853 results about "Body posture" patented technology

Methods and apparatus are disclosed for predicting events using acoustic and visual cues. The present invention processes audio and video information to identify one or more (i) acoustic cues, such as intonation patterns, pitch and loudness, (ii) visual cues, such as gaze, facial pose, body postures, hand gestures and facial expressions, or (iii) a combination of the foregoing, that are typically associated with an event, such as behavior exhibited by a video conference participant before he or she speaks. In this manner, the present invention allows the video processing system to predict events, such as the identity of the next speaker. The predictive speaker identifier operates in a learning mode to learn the characteristic profile of each participant in terms of the concept that the participant “will speak” or “will not speak” under the presence or absence of one or more predefined visual or acoustic cues. The predictive speaker identifier operates in a predictive mode to compare the learned characteristics embodied in the characteristic profile to the audio and video information and thereby predict the next speaker.

A social robot provides more believable, spontaneous, and understandable expressive communication via embodied communication capabilities by which a robot can express one or more of: paralinguistic audio expressions, sound effects or audio / vocal filters, expressive synthetic speech or pre-recorded speech, body movements and expressive gestures, body postures, lighting effects, aromas, and on-screen content, such as graphics, animations, photos, videos. These are coordinated with produced speech to enhance the expressiveness of the communication and non-verbal communication apart from speech communication.

An Intelligent Tutoring System (ITS) system is provided that is able to identify and respond adaptively to the learner's or student's affective states (i.e., emotional states such as confusion. frustration, boredom, and flow / engagement) during a typical learning experience, in addition to adapting to the learner's cognitive states. The system comprises a new signal processing model and algorithm, as well as several non-intrusive sensing devices, and identifies and assesses affective states through dialog assessment techniques, video capture and analysis of the student's face, determination of the body posture of the student, pressure on a pressure sensitive mouse, and pressure on a pressure sensitive keyboard. By synthesizing the output from these measures, the system responds with appropriate conversational and pedagogical dialog that helps the learner regulate negative emotions in order to promote learning and engagement.

The invention is suitable to the independent motion vehicles environment sensation monocular visual navigation method, first surveys the camera distortion parameter, puts the camera on the independent motion vehicles, determines transformation relation from image plane coordinate system to world coordinate system; then records current car body posture, gathers the picture in the current car body visible scope, feedback the picture to the picture operation contact surface in order to definite the walk mode of the car body and do distortion correction on the gathering picture, select the path and the path spot on the path, according to the coordinates transformation relations under the world coordinate system put the current position and choice path result to the car body and demonstrate on the graph operation contact surface by the car body width; the car body walks according to the independently evades bonds or the way track way till the current visible scope last way spot, and then circling start from the gather picture to the final object point. The invention applies the monocular measuring technique in the unknown environment the visual navigation.

In a method, device and compute-readable medium for evaluating the prevalence of different postures of a patient, signals are sensed that indicate the posture of the patient during a monitoring period having a predetermined length, specific body postures of the patient are determined during this monitoring period from the sensed signals, the amount of time the patient spends in each of the specific postures is measured, information regarding each specific posture, and the associated amount of time spent in that posture, are stored, and the prevalence of the different postures of the patient is evaluated by classifying the stored information with respect to specific postures and the amount of time in each posture position.

A control device for a legged mobile robot, in which a correction manipulated variable of a desired floor reaction force (desired floor reaction force's moment) is subsequently determined based on an error between an actual state quantity, such as a body posture angle, of the robot 1 and a desired state quantity of the same, and at the same time, a desired movement of the robot 1 is subsequently determined by the use of the correction manipulated variable and a dynamic model. At this time, a friction force component, which defines a frictional force between the robot 1 and a floor such as a translation floor reaction force's horizontal component, is set as a variable to be limited, and an allowable range of the variable to be limited is set. The desired movement is determined so that the variable to be limited remains within the allowable range and a resultant force of an inertial force and gravity, generated by the movement of the robot 1 on the dynamic model, balances with a floor reaction force obtained by correcting the desired floor reaction force by the correction manipulated variable. The desired movement is determined by adjusting a plurality of movement modes having mutually different generation ratios of a floor reaction force's moment and a translation floor reaction force.

The invention provides a take-off and landing system for an unmanned ship-borne unmanned aerial vehicle, which exerts good stability and can effectively solve a problem that the unmanned aerial vehicle cannot safely take off and land on a bumpy unmanned ship. The take-off and landing system for the unmanned ship-borne unmanned aerial vehicle, provided by the invention, comprises a take-off and landing fixing device, a take-off and landing hanging device and a take-off and landing control device, wherein the take-off and landing fixing device is arranged on the unmanned ship; the take-off and landing hanging device is arranged on the unmanned aerial vehicle; the unmanned aerial vehicle takes off from and lands on the unmanned ship through use of the take-off and landing control device to control coordination between the take-off and landing fixing device and the take-off and landing hanging device; and the take-off and landing control device comprises a take-off and landing process monitoring camera, a meteorological monitoring module, a ship body posture monitoring module, a wireless communication module and a remote control terminal. The take-off and landing system for the unmanned ship-borne unmanned aerial vehicle, provided by the invention, can be applied to the technical field of safety of water area operation equipment.

Systems, methods and devices to measure and potentially promote thermogenesis, preferably non-exercise activity thermogenesis are disclosed. In the various embodiments, the present invention may rely on one or more sensors that detect a subject's body posture and / or activity. Feedback regarding the subject's posture and / or activity (relative to preferred postures and / or activity levels) may preferably be provided after the data is retrieved and analyzed. A power interlock may also be used to control delivery of electrical energy based on a subject's posture and / or activity level.

Embodiments of the present invention provide a distributed computer system and a method for determining the quality of sleep of a sleeping user 340. The distributed computer system will determine the quality of sleep by detecting the changes in body posture of the sleeping user 340. The quality of sleep will be determined by the feature vectors associated with each posture of the sleeping user 340. The posture of the user will be determined by recording a body motion signal 200 caused by the mechanical and muscle movements of the body of the user.

A control device for a legged mobile robot, in which a correction manipulated variable of a desired floor reaction force (desired floor reaction force's moment) is subsequently determined based on an error between an actual state quantity, such as a body posture angle, of the robot 1 and a desired state quantity of the same, and at the same time, a desired movement of the robot 1 is subsequently determined by the use of the correction manipulated variable and a dynamic model. At this time, a friction force component, which defines a frictional force between the robot 1 and a floor such as a translation floor reaction force's horizontal component, is set as a variable to be limited, and an allowable range of the variable to be limited is set. The desired movement is determined so that the variable to be limited remains within the allowable range and a resultant force of an inertial force and gravity, generated by the movement of the robot 1 on the dynamic model, balances with a floor reaction force obtained by correcting the desired floor reaction force by the correction manipulated variable. The desired movement is determined by adjusting a plurality of movement modes having mutually different generation ratios of a floor reaction force's moment and a translation floor reaction force.

The invention belongs to the technical field of medical appliances and relates to a robot for transferring and transporting patients, which comprises a vehicle frame 12, an omnidirectional running system, a transferring arm 2, an arm supporting frame 4, a horizontal moving mechanism, a folded lifting mechanism, a main controller and a control box, wherein the omnidirectional running system, the transferring arm 2, the arm supporting frame 4, the horizontal moving mechanism, the folded lifting mechanism and the main controller are installed on the vehicle frame 12; the control box can be in wireless communication with the main controller; the folded lifting mechanism is positioned between the vehicle frame 12 and the arm supporting frame 4; the transferring arm 2 is put on the arm supporting frame 4 and moves through the horizontal moving mechanism; and the transferring arm comprises two or more than two sub arms 22 with the same structure. The robot of the invention can be used for achieving the purpose of mechanically transporting patients among operation tables, sickbeds or inspection equipment without applying external force by nursing personnel or family members, and the wholeprocess of transferring patients has no need of changing the body postures, thereby avoiding pain and re-injury to patients.

Remotely detecting the presence of urine or feces in a diaper of an infant or adult using a disposable sensor placed inside the diaper, in conjunction with a permanent device that is capable of wirelessly transmitting data to a mobile device or base station is disclosed. The permanent device can also be capable of measuring temperature and body movements. This additional information can be used in conjunction with the detection of urine or feces to identify patterns.

The invention provides an Internet intelligent mirror based on a natural user interface. The Internet intelligent mirror mainly comprises a base, a square mirror frame, a filter single lens, a light emitting screen and a mainboard. The filter single lens, the light emitting screen and the mainboard are located in the square mirror frame. The filter single lens is located on one side, facing a user, of the intelligent mirror. The light emitting screen and the mainboard are located on the rear side of the filter single lens. The mainboard is located below the light emitting screen. A loudspeaker A, an infrared transmitter, a color camera, a depth sensor, a microphone and a loudspeaker B are sequentially disposed on the upper portion of the front side of the square mirror frame from left to right. During use, a user can interacts with the mirror through voices and gestures by facing the mirror, and experiences such as physical data measuring and virtual try on are achieved. The Internet intelligent mirror has the advantages that the mirror can understand human languages and the gestures of people; when the user faces the mirror, Internet information browsing can be achieved by voice control, virtual clothes can be tried on through gesture control so as to decide intraday wearing, and body bone motion trajectories can be recorded and analyzed to aid various exercises high in body posture requirements.

The invention discloses a height measuring method and a height measuring device based on body posture identification. The method comprises the following steps of: acquiring a scene image comprising a body posture; automatically identifying the body posture, wherein different height measuring methods are adopted for bodies of different postures; when a human body is in a posture which is difficult for measuring height directly, partitioning different positions constructing the height or arm reach in a body image to obtain the physical lengths of different positions constructing the height or arm reach respectively; and further summarizing and estimating the height of the human body. According to the method and the device, the automatic degree and height measuring efficiency of body height measurement are increased greatly.

A system for controlling a human-controlled proxy robot surrogate is presented. The system includes a plurality of motion capture sensors for monitoring and capturing all movements of a human handler such that each change in joint angle, body posture or position; wherein the motion capture sensors are similar in operation to sensors utilized in motion picture animation, suitably modified to track critical handler movements in near real time. A plurality of controls attached to the proxy robot surrogate is also presented that relays the monitored and captured movements of the human handler as “follow me” data to the proxy robot surrogate in which the plurality of controls are configured such that the proxy robot surrogate emulates the movements of the human handler.

The invention relates to a method for recovering a real-time three-dimensional body posture based on multimodal fusion. The method can be used for recovering three-dimensional framework information of a human body by utilizing multiple technologies of depth map analysis, color identification, face detection and the like to obtain coordinates of main joint points of the human body in a real world. According to the method, on the basis of scene depth images and scene color images synchronously acquired at different moments, position information of the head of the human body can be acquired by a face detection method; position information of the four-limb end points with color marks of the human body are acquired by a color identification method; position information of the elbows and the knees of the human body is figured out by virtue of the position information of the four-limb end points and a mapping relation between the color maps and the depth maps; and an acquired framework is subjected to smooth processing by time domain information to reconstruct movement information of the human body in real time. Compared with the conventional technology for recovering the three-dimensional body posture by near-infrared equipment, the method provided by the invention can improve the recovery stability, and allows a human body movement capture process to be more convenient.

A force measurement system includes a force measurement assembly with a top surface configured to receive at least one portion of the body of a subject and at least one force transducer configured to sense forces and / or moments being applied to the top surface; at least one visual display device having an output screen configured to at least partially circumscribe three sides of a torso of the subject, and one or more data processing devices operatively coupled to the force measurement assembly and the at least one visual display device. In one or more embodiments, the force measurement assembly may be in the form of an instrumented treadmill. In one or more further embodiments, the force measurement system may additionally comprise a motion capture system configured to detect the motion of one or more body gestures of the subject.

The invention relates to a coordination control method of spatial rope-tying robot compounded body postures after target catching. According to the coordination control method of spatial rope-tying robot compounded body postures after target catching, rope-tying drawing force is brought in, a coordinated posture control method of the rope-tying drawing force and a thrustor is designed, a coordinated control method of the rope-tying drawing force and the thrustor is firstly designed, then considering limitations when rope tying is utilized to control the postures, a coordinated control method of posture control only by means of the thrustor is designed, and lastly a switchover control method of a controller is designed to carry out coordinated posture control.

The invention discloses a moving body posture estimating method which can accurately position body framework points and effectively obtain the features with more expressive power in a three-dimensional moving body and is more effective and simpler in structure. The method includes the steps of firstly, preprocessing depth image data through a median filter method, and conducting part calibrating on body pixels through a Dijkstra algorithm based on geodesic distance; secondly, determining that the number of clusters of each type is three on the basis of a regional feature point extracting algorithm of a K-mean value clustering algorithm, and extracting 32 posture features to express different body postures; thirdly, obtaining position calibrating information of the framework points through PoserPro2012 software in the training stage, synthesizing 300 frames to simulate posture features of a human body, calibrating standard framework points, and calculating a linear regression model of the posture features and the framework points through the posture feature points and the standard framework points of a training sample so that the mapping relation between the posture features and the standard framework points can be obtained.

The invention relates to the technical field of human body fall-down detecting and intervening and provides a human body fall-down prevention early warning and intervening method and system. The human body fall-down prevention early warning and intervening method includes the steps that real-time detection is performed on the body posture of a monitored object, body posture information of the monitored object is collected, and detection data are obtained; fusion processing is performed on the detection data so as to obtain the processed signal data; the processed signal data are compared with a set threshold so as to judge whether the monitored object inclines to fall down or not, and when the monitored object inclines to fall down, early warning information is sent out before the monitored object falls down; fall-down prevention shoes work, intervening measures are carried out, and fall-down prevention is performed. The human body fall-down prevention early warning and intervening method and system achieve early warning and intervening before the human body falls down.

The invention discloses a barrier-avoidance control method combining a depth camera and supersonic wave for robot and a system thereof. The system comprises the depth camera and an ultrasonic ranging module installed on the robot, a control module which is installed in the robot for processing barrier information of inner and outer barriers, and a display screen for displaying obstacle information, wherein the depth data camera and the ultrasonic ranging module are electrically and respectively connected with the input end of the control module, and the output end of the control module is electrically connected with the display screen. The depth data camera shoots depth images with current posture of 0.3-4m and shooting angle of 60 degrees on a real-time basis and determines the existence of outer barriers. The ultrasonic ranging module determines the existence of inner barriers within 0-0.3m body posture of the robot. Non-blind area detection for environment by a robot is realized, so that the robot can effectively avoid barriers during walking.

A system is described for analyzing plays of a sporting event based on body-pose information in conjunction with real-world positional tracking data. The system permits segmentation of sporting event plays into discrete time periods and the labeling of appropriate body-pose characteristics for each period. The system allows for comparison and fine-grained analysis of plays with respect to either a series of body-pose vertices that exist in continuous space (i.e., skeleton) or map directly to attributes, using the positional tracking data and play information to account for contextual differences. To enable analysis for the former, the system performs a projection to 3D space, followed by a spatiotemporal alignment step. Through the system, the importance of particular body-pose motions or specific attributes to the success of particular sporting event plays is quantified.

The invention discloses a method for extracting face feature. Accordingly, body posture analytical data and depth data provided by a Kinect camera are combined with a Depth-Active Appearance Model (AMM) algorithm, and the method based on 2.5 dimensional images is formed. The method comprises steps of training the AMM of the Depth-AMM algorithm by using a principal component analysis method and extracting face features based on the AMM of the Depth-AMM algorithm after completed training.

The invention provides a screen video image adjusting system and method which are applied to a display device. The display device comprises a display screen, a shooting unit and an actuating unit. According to the screen video image adjusting system and method, when a user watches video images on the display screen, the face area, the eye area and eyeball positions are distinguished continuously by means of the face detection technology, the display direction of the display screen or the playing angle and direction of the video images are automatically adjusted according to the detected eye horizontal line offset direction and inclination angle of the user through the actuating unit installed on the display device, and therefore the problems that the user changes the body posture, consequently the difference is caused between the watching sight line and the display angle of the video images, eyestrain is caused and even eyesight is influenced are effectively avoided.

The invention discloses an auxiliary training tool for comprehensive rehabilitation of cerebral palsy. The auxiliary training tool comprises a chassis, a lower limb exoskeleton device and a suspension device, wherein the chassis comprises universal casters with the locking function, a lower chassis, an upper chassis and an exoskeleton device inclination adjusting mechanism; the lower limb exoskeleton device is fixedly mounted on the chassis, and can realize rehabilitation training such as flexion / extension, adduction / abduction and pronation / supination of hip joints, flexion / extension of the knee joint, and dorsi-flexion / plantar-flexion, strephenopodia / strephexopodia and pronation ans supination of feet; the suspension device is fixedly mounted on the chassis, and plays a role in slinging, weight reduction and upper body posture correction of paitents. The auxiliary training tool can help patients with cerebral palsy to correct the abnormal posture of lower limbs, carry out the rehabilitation training on all joints of the lower limbs, promotes the development of all the joints of the lower limbs, and gradually establishes the normal standing and walking functions.

A tool includes different tool heads, and an angularly adjustable handle. The angular adjustability allows better ergonomic body posture during use, thus reducing stress and injury, and also allows multiple functions for each tool. The handle comfortably receives a user's hand, with the user's thumb or forefinger located at a release button. The release button is spring-biased and includes teeth that inter-engage with teeth on the tool head to latchingly hold a selected angular position. A resilient cover encases the handle and the release button, preventing dirt from entering the button area to prevent jamming. The covering slips onto the handle and includes an annular lip that stretches over an end surface to retain the covering on the handle. The cultivator includes tines that, by adjusting an angle of the handle, extend in a direction parallel the handle but offset therefrom, or that extend at an angle to the handle.

The invention, which belongs to the technical field of image processing and computer vision, relates to a sitting posture detecting method based on target detection and body posture estimation. A fusion feature formed by fusion of a feature I and a feature II is extracted, the fusion feature is inputted into a CNN, and if the fusion feature is from a training set, the feature is used for traininga network parameter; if the fusion feature is from a verification set, the feature is used for verifying a network parameter, an error signal is transmitted by a back propagation algorithm, the gradient is updated, an optimal value is found, and classification regression is carried out by using flexible maximum activation function Softmax to obtain a final classification result and classificationaccuracy. Therefore, a problem of target loss under the complicated condition with multiple targets in existing sitting posture detection is solved; the traditional method relying on a wearable deviceor sensor is abandoned; and with the method based on target detection and body posture estimation, the sitting posture of each task target can be determined accurately under the conditions of complicated background and high group density.

The invention relates to the technical field of human body fall-down detection and provides a human body fall-down preventing early warning method and a human body fall-down preventing early warning device. The method includes the steps that real-time detection is performed on the body posture of a monitored object, body posture information of the monitored object is collected, and detection data are obtained; fusion processing is performed on the detection data, and signal data are obtained after being processed; the processed signal data are compared with a set threshold, whether the monitored object inclines to fall down or not is judged, when the monitored object inclines to fall down, warning is given before the monitored object falls down; the body posture information of the monitored object includes triaxial acceleration information, triaxial angular velocity information and triaxial body angle of inclination information of the monitored object, the detection data are nine-axial inertia sensing data which are obtained through detection by an integrated chip, and collection of the body posture information, fusion processing of the detection data and the fall-down judgment of the monitored object are completed on the same circuit board. The human body fall-down preventing early warning method and the human body fall-down preventing early warning device achieve early warning before the human body falls down and are high in integration level.

In order to enable patient data to be reliably taken into account in a simple manner for examination by means of an imaging medical diagnostic equipment of a patient positionable on a table top of a patient table, it is provided according to the invention for an occupancy distribution exerted by the patient on the table top to be ascertained, patient data corresponding to this occupancy distribution, specifically in respect of body dimensions and / or body posture, to be determined, and the diagnostic equipment to be adjusted according to the patient data; to ascertain the occupancy distribution, there is advantageously provided a distribution of pressure sensors.