716 results about "Human skeleton" patented technology

A surgical simulation device includes a support structure and animal tissue carried in a tray. A simulated human skeleton is carried by the support structure above the animal tissue and includes simulated human skin. A camera images the animal tissue and an image processor receives images of markers positioned on the ribs and animal tissue and forms a three-dimensional wireframe image. An operating table is adjacent a local robotic surgery station as part of a robotic surgery station and includes at least one patient support configured to support the patient during robotic surgery. At least one patient force / torque sensor is coupled to the at least one patient support and configured to sense at least one of force and torque experienced by the patient during robotic surgery.

A surgical simulation device includes a support structure and animal tissue carried in a tray. A simulated human skeleton is carried by the support structure above the animal tissue and includes simulated human skin. A camera images the animal tissue and an image processor receives images of markers positioned on the ribs and animal tissue and forms a three-dimensional wireframe image. An operating table is adjacent a local robotic surgery station as part of a robotic surgery station and includes at least one patient support configured to support the patient during robotic surgery. At least one patient force / torque sensor is coupled to the at least one patient support and configured to sense at least one of force and torque experienced by the patient during robotic surgery.

The invention discloses a passenger abnormal behavior identification method based on a human skeleton sequence, which comprises the following steps: 1) shooting an escalator area monitoring video image by a camera; 2) detecting that passenger face through the SVM and trac the passenger face with the KCF to obtain the passenger motion trajectory in the escalator; 3) extracting that human skeleton from the image by using the OpenPose depth learn network; 4) matching that human skeleton to the corresponding passenger trajectory to construct the human skeleton sequence of the passenger; 5) detecting that abnormal behavior skeleton sequence from the passenger human skeleton sequence through template match; 6) using DTW to match it with various abnormal behavior skeleton sequence template to identify abnormal behavior. That invention can accurately and real-time identify a plurality of abnormal behavior of passengers in the escalator base on human skeleton sequence, according to the abnormalbehavior type to control the operation situation of the escalator, and avoid the occurrence of safety accident.

The invention provides a human behavior recognition method based on a depth neural network, comprising the following steps: acquiring original depth data stream of an actor; extracting human skeleton joint data from the original depth data stream of the actor; modeling the entire human body with three-dimensional coordinates corresponding to the extracted human skeleton joint data; extracting features by modeling the entire human body, sending feature data to a restricted Boltzmann machine network for preprocessing, training out a depth neural network model based on received weight initialization BP neural network parameters, and identifying a behavior from a feature extraction result; overlapping the extracted human skeleton joint data and the actual human body through multi-threaded parallel processing, and displaying the identified behavior in real time; and establishing an abnormal behavior template library and alarming for a detected abnormal behavior. The change of human behavior can be detected in real time, and alarm can be raised for abnormal behaviors (such as fall) of a human body.

The invention relates to a three dimensional (3D) virtual fitting method based on somatosensory technology. The 3D virtual fitting method based on the somatosensory technology is characterized by including the steps: step one, setting up a hardware system; step two, tracking human skeleton; step three, reconstructing three dimensions; step four, conducting real-time measurement on three dimensional sign information of a human three-dimensional model, utilizing a measured characteristic size to adjust the size of corresponding place of a garment model and enabling the garment model to fit in with a human body figure and to be superimposed on the human three-dimensional model; steps five, fitting in a scene. Due to the novel information technology of somatosensory location, strengthening reality and image recognition, the 3D virtual fitting method based on somatosensory technology shoots and manufactures real garments into high definition images which fit in with a certain specification, utilizes a depth camera sensor to collect image information of human skeleton and depth, perfectly mixes the garments and real images and produces display effects of different garments in different scenes in a mode of strengthening reality.

The invention discloses a man-machine cooperation device and method based on a Kinect video camera. The man-machine cooperation device and method based on the Kinect video camera is mainly based on a Kinect video camera which is launched by the Microsoft Corporation recently so as to achieve detecting and tracking of a human body target. The man-machine cooperation device and method based on the Kinect video camera can accurately judge the position of a target object and the intention of a tester by utilizing Kinect human skeleton detecting technology, and therefore the risks which occur in the process of handover are avoided. Besides, a rail rapid transit (RRT) algorithm based on working space is provided to achieve route planning. Through repeated experimental verification, the system can conduct interpersonal handover safely.

The invention provides a man-computer interaction method for an intelligent human skeleton tracking control robot on the basis of kinect. The man-computer interaction method includes the steps of detecting actions of an operator through a 3D depth sensor, obtaining data frames, converting the data frames into an image, splitting objects and background environments similar to a human body in the image, obtaining depth-of-field data, extracting human skeleton information, identifying different positions of the human body, building a 3D coordinate of joints of the human body, identifying rotation information of skeleton joints of the two hands of the human body, identifying which hand of the human body is triggered according to catching of changes of angles of the different skeleton joints, analyzing different action characteristics of the operator, using corresponding characters as control instructions which are sent to a robot of a lower computer, receiving and processing the characters through an AVR single-chip microcomputer master controller, controlling the robot of the lower computer to carry out corresponding actions, and achieving man-computer interaction of the intelligent human skeleton tracking control robot on the basis of the kinect. According to the method, restraints of traditional external equipment on man-computer interaction are eliminated, and natural man-computer interaction is achieved.

The invention discloses a human skeleton behavior recognition method and device based on deep reinforcement learning. The method comprises: uniform sampling is carried out on each video segment in a training set to obtain a video with a fixed frame number, thereby training a graphic convolutional neural network; after parameter fixation of the graphic convolutional neural network, an extraction frame network is trained by using the graphic convolutional neural network to obtain a representative frame meeting a preset condition; the graphic convolutional neural network is updated by using the representative frame meeting the preset condition; a target video is obtained and uniform sampling is carried out on the target video, so that a frame obtained by sampling is sent to the extraction frame network to obtain a key frame; and the key frame is sent to the updated graphic convolutional neural network to obtain a final type of the behavior. Therefore, the discriminability of the selectedframe is enhanced; redundant information is removed; the recognition performance is improved; and the calculation amount at the test phase is reduced. Besides, with full utilization of the topologicalrelationship of the human skeletons, the performance of the behavior recognition is improved.

The invention discloses a behavior identification method based on a recurrent neural network and human skeleton movement sequences. The method comprises the following steps of normalizing node coordinates of extracted human skeleton posture sequences to eliminate influence of absolute space positions, where a human body is located, on an identification process; filtering the skeleton node coordinates through a simple smoothing filter to improve the signal to noise ratio; sending the smoothed data into the hierarchic bidirectional recurrent neural network for deep characteristic extraction and identification. Meanwhile, the invention provides a hierarchic unidirectional recurrent neural network model for coping with practical real-time online analysis requirements. The behavior identification method based on the recurrent neural network and the human skeleton movement sequences has the advantages of designing an end-to-end analyzing mode according to the structural characteristics and the motion relativity of human body, achieving high-precision identification and meanwhile avoiding complex computation, thereby being applicable to practical application. The behavior identification method based on the recurrent neural network and the human skeleton movement sequence is significant to the fields of intelligent video monitoring based on the depth camera technology, intelligent traffic management, smart city and the like.

The invention discloses an attitude detection method using a deep convolutional neural network, and is suitable for being performed in computing equipment. The method comprises the steps that a data set is divided into training and testing and preprocessed; identification learning model training of human body joint feature areas is performed so as to identify the learning network of human body joint image areas; joint coordinate positioning learning model training is performed; detection image size preprocessing is performed, and the images requiring human body attitude identification are adjusted into the size of the network input requirements; identification of the image joint areas is performed through the network and corresponding rectangular areas are defined to be saved as sub-images; the acquired sub-images act as the input to be transmitted to the joint coordinate positioning learning model to perform joint coordinate acquisition; and the acquired joint points are connected according to the human skeleton model so as to form human body attitude description. The invention also provides storage equipment and a mobile terminal.

The present invention provides a reconstruction method of human posture based on the geometrical skeleton, including:determining human skeleton pattern; obtaining 3D human skeleton pattern, pre-processing image; obtaining bianry image of separation of the background and the human; acquiring human geometrical skeleton; obtaining linear geometrical skeleton; labelling articulare of the start frame; bonding the manual labelling articulare on the geometrical skeleton, shortening the initial error; tracing the articulare by light stream method; obtaining the new position by the light stream method; processing error judgement and position correction to the new articulare obtained by the trace with the combined geometrical skeleton; processing line correction calculated by the light stream method; re-constructing the human posture; converting the two-dimensinal coordinate of the articulare to the 3D skeleton pattern by the parameter evaluating method of the proportion orthogonal projection model. The invention improves accuracy of the posture reconstruction, obtaining a high processing efficiency, capable of processing stable and effect human posture reconstruction in the intelligent video monitor system.

The invention discloses an abnormal behavior detection method, which comprises the following steps of: extracting dynamic human skeleton joints in a video by using a neural network human skeleton extraction model to form a skeleton data set; obtaining a higher-level behavior feature map corresponding to the bone, namely surface behavior features, by an ST-GCN network; and inputting the behavior feature map into the abnormal behavior classifier model, and performing matching to identify the behavior type. The invention also discloses an abnormal behavior detection system which comprises a videomonitoring module and a network model integration module. According to the method, various human body behaviors and a large amount of human body skeleton data can be accurately and efficiently processed, and abnormal behaviors appearing in video monitoring can be automatically identified.

The invention discloses a human skeleton key point detection method and device. The method comprises the following steps that step one, a monocular depth map is acquired; and step two, the monocular depth map is inputted to a trained full convolutional deep neural network so as to detect the human skeleton key point position, wherein the network feed-forward low abstract early feature map and thehigh abstract later feature map are integrated by the full convolutional deep neural network, and the small feature map is enlarged to other feature maps by using up-sampling so that global information including the small feature map and feature information including the large feature map are inputted in the next convolution computation. The feature information can be effectively utilized with combination of the early and later feature information and the global and local information so that the more abundant feature information can be outputted and the skeleton key point locating effect can be enhanced.

The invention discloses a human body posture recognition method and device based on skeleton key points, a storage medium and a terminal. The method comprises: acquiring video image frames in a videoimage sequence; inputting the video image frame into a preset skeleton detection model for detection; when a human skeleton is detected, extracting a skeleton key point set of each target person in the detection area; and inputting the skeleton key point set into a pre-trained posture judgment model to generate a posture recognition result. Therefore, by adopting the embodiment of the invention, the accuracy of target human body posture recognition can be improved.

The invention discloses a multi-modal action recognition method based on a depth neural network. The method comprehensively utilizes multi-modal information such as video images, optical flow diagramsand human skeleton. The specific steps are as follows: firstly, a series of preprocessing and compression are performed on the video; Obtaining an optical flow graph based on adjacent frames of the video; The human skeleton is obtained from the video frame by using the attitude estimation algorithm, and the path integral characteristics of the skeleton sequence are calculated. The obtained optical flow graph, skeleton path integration feature and original video image are input into a depth neural network with multi-branch structure to learn the abstract spatio-temporal representation of humanmotion and correctly judge its motion category. In addition, the pooling layer based on attention mechanism is connected to the video image branch, which enhances the abstract features closely related to the final motion classification results and reduces the irrelevant interference. The invention comprehensively utilizes multimodal information, and has the advantages of strong robustness and high recognition rate.

The invention discloses an unmanned aerial vehicle man-machine interaction method based on three-dimensional continuous gesture recognition. The method comprises the following steps: acquiring human skeleton tracking data through a Kinect sensor, wherein the human skeleton tracking data at least include skeleton point tracking data of a right hand, a left hand, a right elbow, a left elbow, a right shoulder and a left shoulder; extracting a gesture track feature and preprocessing the gesture track feature, wherein preprocessing includes gesture start-stop detection, smooth filtering processing, resampling and position normalization; performing gesture recognition by using a neural network algorithm; and converting a gesture recognition result into a corresponding control instruction for controlling flight of an unmanned aerial vehicle. Through adoption of the method, gestures can be recognized accurately, so that a user can control flight of the unmanned aerial vehicle more freely and conveniently.

The invention relates to a no-mark human body motion capture method; the method uses human surface three-dimensional voxel of human skeleton sleeve pattern tracing reconstruction, realizes right classification of voxel robustly and extracts articulation points automatically to get human motion parameter. The method comprises the following steps: (1) extracting three-dimensional voxel of human surface; (2) initializing human skeleton pattern and matching with a first frame voxel data; (3) using overall optimization algorithm to realize skeleton pattern tracing voxel data; (4) classifying the voxel based on overall classification distribution histogram of each voxel in tracing process; (5) extracting three-dimensional articulation points from classified voxels; and (6) getting articulation angle based on the coordinate of the articulation points and then getting human motion parameter. The invention has the advantages of easy implementation, relatively low cost, strong robustness and wide application and the like.

An automatic face tracing method on the basis of a Kinect, including the steps: (1) combing the Kinect with a programmable camera to form a tracing device and calibrating the tracing device; (2) acquiring data sequence of human skeleton and extracting skull point coordinates in the Kinect coordinate system; (3) acquiring a transformational matrix from a Kinect coordinate system to a camera coordinate system by utilizing external parameter of the camera and external parameter of the Kinect; (4) transforming the skull point coordinates acquired in the step (2) into the coordinate system of the camera by utilizing the transformational matrix acquired in the step (3), and calculating required rotating angle and zooming times of the camera in a horizontal and a perpendicular directions; and (5) driving the camera to correspondingly rotate and zoom according to the angle and times calculated in the step (4) to trace movements of a human face. The camera is driven to rotate and zoom by utilizing the continuously acquired skeleton data sequence, thus the human face can be traced automatically.

The invention provides a real-time human skeleton articulation point detection method and belongs to the field of image processing. The invention designs a hierarchical context attitude detection network, digital image processing and deep learning are adopted for realizing real-time detection on coordinates of skeleton articulation points of human bodies under the conditions of different attitudes, different illuminations and different scale dimensions, a real-time detection method is realized while precision is guaranteed, calculation amount of a model can be obviously reduced, and model training, deployment and usage efficiency is guaranteed.

The invention discloses a people recognition method and device based on video images. The people recognition method includes the steps of firstly, extracting N images from target video images, and determining a background image and a foreground area in the target video images, wherein the foreground area includes a body contour image; secondly, extracting a plurality of body contour characteristic points from the body contour image; thirdly, setting up a three-dimensional body model based on a human skeleton, wherein the three-dimensional body model includes a plurality of three-dimensional joint angle parameters; fourthly, conducting rectangular projection on the three-dimensional body model to obtain a body smooth curve; fifthly, matching the body contour characteristic points extracted from the images with the body smooth curve to determine all the three-dimensional joint angle parameters; sixthly, conducting dimensionality reduction on all the three-dimensional joint angle parameters to obtain gait data to be recognized; seventhly, matching the gait data to be recognized with well-trained gait data to complete people recognition. According to the technical scheme, the people recognition method and device have the advantages of improving the capacity for analyzing the body contour characteristic information, reducing the operational amount, being high in robustness, and the like.

The invention provides a material-engine-based automatic cartoon generating method. The method comprises that: a user uploads a query request; a server analyzes the semantics of the query request, and searches and integrates image materials related with the semantics of the query request to generate cartoons of multiple styles serving as query results, wherein the image materials comprise a role behavior-based virtual human skeleton model and a scene-based background material; and the user can regulate each image element in the query results. According to the method, a machine can intelligently perform semantic analysis on the search statements submitted by the user, search a theme and related material pictures most accordant with the user search requirement from an image database and then automatically generate a cartoon about the theme, the user can modify the style of the cartoon according to personal preference based on the cartoon, and finally a cartoon capable of expressing the idea of the user is obtained, so that interpersonal exchange becomes richer and more vivid.

The invention belongs to the field of computer vision and deep learning, particularly relates to a human skeleton behavior recognition method, system and device based on a graph convolutional neural network, which aims to solve the problem that the human skeleton behavior recognition result based on the graph convolutional neural network is low in precision. The method comprises the following steps of acquiring a skeleton video frame and normalizing the skeleton video frame; constructing a human joint natural connection graph corresponding to each frame of graph; learning the unnatural connection edge to obtain a human body joint connection diagram; allocating a weight value to each edge of the human body joint connection diagram; carrying out graph convolution operation to obtain the spatial information of the skeleton sequence; and carrying out convolution operation on the time dimension to obtain the behavior category of the skeleton sequence. According to the method, the natural connection edge can learn the basic human body behavior characteristics, the non-natural connection edge can learn the additional behavior characteristics, a graph is formed by the natural connection edge and the non-natural connection edge together, the human body motion information can be more fully represented, and the recognition performance is improved.

A three-dimensional human body motion trace method based on a multi-camera in the computer vision technical field has the following steps: firstly, tissue data points on the human body surface are picked up and outmost points are obtained through processing the tissue data; secondly, a standard three-dimensional skeleton model which is used for dynamic posture adjustment of the model during the trace process is established before skeleton pick-up and human body motion trace, thereby realizing fitting of the model and an original three-dimensional image; thirdly, a skeleton observation method is established and the skeleton model posture is adjusted according to the status that whether the number of the tissue points in each section of bone sleeve is maximal; fourthly, an implementation approach of optimal matching skeleton is established and the state that whether the current skeleton pose has met the trace requirements or not is judged through changing the space positions of root nodes and the angle of rotation of each boot section winding around the father node. The invention can quickly get the human body three-dimensional skeleton based on the existing human body tissue data, thereby realizing the human body motion trace.

The invention discloses a backpack-type walking power assisting device which comprises a supporting frame, wherein a back plate, straps, a backpack and a size-adjustable waistband are arranged on the supporting frame; a rotatable hip joint is mounted at the lower end of the supporting frame; a pair of lower limb exoskeletons are mounted on the hip joint; each lower limb exoskeleton comprises a thigh bone supporting mechanism, a leg bone supporting mechanism and a foot fixing mechanism; the leg bone supporting mechanism is elastically connected with the foot fixing mechanism; the thigh bone supporting mechanism comprises a thigh bone fixing plate and a first gravity balance mechanism; the leg bone supporting mechanism comprises a leg fixing plate and a second gravity balance mechanism; and the thigh bone fixing plate is elastically connected with the leg fixing plate. The backpack-type walking power assisting device has the advantages that the first gravity balance mechanism and the second gravity balance mechanism are used for balancing the lower limb gravity in a moving process of a human body in real time, thereby enabling a user to walk by following a movement trajectory of a human skeleton and reducing the physical output of the user; a pure mechanical structure design is adopted; the device cannot be influenced by an external environment; and the stability and reliability are high.

The invention discloses an uncalibrated human-computer interaction control system and method based on Kinect. The system comprises human skeleton information acquisition, a computer software system and a mechanical arm, wherein human depth image information acquisition is mainly accomplished by a Kinect sensor; the computer software system processes acquired field depth data by utilizing a skeleton tracking technology and establishes a 3D (three-dimensional) coordinate of 20 human skeleton points; and a control system of the mechanical arm acquires a control command sent by conversion of the computer system, and controls an end actuator to follow hand motion to achieve real-time guide of a hand to the end actuator of the mechanical arm. According to the system and the method, master-slave control is performed by constructing a motion mapping relation of the hand relative to a hipbone center and the end actuator relative to a base of the mechanical arm, so that real-time interaction of the hand and the mechanical arm is achieved. An experimental result indicates that the system can well accomplish hand tracking and master-slave control tasks, and has higher timeliness and interactivity.

The invention discloses multifunctional intelligent acupuncture and moxibustion diagnosis and treatment instrument and an application method thereof. The diagnosis and treatment instrument comprises an acupuncture point detection module, an acupuncture point positioning module and an acupuncture and moxibustion therapy module which can be used separately or as a whole, wherein the acupuncture point detection module is used for collecting information of body surface impedance, acoustic electricity, infrared temperature, luminescence intensity, biomagnetism and electromyogram; the acupuncture point positioning module is used for lively and directly displaying the acupuncture point positions on a human 3D (three-dimensional) model, and conducting objective and accurate positioning by combining position relation of human skeleton, muscle, vessel, nerve, lymph or viscera and acupuncture points, without influence by body figure difference of users; and the acupuncture and moxibustion therapy module is used for realizing multiple treatment of oscillation massaging, infrared thermal therapy, electromagnetic treatment, pulse current treatment and the like. The multifunctional intelligent acupuncture and moxibustion diagnosis and treatment instrument and the application method thereof have the advantages of precisely detecting all physical characteristics of the acupuncture points, providing complete and reliable diagnosis reference and basis for patients and medical staff, providing accurate and reliable positioning results, and adopting multiple acupuncture and moxibustion therapymeans so as to provide convenience to users.

The invention discloses a behavior recognition method for learning a human skeleton of a neural network based on an end-to-end space-time diagram. The method is used for behavior recognition of a human 3D skeleton. The method specifically comprises the following steps: obtaining a human body 3D skeleton key point position data set for training, and defining an algorithm target; performing clustering expression on each frame based on the spatial position to obtain a spatial node relation; calculating a time track of each joint point, and performing relation measurement according to the time track to obtain a time node relation; establishing a joint learning framework of the space-time diagram learning and the diagram convolutional neural network; and estimating the behavior category of thecontinuous human body 3D skeleton by using the learning framework. The method is suitable for human body action analysis in a real video, and has a good effect and robustness for various complex conditions.

The present invention relates to a method for implementing a human skeleton tracking system based on depth data, specifically applied to a human skeleton tracking system based on depth data which is composed of a data acquisition unit, a limb segmentation unit, a skeleton point unit, and a tracking display unit. The units are in a relationship of sequential invocation. The limb segmentation unit uses scene depth data obtained after processing by the data acquisition unit to perform limb segmentation. The skeleton point unit uses the result obtained after segmentation by the limb segmentation unit to compute specific positions of respective skeleton points of a limb. The tracking display unit uses the positions of the skeleton points computed by the skeleton point unit to establish a skeleton model of the human body and perform tracking display.

The invention discloses a rail transit abnormal person detection method based on action recognition, and belongs to the field of aviation monitoring. The method comprises: inspecting railways by usingan unmanned aerial vehicle, extracting frames of videos, training and using an SSD detection model, obtaining position information of each person in each video frame image, intercepting a local areacontaining the person, and a key point detection model and a Reset-are detected. The 18-clothes classification model is trained; predicting joint coordinates of each person by using the key point detection model, forming a human skeleton sequence by using the joint coordinates in a certain time period, inputting the human skeleton sequence into an LSTM action recognition model, and recognizing theaction category of each person; and performing clothing classification of the personnel through the Resnet-18 clothing classification model; and judging whether the person is a worker or not according to the action type of each person and the corresponding appearance clothes. The method solves the problem of high cost of traditional manual inspection or roadbed inspection, and has high practicability and robustness.

The invention discloses a method for compiling three-dimensional human skeleton motion based on motion capture data. The method comprises the following steps of: analyzing and judging a similarity of the states of connecting points of segments to be moved and judging whether a transition motion segment is to be added; after eliminating a relative position difference between the motion segments, linking a plurality of motion material segments into a new motion segment meeting the requirement; when jumps are generated due to the inconsistence of the beginning and the end motion gestures of the motion segments in the linking process, making the transition at the joints among the segments smooth and natural by using a transition function at jump positions; when a sliding phenomenon occurs in the motion due to the use of the transition function, breaking apart a fixed skeleton model hierarchical structure and rebuilding at the moment, and eliminating the sliding by using a reverse kinematic principle, wherein the newly built skeleton model hierarchical structure is also applied to adjustment of a motion orientation of a role model as required at the same time; and finally, carrying out a combined compiling on different types of motions so as to greatly expand richness and diversity of the generated new motion types.