203 results about "Motion recognition" patented technology

The invention discloses an emotion prediction and disease derivation method and system based on multi-modal fusion, and the system comprises a data collection and preprocessing module, an emotion fusion module, an abnormal condition detection and cloud uploading module, and a disease possibility derivation module. The data acquisition and preprocessing module comprises a video part, a text part and an audio part, and the video part comprises face emotion recognition and prediction and human motion recognition and prediction; the text part comprises text content emotion recognition and prediction; the audio part comprises voice-to-text and voice tone emotion recognition and prediction, the system comprehensively captures an emotion state by fusing multi-mode information such as video, text and voice, and the accuracy and prediction capability of emotion recognition are improved; and by predicting the future emotion trend, the abnormal condition is warned in advance, and the response timeliness is improved.

The invention discloses a motion recognition method and system based on a redox photoelectric memristor, a terminal and a storage medium, and the method comprises the steps: selecting classical motions based on a human body motion data set, extracting time sequence data, and coding the time sequence data into an optical pulse sequence; constructing a reservoir array composed of a plurality of photoelectric memristors, and expanding an optical pulse sequence signal into a high-dimensional state vector; constructing a supervised training model, solving a weight matrix, and constructing a memristive cross array; and outputting an action classification result through simulation domain operation based on the output current multi-path light current signals in combination with the memristor cross array. According to the method, the motion features can be directly fed into a rear-end classification network for action recognition without depending on a complex digital feature extraction algorithm, so that the transmission and processing overhead of redundant data is fundamentally eliminated; a high-efficiency, low-delay and high-robustness hardware solution is provided for real-time and anti-noise motion recognition in scenes such as intelligent monitoring and man-machine interaction.

The invention particularly relates to a multi-task motion recognition method based on a physical constraint guide condition diffusion model, which comprises the following steps: acquiring original observation data of multi-task motion based on an inertial measurement unit and preprocessing to obtain preprocessed original observation data; constructing a conditional diffusion model, and training the conditional diffusion model by using the preprocessed original observation data based on a preset loss function to obtain a trained conditional diffusion model; performing data enhancement on a key motion state category determined based on the motion state category label corresponding to the original observation data according to the trained conditional diffusion model to obtain a key motion state category sample, and constructing a sample balance data set based on the key motion state category sample; and based on the sample balance data set and a preset multi-task learning network loss function, constructing a multi-task learning pedestrian motion recognition model and carrying out multi-task recognition. Therefore, the problems of few key state samples, unreasonable data and the like in motion recognition are solved.

The invention discloses an action recognition method based on a virtual inertial measurement signal generation model, and relates to the technical field of action recognition, and the method comprises the steps: collecting a surface electromyogram signal and an inertial measurement signal, and carrying out the preprocessing of the collected signals; constructing and training a generator to convert the surface electromyogram signals into virtual inertial measurement signals; inputting the generated virtual inertial measurement signal and the original surface electromyogram signal into an action recognition model, and training to obtain a classification module; the performance of an action recognition model is evaluated by using a test data set, the accuracy rate, the recall rate and the F1 score index are calculated, the recognition effect of the model is measured, a classification model and a generator are optimized according to the recognition effect, and the advantages of two modal signals can be fully utilized by fusing surface electromyogram signals and virtual inertial measurement signals, so that the accuracy of the action recognition model is improved. And the motion information of the fingers, the wrist, the forearm and other parts is analyzed, so that the complex limb motion is identified more accurately, and the performance of the limb motion identification system in practical application is improved.

The invention belongs to the technical field of sensor measurement and recognition, and particularly relates to a human body motion recognition system based on LSTM (Long Short Term Memory), which comprises a data acquisition module, a data calculation module and a data application module, and utilizes a neural network model and a wearable electronic sensor to detect a human body walking state. A new long short term memory (LSTM) recurrent neural network model, namely an LSTM-STRM model, is established, the model combines multi-task learning, an attention mechanism and spatio-temporal feature fusion to accurately classify the walking state of the human body, and the walking state is compared with the original LSTM model. The result shows that the LSTM-STRM model can be used for classifying the time sequence data collected by the measuring unit, the states of the five targets can be classified with high precision, and the recognition accuracy is higher than that of an original LSTM model. The method improves the recognition precision, is high in adaptability, is suitable for the fields of medical treatment, human-computer interaction, exercise training and the like, and has a wide application prospect.

The invention relates to the field of computer vision, artificial intelligence and intelligent fitness, and particularly discloses a fitness action recognition, counting and quality evaluation method based on machine vision, which comprises the following steps of: extracting video frames and standardizing the video frames, realizing background suppression and human body region enhancement through a semantic segmentation or inter-frame difference method, and outputting a standardized image sequence; detecting key joint points by adopting a pre-training model, and outputting a stable skeleton sequence and candidate action stage data through time sequence consistency filtering; reconstructing a feature tensor, fusing spatio-temporal features through double-branch attention collaboration, and outputting action categories and time sequence compensation parameters in a classified manner; a dynamic threshold method accumulates the number of actions, action qualification is judged in combination with biomechanical constraints, the confidence coefficient is optimized, and a structured result is output; bone rendering, error highlighting, voice generation and personalized training suggestions. According to the method, wearable equipment is not needed, the problems of instable identification, miscounting and the like in a complex scene are solved, and real-time accurate analysis is realized.

The invention provides an action recognition method based on adaptive skeleton grouping and direction sensitive space-time modeling, and relates to the technical field of skeleton action recognition. Comprising the steps of skeleton action sequence input and feature embedding, adaptive skeleton grouping and direction weighting space-time modeling, trunk modeling and feature refinement, adaptive time down-sampling, multi-stream feature fusion and classification output and action recognition loss evaluation. The method comprises the following steps: acquiring an introduction result through skeleton action sequence input and feature embedding, acquiring an adjustment result through adaptive skeleton grouping and direction weighted space-time modeling, acquiring a processing result through trunk modeling and feature refinement, acquiring a reconstruction result through adaptive time downsampling, performing multi-stream feature fusion and classified output, and finally executing action recognition loss evaluation. According to the method, the skeleton action recognition precision is improved, and meanwhile, the complexity of long sequence modeling calculation is reduced, so that the skeleton action recognition real-time performance and deployment efficiency are improved, and the problem that the skeleton action recognition precision is not high in the prior art is solved.

The invention discloses a limited space human body motion recognition method based on multi-scale spatial-temporal feature fusion, and the method comprises the steps: firstly collecting motion data when a worker carries out the operation motion during the operation of the worker in a limited space, and building a motion data set; secondly, all action data sets are preprocessed, and actions are subjected to label numbering; and finally, inputting the data in the preprocessed data set into a multi-scale spatial-temporal feature fusion model, carrying out limited space personnel operation action recognition, and outputting a limited space action type label. According to the method, the aggregation connection relation between IMU sensors can be more completely described, the irregular action relation of the spatial dimension of each part of a human body is fully expressed, and the problems of low identification accuracy and low generalization performance of six-axis IMU operation action identification in a limited space in the prior art are solved.

The invention relates to the technical field of railway maintenance education, in particular to a high-speed railway four-electricity system intelligent teaching system and method based on AI, and the method comprises the steps: a teaching data obtaining module collects teaching process data, student learning tracks and industry fault data; the virtual simulation modeling module is fused with a BIM model and a technical specification text to construct a four-electric system twinborn body; the AI intelligent analysis engine constructs student ability portraits through a machine learning algorithm, generates a personalized learning path and intelligently answers questions; the virtual-real teaching interaction module builds a digital-intelligent practical training scene, carries out three-dimensional visual error correction and remote guidance through real-time motion recognition, and outputs practical training data. The cross-professional fault simulation module carries out cross-professional fault linkage simulation deduction through an association rule mining algorithm and outputs a deduction result; and the teaching effect evaluation module establishes a binary evaluation system combining process and practical operation skill assessment, and outputs teaching effect data. Therefore, the problems of fixed teaching strategy, low precision and the like in the prior art are solved.

The application discloses a non-invasive brain-computer interface rehabilitation robot and relates to the technical field of intelligent rehabilitation equipment, and solves the technical problem that the existing rehabilitation robot mainly adopts a set program to perform repetitive rehabilitation training, and patients are not actively involved, the passive training mode limits the autonomous control and participation of the patients, and the rehabilitation effect is limited, especially in the aspect of neural injury repair, and the effect is poor; the application obtains motion data of the patient; an artificial intelligence model is trained based on historical motion data to obtain a motion recognition model; the motion data is recognized based on the motion recognition model to obtain a recognition result; the patient is subjected to rehabilitation training through the rehabilitation robot based on the recognition result; a rehabilitation effect evaluation coefficient of the patient is calculated based on the electromyographic characteristic data; and the recovery progress of the patient is judged based on the rehabilitation effect evaluation coefficient and a preset rehabilitation effect evaluation threshold value, so that the above technical problem is solved.

Disclosed herein is an article of smart clothing which automatically recognizes body configuration and motion. This smart clothing includes inertial motion units which are distal relative to selected joints and also sets of strain sensors which span those joints. The type of energy transmitted through a strain sensor can be electrical energy or light energy. Combined multivariate analysis of data from both inertial motion units and strain sensors provides more accurate recognition of body configuration and motion than data from either alone.

This application discloses a method, device, storage medium, and program product for rowing motion recognition based on an adaptive multi-scale peak algorithm, belonging to the field of computer technology. The method includes: periodically acquiring first acceleration data in a target direction; for each acquired first acceleration data point, performing peak and trough detection on the first acceleration data set within a preset time window to obtain a peak position set and a trough position set; and performing rowing motion recognition based on the peak and trough position sets to obtain one or more rowing motion information. This application uses only the first acceleration data in the target direction, avoiding interference from acceleration data in other directions, thus improving the accuracy of peak and trough detection. Furthermore, both the peak and trough position sets can reflect the rowing motion pattern; using bidirectional temporal constraints to recognize rowing motions improves the accuracy of rowing motion recognition, thereby improving the accuracy of rowing motion counting.

The invention relates to an action recognition system for online education, and the system comprises a real-time snapshot device which is disposed at a client of remote education and is used for carrying out the real-time snapshot processing of an environment where a remote education user is located, so as to obtain and output a corresponding snapshot processing image; and the contact notification mechanism is used for executing on-site broadcasting of notification information corresponding to small action recognition when the contact between the head and the hand is intelligently recognized based on various image processing data by adopting the multiple trained Hough neural network. According to the invention, the Hough neural network after multiple times of training can be introduced to intelligently identify whether the head and the hand are in contact based on various image processing data, and when the head and the hand are intelligently identified to be in contact, on-site broadcasting of notification information corresponding to small action identification is executed. Therefore, intelligent detection and warning of illegal small actions of remote education customers are realized.

The invention relates to an action recognition method and system based on video decoupling, and the method comprises the steps: constructing a visual feature extraction network, a semantic feature extraction network and a nonlinear similarity measurement learning module, and carrying out the connection and integration to form a zero-sample action recognition model; constructing a category name query library according to the training data, inputting the training data into a model for model training and hyper-parameter adjustment, and fixing model parameters after training; updating a category name query library according to the test data, and inputting the test set data into the model to obtain a corresponding test recognition result; and judging whether the accuracy rate of the test identification result is greater than or equal to a preset value, if so, updating the category name query library again according to the actual demand and inputting the actual data set into the model for identification, otherwise, retraining the model. Compared with the prior art, the method has the advantages that video decoupling and nonlinear similarity measurement learning are used, the discrimination of visual features can be enhanced, and the visual-semantic cross-modal correlativity is captured.

This invention relates to a skeletal action recognition method based on spatiotemporal topology learning, belonging to the field of computer vision and artificial intelligence technology. The method includes: constructing a two-dimensional topology coding module to simultaneously capture the static and dynamic topological relationships of the skeletal structure; employing a multi-level spatial attention aggregation module to adaptively weight and aggregate skeletal features at different levels to enhance the expressive power of key nodes and edges; and designing a temporal dynamic sequence pooling method to extract high-order dynamic information from time-series data based on a dynamic modality decomposition strategy, thereby improving the accuracy of action recognition. The advantages are: this method can fully utilize the spatiotemporal structural information of the skeleton data to achieve accurate recognition of human actions, while improving the modeling ability for complex dynamic behaviors, avoiding the limitations of traditional methods in capturing high-order dynamic information.

The present disclosure provides a motion recognition method and device and electronic equipment, and relates to the technical field of interaction. The technical problem of low accuracy of user motion recognition in somatosensory interaction is solved. The method comprises: in response to the operation of the somatosensory interaction device, acquiring the motion signal collected by the somatosensory interaction device; separating the motion attribute features in the motion signal and sample attribute features by means of knowledge distillation to obtain the motion attribute features corresponding to the motion signal; wherein the sample attribute features are used to represent the self attribute features of the user; and performing motion recognition by a classification neural network model according to the motion attribute features to obtain the motion recognition result of the user.

This invention discloses a fingertip tactile sensor and its sensing method capable of motion recognition and three-dimensional force measurement. The sensor comprises, from top to bottom, a stacked sensing electrode layer, a pressure-sensitive layer, and a grounding layer. The sensing electrode layer consists of four... x - y The device consists of four symmetrically distributed sensing electrodes arranged in pairs along a central axis. A common electrode forms the grounding layer, with its lower surface attached to the fingertips of the intelligent robotic arm. In the non-contact state, the four sensing electrodes are activated simultaneously or sequentially, forming three asymmetrical sensing units with the common electrode. This asymmetrical design effectively enables the recognition of robotic arm movements. In the contact state, the four sensing electrodes are activated sequentially, forming four sensing units with the common electrode. Three-dimensional pressure-shear force measurement is achieved by calculating the difference between two sensing units in the same measurement direction. This invention is used for non-contact movement recognition and three-dimensional force measurement after contact with an object during robotic arm operation, improving operational flexibility and accuracy.

Embodiments of the innovation relate to a method for generating a labeled object data set. The method comprises receiving a task performance video, playing the task performance video in reverse, and for each video frame of the task performance video, applying a mask to images of the objects within the object stream. The method further comprises identifying an object entering a first video frame of the task performance video along a direction perpendicular to a direction of the object stream, in response to detecting motion of the identified object from the first video frame of the task performance video to a second video frame of the task performance video along the perpendicular direction, designating the object as an object of interest, and storing mask segmentation data associated with the mask of the object of interest as part of the labeled object data set.

We provide a system that enables more natural and accurate speech translation. [Solution] The system includes means for receiving the user's voice and acquiring audio data, means for providing speech recognition technology that analyzes the audio data and converts it into text data, means for motion recognition technology that captures the user's mouth movements and generates motion data, means for transmitting the text data and motion data to a server, means for the server to translate the text data into different languages ​​and convert the text in the different languages ​​into audio data, and means for transmitting the audio data to the user's terminal and playing it back.

The application belongs to biological signal recognition and data processing technology, and is a multi-sensor fusion motion recognition system for shoulder rehabilitation evaluation. The system comprises a flexible strain sensor, an inertial measurement unit, a multi-channel data acquisition module, a data preprocessing module and a motion recognition module. The flexible strain sensor comprises a plurality of sensing areas and connecting areas distributed around the rotator cuff area. The multi-channel data acquisition module acquires multi-channel sensing signals, which are preprocessed by the data preprocessing module. The motion recognition module adopts a multi-modal feature fusion algorithm based on bidirectional cross-modal interaction attention and time period-specific adaptive weight mechanism to realize dynamic correlation modeling between strain sensing signals and inertial measurement data in a unified time sequence space, fuse cross-modal time sequence features, capture global and local dependency of shoulder movement, and recognize multi-class rehabilitation actions. The application effectively overcomes the static limitation of the prior art and significantly improves the accuracy and robustness of shoulder rehabilitation evaluation.

The invention discloses a flexible piezoresistive strain sensor and a preparation method thereof, and an action recognition method and system, the flexible piezoresistive strain sensor takes a flexible polymer material as a matrix, and a plurality of conductive fillers are compositely arranged in the matrix, so that the conductive fillers form a continuous composite conductive network structure in a dispersion manner; therefore, stable resistance change is generated under the action of external strain. Based on human body joint strain signals collected by the sensors, resistance signals are preprocessed, and a multi-layer perceptron neural network model is constructed, so that human body actions of different joints and different bending angles are classified and recognized. The structure stability of the flexible piezoresistive strain sensor and the realizability of action recognition are both considered, and the method is suitable for application scenes such as human motion monitoring, rehabilitation evaluation and human-computer interaction.

The embodiment of the application relates to the technical field of human-computer interaction, and discloses a joint data feedback method and device based on a flexible sensor, a medium and a product. The method comprises the following steps: determining a timing calibration feature set according to a multi-source synchronization signal of a flexible sensor array; determining a joint function evaluation result and a motion classification result according to the timing calibration feature set; determining joint dynamic function deviation data according to a deviation between the motion classification result and a preset biomechanics standard library in combination with the joint function evaluation result; and determining a biomechanics feedback instruction of a wearable device according to the joint dynamic function deviation data; wherein the biomechanics feedback instruction is adapted to a function state corresponding to the joint function evaluation result, and can at least be used to solve the technical problems that joint function and motion recognition are inaccurate and precise personalized control is difficult to achieve in related technologies.

The invention relates to the technical field of physical training evaluation, in particular to a physical training evaluation method and system based on motion recognition, and the method comprises the steps: positioning a motion reversing key moment and an image frame according to knee-shoulder angular velocity reversal, constructing a shoulder-knee connection path, and extracting a pixel length to form a time sequence table; non-smooth mutation is monitored, a standard trend is compared to generate an action offset list, a rhythm fluctuation time period is identified based on key frame interval change, offset and fluctuation information is analyzed in a cross mode, and a training action identification evaluation result is obtained according to distribution characteristics of overlapped interval parts. According to the method, action conversion is recognized through angular velocity conversion, a shoulder-knee track is constructed to extract extension length, offset is judged based on sudden change and combined with rhythm trend, concentrated features of overlapped interval parts are analyzed in a cross mode, synchronous offset and rhythm interference are accurately extracted, action continuity and stability discrimination capability is improved, and key state recognition resolution is enhanced. And fine tracking and effective early warning of the complex action flow are realized.

The invention is suitable for the technical field of crossing of computer vision, artificial intelligence and sports science, and provides a tennis posture evaluation system based on multi-modal data fusion, which comprises a three-dimensional posture extraction module, an action recognition module, an index calculation module and a natural language evaluation generation module, the three-dimensional posture extraction module is used for extracting a human body three-dimensional key point sequence from a monocular video according to an STCFormer model; the action recognition module is used for performing standardization processing, Bi-LSTM network processing and full-connection classification network processing on the human body three-dimensional key point sequence to obtain tennis action types; the index calculation module is used for calculating biomechanical parameters according to the action type and the human body three-dimensional key point sequence; and the natural language evaluation generation module is used for inputting the action type and the biomechanical parameters into a preset large language model to generate feedback information in a natural language form. Therefore, end-to-end automatic processing from original video input to final professional evaluation report generation is realized, and objectivity and accuracy of evaluation results are improved.

Provided is an input system enabling direct manual input to a displayed video from a spaced-apart position.　This input system comprises: a display device; a 3D camera that captures a user facing the display device to look at a display screen; and an information processing device connected to the display device and the 3D camera. The information processing device outputs a video signal to the display device in order to display a video, detects a viewpoint and a position of the hand of a user looking at the display screen from a video of the 3D camera, identifies a position on the display screen that is an extension of a straight line connecting the viewpoint and the position of the hand of the user, as an operation position, and recognizes the operation position and the movement of the hand of the user as an input to the information processing device.

The application provides a motion recognition method and device, which can recognize motion information and optical flow information of a target object in an image based on the image, and determine the motion of the target object according to the motion information and the optical flow information, has high accuracy when recognizing the standing and sitting motions of students, reduces the error switching of the shooting mode caused by the false detection of the recording and broadcasting equipment, and thus can improve the use effect of the recording and broadcasting equipment and the viewing experience of the recorded video data.

The present application relates to a kind of power transmission engineering smoke hidden danger identification method, device and storage medium.In the present application, the output feature of the motion recognition of the motion recognition network of the DBG video action recognition network is cascaded with the output optical flow feature of the global matching optical flow network of GMFlow after operation, and then input into the first Transform for deep feature fusion;In the first Transform, the feature map after target feature extraction is converted into input-output sequence, and then the multiple self-attention layers are optimized to calculate the multiple attention outputs linearly connected to the desired dimension;Obtain the hidden danger data containing smoke hidden danger in power transmission engineering, train the recognition network architecture by hidden danger data to obtain parameters, and finally obtain the recognition model for power transmission engineering smoke hidden danger.The present application detects smoke by combining spatial features and time sequence features, greatly reduces the frequency of smoke false alarm and improves the accuracy of prediction.

The invention discloses a personnel positioning method based on motion state constraint. The method comprises the following steps: 1, signal acquisition; 2, data preprocessing; 3, motion state recognition and classification; 4, step number detection; 5, step length estimation; 6, estimating a course angle; and 7, outputting position information. According to the invention, personnel positioning based on motion state constraint is realized, the classification result of human body motion identification is used as a constraint condition, the personnel positioning precision is improved, and the actual application requirement of personnel positioning in a complex environment can be met.

Embodiments of the present application relate to the technical field of video recognition, and disclose a motion counting method and device, equipment and a storage medium to solve the technical problems of poor robustness and inaccurate counting of existing motion counting. In the present application, motion counting includes: using a video frame motion recognition model obtained by pre-training to recognize a video to be counted to obtain a Gaussian regression output sequence; performing Gaussian modeling according to the Gaussian regression output sequence to obtain a Gaussian model; and performing motion counting according to the number of Gaussian distributions in the Gaussian model.

The application discloses a motion classification method for a dynamic vision sensor and relates to the field of motion classification. The application first adopts an event index plane, considers the space-time information in the cross neighborhood of each event in an event stream, calculates the motion gradient direction of each event as the local motion feature of each event in the event stream, then does pooling and pulse coding in the space-time dimension, and finally inputs the pulse sequence into a pulse neural network to output the classification result of the motion in the scene. The application introduces the event index plane with speed invariance to record the global motion history information of the motion, introduces the motion history information and the gradient direction calculation into the processing of the event stream, and proposes a novel motion gradient direction feature expression method based on events, which can efficiently extract the motion information of the motion and improve the motion recognition accuracy. In addition, compared with the optical flow motion feature expression, the proposed feature expression method avoids the complicated optical flow estimation process and saves the calculation energy consumption.