formed, so that the tilt correction of the agricultural machinery is more precise.

The invention relates to a multi-sensor fusion-based robot indoor path planning method. According to the method, after a robot system reconstructs an environmental map by using visual positioning andmapping (SLAM) technology, a multi-sensor coordinated working mode is adopted, so that the robot performs path planning according to a target location determined in the map and realizes obstacle avoidance as well as posture correction and operation direction correction during the driving of the robot according to environmental data obtained by sensors mounted on the system. In order to effectivelyverify the effectiveness of the method, a depth camera, an ultrasonic sensor, an inertial sensor and the like which are mounted on the robot mobile platform are tested. A plurality of tests in an indoor environment prove that the multi-sensor collaborative work can improve mapping accuracy during a process in which the robot performs indoor working environment-based movement path planning, and can effectively realize the autonomous path planning of the machine.

In a sleep posture alerting method or an apparatus therefor, the sleep posture of a person is detected and the person is automatically alerted by an alerting device when the sleep posture is out of a predetermined body posture range. The detection of the sleep posture or at least the alerting of the person, when his / her body posture is out of the predefined body posture range, is deactivated during a sleep-in time period.

The invention discloses a three-dimensional face detection and identification technology. The major technical process comprises: first of all, carrying out three-dimensional face detection to obtain data which is obtained by use of a 3D imaging technology such as structured light or stereo visual sense and the like, secondly, carrying out three-dimensional face cutting and data preprocessing which comprise face detection, cutting, denoising and the like, then, carrying out posture correction on a three-dimensional face and performing characteristic extraction on the data, and finally, carrying out three-dimensional face identification to construct a proper classifier for determining the face data. 3D face identification research can be traced back to as early as early 90s of last century, due to restrictions of various factors, such as computing level restrictions of computers, immature 3D acquisition devices and the like, no great breakthroughs are made in correlation research. During the last decade, along with rapid development of a computer technology and the 3D imaging technology and development bottlenecks of a 2D face identification technology as well, the academic society gives more attention to the research on a 3D face identification technology.

A posture correction exercise device is disclosed to aid in correcting the common postural condition of kyphosis-lordosis by aiding in the exercise of the spinal erectors to strengthen the erectors to pull the user's spine and torso backward into normal alignment and by exercise of the mid-trapezious, rhomboid and posterior deltoid muscles to strengthen these muscles to pull the user's shoulder blades together and force the shoulders into normal alignment. The device operates by seating the user upon a declined seat to provide increased resistance by gravity. The device provides resistance to backward movement of user's body and resistance to backward rotation of user's arms. The hands of the user are positioned in supinated palms-up hand positions to increase the training effect of the backward rotation of the user's arms.

The invention relates to a posture training and correction equipment and a control method of posture training and correction. In the posture training and correction equipment, a power supply module supplies power to a microprocessor module, a body posture measurement module, a wireless transmission module and a body posture correction reminder module; the body posture measurement module collects the angle data of the body posture when people sit or stand, and transmits the data to the core control microprocessor module; the core control microprocessor module is used for analyzing the receivedangle signal, comparing the analyzed angle signal with pre-collected body posture reference data and judging whether the body posture is standard, then the body posture correction reminder module shakes and make an indicator light illuminate for prompting people, and posture correction is achieved through correction; the wireless transmission module is used for communication between the core control microprocessor module and an externally controlled analysis and display terminal; the externally controlled analysis and display terminal is used for controlling the operation process of the equipment through wireless transmission module, analyzing and displaying posture correction feedback information and interacting with users.

A device for correcting sitting posture consisting of a back pad (10) a cord (16) and a control box (22) that is easily used on chairs with a variety of seat back heights and gives audiovisual and tactile indication on posture position.

The invention discloses a pen-holding posture correction device and an intelligent pen and relates to the field of stationery. The pen-holding posture correction device comprises a sensor, a controller and a prompt device, wherein the sensor is arranged on the main body of a pen and is used for sensing whether the pen-holding posture is correct and sending a sensing signal to the controller under the condition that the pen-holding posture is correct; the controller is used for receiving the sensing signal sent by the sensor and controlling the prompt device to send a prompt signal according to the sensing signal; the prompt device is used for sending a prompt signal according to a control command sent by the controller. According to the invention, the sensor is used for sensing the pen-holding posture of a pen-holder, the controller receives the sensing signal and sends the prompt signal to the prompt device under the condition that the pen-holding posture is correct, and the prompt device gives corresponding prompt to remind the pen-holder to correct the pen-holding posture at any time, so that the technical problem in the prior art that the wrong pen-holding posture of children or pupils is difficult to correct when children or pupils do practice in writing.

The claimed invention provides an improved posture correction tool in the form of a table to be used by chiropractic practitioners to treat mechanical disorders of the spine and musculoskeletal system. The improved posture correction tool provides a plurality of pads to support the various major areas of the body and has built in drop capability and adjustment capability for the pelvic pad, the lumbar pad, the thoracic pad and the head and cervical area. The claimed invention also has a novel cervical support.

The invention discloses a real-time human motion posture correction method and system. The method comprises the following steps: acquiring depth map data by using Kinect equipment; obtaining bone data from the depth map data, and carrying out stabilization and smoothing processing; detecting and identifying the human body posture through a preset method; evaluating the standard degree of the posture by calculating the posture matching accuracy; and feeding back a result in the posture changing correction process to a user in real time. The beneficial effects are that the user can select the fitness time and place at will, which is more suitable for modern busy office workers and young people; action done by a user can be standardized, damage to the body of the user is avoided, and a better fitness effect can be achieved when the mobile phone APP is used for action guidance; it can be avoided that wearing is cumbersome, and better user experience and effect can be obtained.