371 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 an intelligent data labeling method based on artificial intelligence, and relates to the technical field of intelligent medical treatment, and the method comprises the following steps: obtaining physiological parameter data, historical health parameter data and motion state data of a user; outputting motion state label data through a pre-constructed motion recognition model according to the motion state data; and performing sliding window analysis on the historical health parameter data, and dynamically establishing and updating long-term change data of the user health parameters. According to the scheme, whether the physiological parameter fluctuation is caused by the movement or not can be distinguished through associated retrieval of time window division and the movement state label, for example, when it is detected that the heart rate fluctuation of the user during running exceeds the threshold value, normal physiological response instead of abnormity can be judged in combination with the movement label; the probability that normal physiological parameter fluctuation caused by movement is mistakenly marked as abnormal can be effectively reduced, and meanwhile, the pertinence of anomaly detection 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 relates to the technical field of intelligent wearable devices, and discloses a fusion multi-modal interaction method and device and a storage medium. The method comprises the following steps: acquiring an input signal, and performing gesture recognition processing on touch data to obtain a gesture track; comparing the gesture track with a preset gesture model to obtain a gesture recognition result; performing voice recognition processing on the voice data to obtain a voice recognition result; according to a preset motion feature model, performing identification operation processing on the motion data to obtain a motion identification result; and according to a preset cloud large model, carrying out fusion analysis on the gesture recognition result, the voice recognition result and the motion recognition result to obtain operation recognition data of multi-modal interaction. In the embodiment of the invention, the operation identification data is obtained through the method, and the equipment can perform multi-modal interaction, so that the overall interaction is more natural to establish a stable user connection feeling.

The invention relates to the technical field of action recognition, in particular to a pattern rope skipping action recognition system and method, and the system comprises a limb angle collection module, a stability recognition module, an action triggering and screening module, a rope body direction analysis module and a cross mapping judgment module. According to the method, by introducing three-dimensional coordinate extraction and included angle change trend analysis of limb key joints in the jumping period, the dynamic characteristics of limbs in the action process can be accurately reflected, and the action amplitude and stability change can be effectively expressed through an angle data sequence constructed by multi-dimensional indexes such as the maximum value, the minimum value and the average value of the included angle in the period; a stability identification mechanism is constructed to carry out local regression fitting and residual error statistics on a periodic angle trend, accurate labeling of a stable state of an action posture is realized, and then a key frame sequence with an actual jump intention and a continuous posture in the jump action is effectively identified through fusion screening of labeled frames and a jump-empty state.

The invention belongs to the field of computer vision, and discloses a method, a system, equipment and a medium for recognizing whole-body actions of a three-dimensional skeleton human body based on a multi-style topological matrix and refined skeleton features, and the method comprises the following steps: firstly, acquiring skeleton action sequence data containing multi-frame three-dimensional coordinates of human body articulation points; constructing a multi-style topological structure composed of three local adjacent matrixes of the head, the trunk and the lower limbs and a global adjacent matrix; after spatio-temporal feature extraction is carried out through a graph convolutional network, refining processing is carried out on output features to generate local and global feature representations, and corresponding prediction probability distribution is calculated; and training the network by using a combined loss function of global and local prediction probability distribution joint optimization, and finally outputting an action classification result. According to the method, the joint relation is captured through effective skeleton topological representation, local and global feature refined learning is combined, and the three-dimensional skeleton human body action recognition performance is improved.

The invention discloses a fan defect detection method and system based on machine vision, and belongs to the technical field of image data processing, and the method comprises the steps: obtaining a historical shot image of a fan blade, generating a training data set, building a deep learning network architecture based on a convolutional neural network, and building a fan blade motion recognition model. Carrying out calculation processing by using a dark channel prior algorithm, obtaining a dynamic adjustment weight, training an AOD-Net model based on the dynamic adjustment weight, establishing a fan blade fuzzy correction model, carrying out real-time shooting on the fan blade, and carrying out motion identification correction by using a fan blade motion identification model. The fan blade fuzzy correction model is used for dust fog removal, the defect detection model is established, and the defect detection model is used for defect detection, so that the fan blade moving at a high speed can be accurately identified, the outline details of the fan blade are clear, and the state of the fan blade can be timely and accurately analyzed during defect detection. And the working performance of the fan blade is improved.

The invention discloses an eye protection method and system of an intelligent terminal, relates to the technical field of eye protection terminals, and aims to solve the problem of child eye use safety monitoring, multi-source data such as child face images, eye distances, equipment postures and environmental stability are collected, and time sequence data in a unified format is formed through noise filtering and synchronous processing; the posture angle and equipment stability information is extracted through the visual recognition and motion recognition sub-module, and the unhealthy eye using state is comprehensively judged; dynamically updating an eye using distance and a posture threshold value according to the height and the vision condition of the child and parent feedback; real-time monitoring is carried out, friendly reminding is triggered, and feedback data are recorded for closed-loop optimization; through cloud management, a parent-side App can check data in real time, a protection mode can be remotely started, and personalized eye protection suggestions are provided based on big data analysis. Through real-time remote intervention, accurate monitoring and personalized management of eye using behaviors of children are remarkably improved, and the risk of myopia is effectively reduced.

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 provides an interaction method based on finger pinching action recognition, electronic equipment and a storage medium. The method comprises: acquiring an image in real time; determining the type of finger pinching gestures in a preset number of continuously acquired frame images; when same gesture images in the preset number of frame images meet a target condition, the finger pinching gesture is determined to be an effective finger pinching gesture, the same gesture images are images with finger pinching gestures of the same type, and the target condition includes that the number of the same gesture images is larger than or equal to a first number; determining a man-machine interaction instruction corresponding to the effective finger pinching gesture; and executing the man-machine interaction instruction. According to the method, the pinching gesture is taken as a gesture instruction in the man-machine interaction process, so that the pinching gesture is more difficult to trigger by mistake compared with a common gesture, and the safety of man-machine interaction is enhanced.

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 relates to the technical field of intelligent security and protection monitoring, and discloses a library intrusion intelligent detection method and system based on deep learning, and the method comprises the steps: collecting library video data, carrying out the preprocessing, extracting spatial-temporal features, and carrying out the recognition of the spatial-temporal features; a deep convolutional neural network and a long-short-term memory network are combined to construct a double-flow fusion model, action recognition and abnormal behavior detection are realized, an intrusion event is determined through a multi-level threshold judgment mechanism, and real-time alarm is realized. According to the method, the accuracy and the real-time performance of warehouse intrusion detection are improved, false alarms and missing alarms are effectively reduced, and meanwhile, the method has autonomous learning and environment adaptability.

The invention relates to a lightweight pedestrian falling detection method and system for an inspection robot, and belongs to the technical field of computer vision and real-time human body posture estimation. The system is used for executing the method and comprises the steps that pedestrian posture image data is inspected through an inspection robot, and the data is preprocessed; constructing a lightweight YOLOv11 network, wherein the lightweight YOLOv11 network at least comprises a plurality of ADown lightweight down-sampling modules and a C2PSADAT composite module; the method comprises the following steps: training a lightweight YOLOv11 network to obtain an optimal weight so as to establish a pedestrian key node rapid detection model, and obtaining pedestrian key node data in real time through the pedestrian key node rapid detection model; and processing the obtained pedestrian key node data by adopting a motion recognition method ST-GCN model based on dynamic bones, and carrying out pedestrian fall-down detection in real time. According to the method, the light weight performance is better, and meanwhile, the accuracy is higher.

An electronic device and a method for anchoring an augmented reality object are provided. The electronic device includes a memory, a display and at least one processor operatively connected with the memory and the display. The at least one processor may be configured to control the display to display at least one augmented reality object on an augmented reality space, obtain anchoring attribute information designated to the at least one augmented reality object, identify an anchoring type of content anchored to the at least one augmented reality object according to a user's motion based on the anchoring attribute information, and control the display to display a visual effect representing the anchoring type to the content.

The invention discloses an AI-based piano practice assisting method, system and equipment and a medium, and the method specifically comprises the steps: carrying out the denoising and segmentation of sound data through employing a signal processing technology, extracting the finger key time sequence characteristics of motion data through employing a motion recognition algorithm, and obtaining a sound feature set and a motion feature set; based on the sound feature set and the action feature set, performing multi-dimensional analysis by adopting a bimodal Transform evaluation network to obtain a first evaluation score; acquiring emotional expression data of the learner during piano playing, and analyzing and processing the emotional expression data according to a preset emotional analysis model to obtain an emotional analysis result; and according to the first sentiment analysis result and the first evaluation score, a deep learning algorithm is adopted to classify playing styles and weak links of the learner, and a personalized improvement direction and a priority sequence are determined. According to the invention, comprehensive playing evaluation and sentiment analysis are provided for learners, and the efficiency and pertinence of piano practice are effectively improved.

The invention discloses a sonar target motion identification method based on a low-frame-rate bright spot structure sequence. The sonar target motion identification method comprises the steps of 1, roughly intercepting a bright spot structure; 2, accumulating a bright spot structure, sonar platform information and tracking information; step 3, motion compensation of the sonar platform; 4, accurately intercepting a bright spot structure; and 5, searching the optimal radial speed. According to the method, target radial motion parameters are extracted by means of distance steep motion of a sonar target among multiple frames of echoes, and a speed estimation loss function based on bright spot structure global optimal estimation is innovatively designed for the problems that the time interval between adjacent echoes of a low-frame-rate sonar target is long and the bright spot structure fluctuates greatly. According to the method, the global similarity between input period bright spot structures is fully utilized, the distance steep motion measurement precision is improved, the radial speed of the sonar target can be given at the same time, and the motion identification precision and stability of the sonar target are 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 relates to the technical field of radar motion recognition, in particular to a method and system for recognizing a human motion state through radar, and the method comprises the following steps: receiving echo signals of millimeter wave radar through a sensor, analyzing the amplitude and phase change of the signals, calculating the average value and standard deviation of the amplitude, and comparing the received signals. And recording an amplitude extreme point and a phase abrupt change point to obtain a radar echo signal feature. According to the method, the amplitude and phase change of the radar echo signals are meticulously analyzed, the execution process optimizes the monitoring of the motion state of the human body, while key signal features are extracted, the amplitude average value and the standard deviation of the signals are calculated in a continuous time period, and the sensitivity and the accuracy of signal processing are further improved; by analyzing the gradient value of the phase change and comparing the change of the adjacent time points, the method effectively recognizes the fine change of the human body movement speed, and greatly improves the capturing capability of the dynamic movement track.

The present invention relates to a technology capable of identifying a companion animal by analyzing video, image, and voice data collected through CCTV or a camera, for management of companion animals and tracking in case of loss thereof, wherein, by simultaneously or sequentially using at least one identification method among facial recognition, nose print recognition, voice recognition, and motion recognition by analyzing a video, image, or voice, an effect of greatly improving the reliability of object identification for companion animals can be provided.

The invention discloses a video-based 3D cerebral palsy baby action recognition method and system, and is applied to the technical field of baby action recognition. The method specifically comprises the following steps: respectively acquiring video files of normal twisting motion and abnormal monotonous motion of an infant, performing frame extraction processing to obtain image data of the infant, labeling the image data of the infant, making a data set based on the labeled image data of the infant, constructing and training a key point recognition model and a motion recognition model, and performing image recognition on the key point recognition model and the motion recognition model. And performing infant action recognition through the trained key point recognition model and action recognition model. According to the method, the data set containing the normal twisting motion and the abnormal monotonous motion image of the infant is made, the key point recognition model and the motion recognition model for recognizing the motion of the infant are constructed and trained, the motion posture can be rapidly and accurately extracted based on the monitoring video data of the infant, and support is provided for assessment of the infant with cerebral palsy.

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 provides a sewing action recognition method and system, a medium and a terminal. The method comprises the following steps: acquiring a sewing machine working area image when a turner performs sewing operation; acquiring a cloth contour and a hand position in the working area image of the sewing machine; acquiring sewing action information of the sewing machine; the sewing action information comprises the sewing needle number, the presser foot lifting state and the thread trimming frequency; and obtaining a sewing action recognition result according to the cloth contour, the hand position and the sewing action information. According to the sewing action recognition method and system, the medium and the terminal, accurate recognition of the sewing action is achieved through fusion of multi-modal data, and rapidness and high efficiency are achieved.

The invention discloses a fusion positioning method based on distributed multilayer tight coupling, and the method comprises the steps: carrying out the organic combination of motion data obtained by waist and foot nodes and an ultrasonic distance measurement result based on a dual-node positioning model of an internal constraint mechanism; extracting motion features of multi-layer data of the distributed sensor, and constructing a hybrid speed estimator model based on a deep learning network; constructing a pedestrian motion recognition and walking speed estimator model based on a space-time network; and according to an unscented Kalman filtering algorithm, fusing the original data of the distributed sensor, the motion data provided by the pedestrian motion identification and walking speed estimator model and the distributed self-optimization observed quantity provided by the mixed speed estimator model, and outputting the fused positioning data. According to the method, the multi-source fusion positioning precision and robustness of the distributed sensor positioning system in the large-range urban denial space are improved, and meanwhile, a multi-layer tight coupling fusion framework is used for stabilizing the positioning precision under the condition of complex personnel movement.

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 discloses a rehabilitation training system based on a key point recognition model and a graph neural network, and belongs to the field of deep learning neural networks. According to the system, a YOLOv8-Pose attitude recognition model, STGCN space-time diagram convolution and a double-layer full-convolution twin network are fused. The YOLOv8-Pose posture recognition model is used for accurately detecting the posture of the human body and providing basic data for action analysis of the posture of the human body. Based on STGCN space-time diagram convolution after space-time attention improvement and a double-layer full-convolution twin network, action recognition is carried out according to the features of human body postures, the correctness of rehabilitation actions is evaluated, and therefore the rehabilitation progress of a patient is accurately monitored and evaluated.

The invention discloses a low-energy-consumption long-sequence motion recognition method and system based on a mamba pulse neural network, and relates to the field of motion recognition, and the method comprises the steps: obtaining a motion recognition data set of an original event pulse, carrying out the space-time dimension processing of the motion recognition data set of the original event pulse, and obtaining an embedded vector sequence, the dimension of the embedded vector sequence is fixed; performing spatio-temporal context coding on the embedded vector sequence to obtain an embedded vector sequence containing the position context information, inputting the embedded vector sequence containing the position context information into a pre-established mamba spiking neural network model for training, and outputting to obtain a trained spiking neural network model; and the action data of the to-be-recognized event pulse is acquired, the action data of the to-be-recognized event pulse is input into the trained pulse neural network model, and a final human body action recognition result is output, so that accurate recognition of human actions in diversified scenes and motion states can be ensured.

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.

A micro-action recognition method based on space-time structure optimization comprises the steps that firstly, a to-be-trained micro-action video sample is preprocessed; secondly, designing a space-time structure optimization module STM, realizing adaptive enhancement of key features in the spatial dimension, interactively fusing information between adjacent time frames in the time dimension, and enhancing the time modeling capability of the micro-action recognition model; afterwards, micro-action joint embedding losses are designed, including cross entropy losses and semantic embedding losses, when the semantic embedding losses are calculated, video features and micro-action labels are mapped to a shared joint embedding space, and video feature embedding vectors and micro-action label embedding vectors are generated; the distance between the video feature embedding vector and the micro-action label embedding vector is shortened, and semantic alignment of the video features and the micro-action labels is realized, so that micro-action categories which are similar visually but different semantically are distinguished; and finally, under the supervision of the micro-action joint embedding loss, predicting a micro-action label of the video, and realizing micro-action identification and classification. According to the method, the accuracy and robustness of action classification are improved.

The invention discloses a dining table turntable control method based on diner action recognition of a side-mounted camera, and belongs to the technical field of image processing, and the method comprises the steps: obtaining an image region calibrated by a rotating disc, and representing the image region through an approximately elliptical polygon; obtaining a minimum circumcircle shape corresponding to the image area, and adjusting one end, far away from the camera, and the other end, close to the camera, of the approximate elliptical polygon to obtain a corrected image area calibrated by the rotating disc; an image of a dining table during dining is collected through a camera, whether the projection of the key points of the hand falls in the corrected image area calibrated by the rotating disc or not is recognized through a pre-trained RTMO model based on the key points of the human body, and whether the projection of the key points of the hand repeatedly moves or not is recognized, so that a motor is controlled. The intelligent dining table solves the problem that an existing intelligent dining table cannot accurately recognize food clamping, serving and other actions of diners under the condition that a camera is laterally installed, and consequently motor control is not accurate.