92 results about "Movement recognition" patented technology

The invention belongs to the technical field of computer application, and relates to a limb rehabilitation action recognition and evaluation method based on deep learning, and the method comprises the steps: collecting video data and skeleton data of limb function rehabilitation actions, carrying out the preprocessing, and constructing a training set and a verification set of the video data and the skeleton data; a hybrid model of SE-ResBlock3D and LSTM is constructed, and recognition and classification of limb function rehabilitation actions are achieved on input video data through an execution convolution layer, four residual block sequences and an LSTM module in sequence by the hybrid model; and a deep learning network SGP-Net is constructed, and the deep learning network SGP-Net extracts and evaluates space and time sequence characteristics of the limb function rehabilitation actions by executing an STGCN module, a GAT module and a PMTC module on the input preprocessed skeleton data in sequence, so that quality evaluation of the limb function rehabilitation actions is realized.

The invention relates to a simulation digital human real-time intelligent voice interaction system and a simulation digital human real-time intelligent voice interaction method based on vision and a large model, and aims to solve the problems of inaccurate target speaker recognition, high response delay and the like in digital human voice interaction in a complex scene. The system circles an effective recognition range through a camera, triggers audio collection in combination with face detection, locks a target speaker and reduces noise by using lip movement recognition and sound image fusion technologies, converts the target speaker into a text through voice wake-up, generates an answer by means of a large language model (LLM) and knowledge retrieval enhancement (RAG) technologies, generates low-delay voice through a voice synthesis technology accelerated by the vLLM, and performs voice recognition on the target speaker. And driving the preloaded digital human image to synthesize a video stream and pushing the video stream to a front end for rendering in real time. Accurate pickup, low-delay interaction and rapid digital human image switching in a complex environment are realized, the accuracy and real-time performance of intelligent voice question answering are improved, and the method is suitable for government affair halls, exhibition halls and other scenes.

The invention discloses a sign language recognition method and device based on multi-modal deep learning, and the method comprises the steps: multi-modal data input: capturing hand motions, gesture tracks and facial expressions at the same time through a camera, a motion capture sensor and other devices, and forming multi-modal data input; sign language action recognition: precise recognition of sign language actions is realized through a combined model of a deep convolutional neural network and a long-short-term memory network; facial expression and gesture track combined recognition: realizing understanding and translation of complex sign language sentences by combining the captured facial expressions and gesture tracks; and context natural language processing: generating a target statement in combination with context semantic understanding, and outputting a translation result. Through hand motion capture, facial expression analysis, gesture trajectory tracking and context natural language processing, complex sign language motions can be recognized more accurately and translated into characters or voices in real time, and low delay and high accuracy are achieved.

The invention discloses a dance movement recognition method, device and equipment based on dynamic time warping and a computer readable storage medium. The method comprises the steps of obtaining a user skeleton point sequence corresponding to a user dance movement and a standard skeleton point sequence corresponding to a standard dance movement; for each pair of frames in the user skeleton point sequence and the standard skeleton point sequence, multi-dimensional differences including joint point position differences, angle differences and motion amplitude differences are calculated; a double-layer dynamic weighting mechanism is applied to perform weighted fusion on the multi-dimensional difference values, and local cost between two frames is calculated; constructing a cost matrix based on local cost, and determining an optimal regular path and a dance motion similarity score by applying a path constraint dynamic time warping algorithm; and on the basis of the dance motion similarity score and the optimal regular path, generating an identification report including an overall score, a subitem score and visual correction information. The method has the advantages of being high in dance movement recognition precision, high in specialty and the like.

The invention discloses a deep learning-based human behavior recognition method and recognition system, and the method is characterized in that the method comprises the following steps: S1, data collection: collecting video data containing a plurality of human behaviors through a high-definition camera or a video database, and covering different scenes, illumination conditions and human postures; s2, data preprocessing: firstly extracting a three-dimensional coordinate sequence of human skeleton key points by using a Medape pre-training model, and then performing mean filtering and normalization preprocessing on the collected data to improve the generalization ability of the model; according to the method, the advantages of the DCN and the LSTM are combined, the improved double-flow convolution model is added with the space-time soft attention mechanism, the problems that space-time feature extraction is insufficient and feature design is complex in human body action recognition are effectively solved, the lightweight degree of the model is remarkably improved, and the human body action recognition accuracy is improved. And a new method is provided for research and application of human behavior recognition.

The invention relates to the technical field of health management, in particular to a risk assessment method and device for a stroke patient, equipment and a medium, and the method comprises the steps: obtaining a video image and audio data of the stroke patient, the video image comprises a face reaction image made by the stroke patient based on the first guide instruction and a limb reaction image made by the stroke patient based on the second guide instruction, and the audio data is a reply made by the stroke patient based on the third guide instruction; determining a facial paralysis recognition result and an eye response recognition result based on the facial response image; determining a limb motion recognition result based on the limb reaction image; based on the audio data, determining a language pronunciation recognition result; according to the method, the risk assessment level of the stroke patient is determined based on the facial paralysis recognition result, the eye response recognition result, the limb movement recognition result and the language composition recognition result, and the risk of the stroke patient can be accurately and quickly assessed without considering medical environment conditions.

The invention belongs to the technical field of anti-unmanned aerial vehicles, and discloses an unmanned aerial vehicle capturing system based on radar search, which comprises a radar echo analysis unit, a phased array radar array is deployed to scan a target airspace in real time, radar echo signals are acquired, target detection sensitivity is adjusted in real time through a nonparametric dynamic threshold value method, and the target detection sensitivity is acquired. Target echoes and natural clutters are distinguished, frequency drift and waveform deformation of radar echo signals are analyzed, and a target dynamic trajectory sequence is output; the target motion recognition unit is used for receiving the target dynamic trajectory sequence, performing recognition analysis on a flight mode of the target based on a rule-driven trajectory fitting method, judging whether the target accords with preset unmanned aerial vehicle flight characteristics or not, and generating an unmanned aerial vehicle recognition flag bit if the target accords with the preset unmanned aerial vehicle flight characteristics; the sensing precision, the recognition reliability, the interception efficiency and the combat safety of the unmanned aerial vehicle target in a complex environment are improved.

The invention discloses a seat pre-adjustment control method based on embedded CNN waist-hip trajectory dynamic tracking, and the method can achieve the precise prediction of the motion intentions of people with different heights through the construction of a height proportion change curve, effectively eliminates the motion recognition error caused by the height and body type difference of different individuals, and improves the accuracy of the motion recognition. The method enhances the refinement of seat control, and reflects the change of the action stage of the target person by setting the track slope, thereby recognizing the transition of the target person from sitting down to stable sitting posture and from sitting posture to getting up in different action stages, predicting the next trend of the action in advance, effectively improving the prediction accuracy of the action intention, and improving the user experience. The seat system can make a response when the action starts, and the situation that the comfort is affected due to delayed adjustment is avoided.

The invention relates to the technical field of dance training, and discloses a dance motion capture and real-time feedback control system which comprises a motion capture module, a motion analysis module, a real-time feedback control module and a motion execution module. Capturing dancing actions and physiological parameters of the dancer in real time through an action capturing technology to form a dancing action data set; training the dance movement recognition model and the movement evaluation model by using a deep learning algorithm to realize accurate recognition and multi-dimensional evaluation of the dance movement; constructing a feedback control model in combination with a reinforcement learning algorithm, and dynamically generating and adjusting a feedback control instruction according to an evaluation result; and finally, real-time correction and guidance of the dance movement are realized through the movement execution module. According to the method, timely and objective feedback can be provided for the dancer, the dancer is helped to adjust and optimize dance actions, the training efficiency and effect are improved, and the training consistency is ensured.

The invention relates to the technical field related to robots, in particular to a design method and device for a robot with human characters and capable of achieving self thinking. The method comprises the following steps: acquiring a five-recognition information matrix; wherein the five-recognition information matrix comprises image recognition information, voice recognition information, taste recognition information, smell recognition information and body touch and limb movement recognition information; the five-recognition information matrix is a partial matrix in the state matrix; determining a stimulation matrix based on the change of the state matrix over time and a predetermined character matrix; wherein the character matrix is used for representing characters of the robot; wherein the stimulation matrix is used for representing the change of the state matrix, and stimulation is obtained under the influence of the character matrix; adjusting a state matrix in combination with the stimulation matrix, the character matrix and a preset memory warehouse; the state matrix is used for representing the current state of the robot; based on the adjusted state matrix, behaviors needing to be carried out by the robot are determined, and a behavior matrix is obtained; and adjusting the character matrix in combination with the state matrix and the stimulation matrix.

Systems and methods described herein facilitate the tracking of events relating to property. For example, in certain embodiments, a system includes a property event detection device (e.g., smart home device, sensor device, and so forth) configured to detect activity (e.g., motion, light, sound, and so forth) proximate the property. The system also includes a property event tracking system configured to receive data (e.g., images, videos, facial recognition, movement recognition, object tracking, sound signatures, wireless data streams, and so forth) relating to the activity from the property event detection device, to determine whether the activity relates to a property event (e.g., home service, and so forth) for the property, and to store data relating to the property event in a distributed ledger (e.g., blockchain network) upon determination that the activity relates to the property event for the property.

The invention discloses a boxing scene-oriented data refinement and boxing action recognition method and system, and belongs to the technical field of data mining. Comprising the following steps: collecting multi-skeleton point time sequence data of a boxer; performing anomaly and deletion detection on the time sequence data; processing the detected abnormal and missing time sequence data; and constructing a boxing action recognition model based on the LSTM and the TCN network, and inputting the processed time sequence data into the boxing action recognition model to realize a boxing action recognition task. According to the method, the fuzzy C-means clustering algorithm and the projection approximate point algorithm are combined for use, motion data approximate to real human body skeletons are reconstructed, motion information of multiple skeleton points of the whole human body skeleton is comprehensively analyzed, accurate recognition and classification of boxing actions are achieved, and the accuracy of action recognition is improved.

The invention discloses an automatic classroom director method and electronic equipment. Audio data and video data of a current classroom scene are acquired; based on the audio data, sound source direction positioning is carried out through a microphone array, and the current sound source direction is determined; face key points are extracted according to the video data, lip movement recognition is carried out according to the face key points, and a lip movement recognition result is obtained; extracting human body key points according to the video data, and performing action recognition according to the human body key points to obtain a target action recognition result; based on the sound source direction, the lip movement recognition result and the target action recognition result, a current shooting picture of the camera device is controlled, and the current shooting picture of the camera device is a director picture; and outputting and displaying the director picture. According to the application, audio and video multi-mode information is fused, high-precision identification and natural and accurate automatic picture switching of the speaker and the interaction object in the classroom scene are realized, and the automation level of director and the overall classroom recording and broadcasting effect are improved.

The invention discloses a personnel state analysis method and system based on limb movement recognition, relates to the technical field of limb movement recognition, and determines the movement state of a corresponding limb part based on recognition of each movement-expression combination. And the driving response state of the personnel is determined based on the action state of each limb part, the corresponding part priority and the driving state of the truck, so that the accuracy of the driving response state of the personnel is improved. Therefore, the change event of the facial expressions is determined according to the plurality of facial expressions at different time, and the driving fatigue state of the personnel is determined according to the change event of the facial expressions and the lane changing frequency of the truck; according to the method, the voice interaction event of the person in the driving process is collected, the multiple state key contents are determined according to recognition of the voice interaction event, the state analysis system of the person is determined according to the multiple state key contents, the driving response state of the person and the driving fatigue state, and the accuracy of the state analysis system of the person is improved.

The invention relates to a voice interaction method and system based on lip movement and voice fusion recognition and a garbage truck, and the method comprises the following steps: collecting a high-definition lip movement image, and carrying out the preprocessing and lip region positioning of the lip movement image, and obtaining a lip image sequence; the method comprises the following steps: acquiring a voice signal, and carrying out noise reduction processing on the voice signal to obtain a voice signal after noise reduction; extracting lip movement features of the lip image sequence, and extracting voice features of the voice signal after noise reduction; respectively recognizing the lip movement features and the voice features to obtain a lip movement recognition result and a voice recognition result; the lip movement recognition result and the voice recognition result are fused, and a final operation instruction is generated; and executing corresponding operation based on the operation instruction. According to the method, the recognition accuracy in a high-noise environment can be remarkably improved.

The invention provides a neonatal limb movement recognition method based on double-branch multi-scale feature fusion, and the method comprises the steps: building a neonatal limb movement video sample set through collecting neonatal videos in different limb movement states; the method comprises the following steps: constructing a newborn limb movement recognition model based on double-branch multi-scale feature fusion, wherein the model comprises a first branch feature extraction network, a second branch feature extraction network, a feature fusion module and a classifier; obtaining a newborn limb movement recognition model; performing action recognition on a newly input test video by using the obtained newborn limb action recognition model; according to the method, action features are extracted from videos with different frame rates by using double branches, the ability of capturing subtle action changes is improved, key features of limb actions are focused by using a multi-scale convolution attention mechanism, and the accuracy of newborn limb action recognition is effectively improved.

This invention discloses a Tai Chi movement recognition method based on multi-rate compressive convolution. First, electromyographic (EMG) data of Tai Chi movements is collected and preprocessed. Then, temporal features of the source signals are extracted to construct a feature matrix. A multi-rate compressive convolution algorithm is used to extract cross-channel compressed feature sequences, which are then fused to obtain a multi-dimensional fused feature matrix. Temporal relationship features are then obtained through a long short-term memory (LSTM) network. Finally, a fully connected layer is used to obtain the movement recognition result, thus completing the Tai Chi movement recognition. This invention achieves multi-scale cross-channel feature extraction of EMG signals through multi-rate dilated convolution, overcoming the limitation of ordinary convolution which can only extract spatial relationships between adjacent channels. It can compress the information contained in EMG signal sequences of arbitrary sizes into a one-dimensional compressed feature sequence to extract highly fused features, reducing data redundancy, the number of parameters, and model computation, thereby improving the accuracy of Tai Chi movement recognition.

The invention provides a backpack multi-sensor data fusion-based motion attitude anomaly real-time detection method, which comprises the following steps of: acquiring multi-channel original data through a backpack-type integrated triaxial accelerometer, a gyroscope, a magnetometer and a barometer, implementing synchronous sampling and time-space alignment, and constructing a standardized time sequence data stream through wavelet denoising and multi-dimensional normalization preprocessing; high-dimensional features representing motion differences are extracted, nonlinear dimensionality reduction is achieved through principal component and Laplacian feature mapping, and a motion mode prototype library is generated; according to the method, a new motion situation can be continuously and adaptively learned, and the motion recognition accuracy, the system robustness and the attitude anomaly detection capability in a complex scene are effectively improved.

Aspects relate to a virtual reality management technique for facilitating precise long-range and short-range movement in a virtual environment while enabling complex multi-task actions. The virtual reality management technique includes determining, by analyzing the set of video data using a movement recognition model, a short-range movement action for an avatar in the virtual reality environment in a case that a set of movement factors detected for both a first arm and a second arm of the user satisfy a predetermined movement threshold and executing the short-range movement action, determining, by analyzing the set of video data using the movement recognition model, a long-range movement action for the avatar in the virtual reality environment in a case that a first hand of the user corresponds to a pointing gesture and a confirmation action is received from the user, and executing the long-range movement action.

The invention provides a limb movement equipment recognition method and system based on artificial intelligence, and relates to the technical field of data processing, and the method comprises the steps: obtaining a to-be-recognized angle group sequence JX and a to-be-recognized reference movement identification sequence DX corresponding to a to-be-recognized target in a target time window; obtaining a first feature list and a second feature list according to the JX, the DX, a preset reference angle group sequence JB, a preset reference action identification sequence DB and a hidden Markov model; obtaining a first matching degree according to the first feature list and the second feature list; obtaining a second matching degree according to the JX and the JB; obtaining a limb movement recognition result corresponding to the to-be-recognized target according to the first matching degree and the second matching degree; wherein the limb movement recognition result is used for describing the execution accuracy of the to-be-recognized target on the target limb movement set. According to the invention, an accurate and objective identification result can be obtained.

This invention relates to the interdisciplinary field of image recognition and intelligent medical technology, specifically disclosing a method for orthopedic rehabilitation movement recognition and assessment based on image recognition. This method acquires patient motion images using a non-invasive multi-view visual sensor, extracts the three-dimensional coordinates of key skeletal points, and constructs a parametric biomechanical digital twin model integrating joint range of motion, muscle force lines, and ligament tension mechanisms. The key point data is input into a graph neural network for posture recognition, and the digital twin model is simultaneously invoked for physical feasibility verification and posture correction. Finally, the spatiotemporal trajectory similarity is calculated using a standard rehabilitation movement template, generating a comprehensive assessment result including movement completion, safety level, and injury risk. This invention, through the above technical solution, improves the robustness, physiological rationality, and clinical safety of movement recognition.

This invention relates to a scoring system and method for aerobics competitions, belonging to the field of sports competition scoring. The system includes a data acquisition module, a first data processing module, a second data processing module, a core calculation module, and an output module. The data acquisition module acquires scoring data input by the art, execution, and difficulty judging groups and the chief judge. The first data processing module performs arithmetic mean calculations on the art, execution, and difficulty scores respectively to generate average scores for each item. The second data processing module sums the points deducted by the chief judge and the points deducted based on the line of sight to generate the total points deducted by the chief judge. The core calculation module sums the average scores for each item with the total points deducted to generate the total score for the routine. The output module displays the total score. Through automated data calculation, combined with difficulty suggestion scoring provided by the movement recognition module, data compliance ensured by the verification module, and full traceability achieved through the storage module, the system improves the accuracy, efficiency, and objectivity of scoring, and enhances the transparency and credibility of the scoring.

Provided is a movement identification device capable of identifying a specific motion of a construction machine based on the output of a sensor attached to the construction machine with higher accuracy than the conventional technology. A movement identification device 100 includes a waveform generation unit 111, a waveform storage unit 121, and a motion identification unit 112. The waveform generation unit 111 generates a force waveform based on the signal of a force sensor that detects the force acting on the construction machine and an attitude waveform based on the signal of an attitude sensor that detects the attitude of the construction machine. The waveform storage unit 121 stores reference waveforms, which are combinations of force waveforms and attitude waveforms corresponding to specific motions. The motion identification unit 112 compares a motion waveform, which is a combination of a force waveform and an attitude waveform corresponding to an arbitrary motion of a construction machine, with the reference waveforms stored in the waveform storage unit 121 to identify a specific motion in the arbitrary motion of the construction machine.

The present application takes the teacher's hand gesture and upper limb movement as the research object, and discloses a teacher teaching intention detection method and system based on staggered attention for the auxiliary role of computer vision technology in the teaching scene. The method comprises the following steps: 1) respectively acquiring the teacher's hand gesture and upper limb movement video stream under the RGB-D camera and 3D structured light camera in the teaching environment; 2) respectively pre-processing the image data stream. The collected video stream is converted into teacher gesture, teacher upper limb movement key point heat map data stream and teacher gesture, teacher upper limb movement structured light image data stream; 3) the pre-processed data stream is respectively input into the teacher hand gesture recognition model and the upper limb movement recognition model. 4) after model prediction, the teacher hand gesture recognition result and the teacher upper limb movement recognition result are respectively output. The teacher gesture and the upper limb movement recognition result are combined to judge the teaching gesture. The present application uses a teacher teaching gesture estimation model based on a staggered attention mechanism, so that the network can recognize 3D teaching gestures according to the key point heat map when predicting the teacher gesture. At the same time, by combining the teacher upper limb movement recognition result with the gesture recognition result, the detection of the teacher's teaching intention is realized, and reference support is provided for the non-verbal ability evaluation of the teacher's teaching process.

The present application discloses a method and device for identifying radar range-velocity deception jamming, which relates to the field of anti-jamming of radar networks. The method determines that the traces originate from different types of deception jamming by using the mutations of the number of traces in the range dimension and the velocity dimension; establishes a spatial recognition feature set; determines the optimized range deception jamming and the first uncertain jamming based on the spatial recognition feature set and a preset spatial decision threshold; establishes a motion recognition feature set; determines the optimized velocity deception jamming and the second uncertain jamming based on the motion recognition feature set and a preset motion decision threshold; establishes a spatial motion recognition feature set; determines the optimized range-velocity deception jamming and the third uncertain jamming based on the spatial motion recognition feature set and a preset spatial motion decision threshold; and makes a comprehensive decision on the first uncertain jamming, the second uncertain jamming and the third uncertain jamming to determine the target range-velocity deception jamming. The present application improves the recognition rate of range-velocity deception jamming.

This application provides a method, system, and device for monitoring intelligent knee braces. The method is applied to an intelligent knee brace, which includes a motion data acquisition device comprising multiple sensors. The method includes: acquiring motion data of a target user (a user wearing the intelligent knee brace) collected by each sensor; based on the motion data, identifying basic movement types using a basic classification algorithm model to obtain basic movement recognition results; if the basic movement recognition results are not composite movements, using the basic movement recognition results as the target user's movement state; if the basic movement recognition results are composite movements, further identifying subdivided movement types using a subdivided movement algorithm model to obtain the target user's movement state.

The invention relates to a physical education teaching and training all-in-one machine integrating AI motion recognition and voice interaction, belongs to the field of physical education teaching and intelligent motion equipment, and solves the problems that existing campus motion equipment is single in function and lacks intelligent guidance. The device comprises a machine body shell, a core function module, an AI motion recognition module, an AI voice large model dialogue module, a data statistics module, a display module and a storage module. The core function module covers free training, classroom teaching and other scenes; the AI motion recognition module collects images and corrects postures; the AI voice large model dialogue module realizes intelligent dialogue; the data statistics module analyzes the score; the display module displays the information; and the storage module is used for storing data. The all-in-one machine integrates multiple functions, supports multi-person interaction, improves the standardization and interestingness of sports, and meets the requirements of campus physical education.

A method for lower limb movement recognition based on surface electromyography (EMG) decoding using S-transform energy concentration is proposed. First, the raw EMG signal is preprocessed. The preprocessed signal is then truncated to a useful time segment using endpoint detection. Next, the signal within this time segment undergoes segmented S-transform and energy concentration calculation. Segmented operations are used to extract signal features of a specified dimension. Movement pattern classification is performed using SVM, and multi-channel signal features are fused and analyzed for lower limb movement recognition. This invention performs segmented S-transform on the signal to preserve its temporal information, while optimizing the energy concentration calculation process to improve movement classification accuracy. An SVM multi-classifier is built, and the accuracy of lower limb movement pattern recognition is further improved through S-transform energy concentration and feature fusion.

The application discloses a kind of based on deep learning's hip exoskeleton movement mode identification method and system.The method includes: data acquisition and processing: through the inertial measurement unit and joint motor of hip exoskeleton, heterogeneous sensor data are acquired;Offline / real-time calibration and time synchronization are carried out to data, and data set is constructed in combination with motion label;Model construction and training: splice multimodal sensor data as input, construct deep learning network, fuse heterogeneous features and identify terrain and movement mode, train model and save optimal model;Lightweight deployment: through ablation experiment optimization sensor configuration, adopt channel pruning and compress model parameter quantity, and generate light weight model in combination with INT8 quantization technology.The system includes three major modules of data acquisition, mode identification, quantization deployment.The application solves the problem of heterogeneous sensor data fusion and real-time deployment, significantly improves the precision and efficiency of exoskeleton movement recognition.

The application discloses a lip movement recognition method and device based on three-dimensional lip reconstruction, and the method comprises the following steps: acquiring a lip reading video to be recognized; generating a lip image to be recognized; inputting the lip image to be recognized into a target three-dimensional lip reconstruction model to obtain three-dimensional lip data to be recognized; and inputting the three-dimensional lip data to be recognized into a target lip movement recognition model to obtain a lip movement recognition result. Wherein, the method comprises the following steps: acquiring a lip language video; generating a lip image to be trained and text information; constructing an initial three-dimensional lip reconstruction model; constructing an initial lip movement recognition model; training the initial three-dimensional lip reconstruction model to obtain a target three-dimensional lip reconstruction model; inputting the lip image to be trained into the target three-dimensional lip reconstruction model to obtain three-dimensional lip data to be trained; and training the initial lip movement recognition model to obtain a target lip movement recognition model. The application realizes lip movement recognition, improves the accuracy and robustness, and can be widely applied to the technical field of visual speech recognition.