Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1046 results about "Posture recognition" patented technology

Human body posture detection method and equipment based on machine vision

The invention provides a human body posture detection method and equipment based on machine vision, which are applied to posture recognition in physical fitness detection, and are used for generating a dynamic human body region set of a target user by acquiring a multi-frame continuous image sequence of a physical fitness training scene and performing human body region positioning processing on the multi-frame continuous image sequence. Performing posture feature extraction processing on the dynamic human body region set to obtain a space-time posture feature set of the target user, performing posture state recognition processing on the space-time posture feature set based on a preset physical fitness evaluation model to generate a posture state recognition result of the target user, and generating physical fitness evaluation parameters according to the posture state recognition result, and the physical fitness evaluation parameters are fed back to the physical fitness training guidance system. According to the method, the identification capability of fine posture change in the fitness action of the complex body can be improved, the synchronous evaluation of the action specification degree and the physiological load state is realized, and the limitation of the traditional single-dimensional action evaluation is broken through.
Owner:四川吉利学院

Human shape posture recognition method and system based on image analysis

The invention relates to a human shape posture recognition method and system based on image analysis, and the method comprises the steps: inputting the reference human shape data of a monitored object, and collecting the multi-modal data of an RGB image, an infrared image and inertial measurement data in a target scene in real time; space-time alignment processing is carried out, and corresponding features are fused; image space features are extracted, time sequence modeling is carried out on inertial data, and dynamic weighted fusion of two paths of network outputs is realized through a gating mechanism; human body basic joint points are positioned, and refined posture vectors including joint angles and limb relative positions are generated; according to attitude data and environment information collected in real time, adaptively adjusting an attitude classification threshold value and a similarity measurement standard, and predicting abnormal behaviors in a future time period; and when the abnormal behavior is predicted, triggering to execute a preset safety measure. Multi-modal data can be efficiently fused, attitude features can be accurately extracted, an identification strategy can be adaptively adjusted, and human shape attitude identification with behavior trend prediction capability can be realized.
Owner:CHINA WEST NORMAL UNIVERSITY

Posture recognition algorithm for any object under monocular camera and application system

The invention provides a posture recognition algorithm for any object under a monocular camera and an application system, and the algorithm comprises the steps: S1, constructing a target three-dimensional model, carrying out the multi-view annular shooting image collection of a target, and generating a dense grid model through feature extraction, matching, posture calculation and a multi-view geometric method; s2, generating an image depth map, and predicting depth information of a target in a motion process based on a monocular image sequence; s3, extracting a target image mask, and generating a target area mask graph through an image encoder, a prompt encoder and a mask decoder; and S4, executing attitude estimation, performing attitude initialization, correction and screening by combining the three-dimensional model, the depth map and the mask map, and outputting a six-degree-of-freedom attitude result of the target. According to the method, the target is subjected to annular shooting modeling through the method based on multi-view geometry, the three-dimensional model of the target is generated, attitude estimation is achieved in combination with the image mask and the depth map, the generalization ability of an attitude estimation algorithm in an actual scene is improved, and the application range of the attitude estimation algorithm in the actual scene is widened.
Owner:HANGZHOU BINGBAI INTELLIGENT TECHNOLOGY CO LTD

Chip clamp debugging system based on digital twinning

The invention relates to the technical field of automatic debugging, in particular to a digital twinning-based chip fixture debugging system, which comprises a state sensing fusion module, a positioning correction judgment module, a contact adjustment execution module, a closed-loop feedback correction module and a data linkage optimization module. According to the method, through time axis synchronous matching of multiple types of sensing data, extraction of position offset and pressure sudden change intersection features, enhancement of direction identification and dynamic precision, angle direction trend quantification through included angle interval analysis, improvement of spatial positioning continuity, and guarantee of effective response of an adjustment window through driving rate difference comparison, the accuracy of the adjustment window is improved, and the accuracy of the adjustment window is improved. Stretching and deformation data backtracking are introduced to improve the path correction capability, a virtual and real link is constructed in combination with a node log and a delay identifier, the consistency of simulation and actual behaviors is constrained, the overall debugging process is optimized through data linkage and time sequence control collaboratively, and higher response timeliness, posture recognition precision and data fusion stability are achieved.
Owner:SHENZHEN DAIPUSEN NEW ENERGY TECH CO LTD

Factory operator-oriented posture recognition management system and method

The invention discloses a factory operator-oriented posture recognition management system and method, and relates to the technical field of factory operation safety management, and the system comprises a video image collection module, a target detection module, a behavior recognition module, an illegal behavior detection module, an alarm module, a recording module and a QT5 integration module which run in sequence. The application scene of the whole management system identifies and manages operators and automation equipment in a factory. The technical key points are as follows: aiming at the problem that in the prior art, false alarm is easy to generate in behavior recognition in a factory scene, the invention provides a system for detecting factory human-object interaction violation behaviors, the system integrates target detection and behavior recognition algorithms, the interaction condition between factory operators and equipment can be monitored in real time, and the system has high practicability. Possible illegal behaviors can be accurately identified, and an alarm signal can be timely sent out, so that the safety management level of a factory can be improved.
Owner:ZHEJIANG SCI-TECH UNIV

Fitness assisting method and device, equipment, storage medium and product

The invention relates to the technical field of artificial intelligence, in particular to an auxiliary fitness method and device, equipment, a storage medium and a product. The method comprises the following steps: performing decoding and frame extraction on a user fitness video to obtain fitness continuous frames; performing human body key point detection on each frame in the fitness continuous frames to obtain key point information; generating a human body dynamic model based on the key point information; based on a preset posture recognition model, performing posture recognition on the human body dynamic model to obtain a motion posture set; and if the wrong motion posture exists in the motion posture set, generating correction data based on a standard posture corresponding to the wrong motion posture in a preset standard posture library. According to the method, refined decoding and frame extraction are carried out on the fitness video of the user, the key points of the human body can be accurately detected, the dynamic model is generated, then the preset posture recognition model is used for recognizing the motion posture and correcting wrong actions in time, and therefore the fitness effect is improved.
Owner:SHENZHEN JIUZHOU ELECTRIC

Object positioning and posture recognition method based on 3D vision

ActiveCN119625068Aquality improvementImprove image processing capabilitiesImage enhancementImage analysisPattern recognitionPoint cloud
The invention provides an object positioning and posture recognition method based on 3D vision. The method comprises the steps that 3D point cloud data and image data corresponding to the 3D point cloud data are collected; preprocessing the image data to obtain a quality evaluation result, and executing image restoration processing based on the quality evaluation result to generate optimized image data; inputting the optimized image data into a pre-constructed conditional diffusion model based on hierarchical feature guidance, and generating feature representation of the optimized image data; and inputting the feature representation of the optimized image data into a differential transformer network to obtain a position and attitude prediction result of the object. According to the invention, through innovative image quality evaluation based on dual representation interaction driving, a conditional diffusion model based on hierarchical feature guidance and the design of a differential transformer network, the precision and robustness of object positioning and posture recognition in a complex environment are improved.
Owner:SHENZJEM SOFTWELL TECH DEV CO LTD

Rehabilitation training detection method and system based on artificial intelligence

The invention relates to the technical field of rehabilitation training detection, in particular to a rehabilitation training detection method and system based on artificial intelligence, a standard action library is constructed through standard action videos shot at multiple angles, and track and angle features of key joints are extracted for user training comparison; the skeleton key points of the user are extracted in real time through a MoveNet network, and efficient posture recognition in a home scene is achieved; analyzing position difference, angle change and acceleration characteristics by combining a space-time sequence matching algorithm, generating a dynamic matching degree index, and positioning a deviation joint to generate a correction prompt; introducing an attention mechanism model, learning the contribution degree of each joint to cycle recognition, dynamically selecting a dominant joint for action counting, recognizing starting and ending points of an action cycle through an acceleration curve, and finishing effective action statistics in combination with a dynamic threshold value, so that the counting accuracy and the self-adaptive capability are improved; therefore, the training cost is reduced, the evaluation credibility is enhanced, and accurate statistics and analysis of rehabilitation training data are realized.
Owner:HEALTH & HEALTH TECH INFORMATION SERVICE (GUANGZHOU) CO LTD

Intelligent projection method and system based on posture recognition, medium and program product

The invention discloses an intelligent projection method and system based on posture recognition, a medium and a program product, and the method comprises the steps: collecting human behavior data through a distributed multi-mode sensing network; preprocessing the human body behavior data by using a self-organizing data cleaning algorithm to obtain de-noised human body behavior data; inputting the de-noised human behavior data into a dynamic space-time diagram network, and extracting human behavior feature data; based on the human body behavior feature data, a hierarchical semantic parser is used for conducting multi-scale parsing on human body behaviors to obtain a parsing result, the parsing process comprises action recognition, intention inference and sentiment analysis, and the parsing result comprises prediction intention and prediction sentiment; and determining target projection content from a preset dynamic knowledge graph by using an environmental response generator according to an analysis result, and controlling projection equipment to play the target projection content. According to the method and the device, the complexity of user operation is reduced, the selectivity of the user is increased, and the suitability with user preferences is improved.
Owner:SHENZHEN EFERCRO ELECTRONIC TECHNOLOGY CO LTD

Patient body position intelligent monitoring system based on deep learning

The invention relates to the technical field of medical monitoring, in particular to a patient body position intelligent monitoring system based on deep learning, which comprises a data acquisition module, a preprocessing module, a body position recognition model construction and training module, a body position monitoring module, an early warning module and a database module. The data acquisition module acquires body position image data of a radiotherapy patient; the preprocessing module cleans and standardizes the data; the body position recognition model is trained according to the labeled data and the requirements of a doctor; the body position monitoring module inputs the preprocessed data into a model to obtain an identification result, and compares the identification result with a standard body position to monitor consistency and a treatment position; the early warning module gives out early warning when abnormity occurs; the database module stores various data. The system can improve the radiotherapy precision, guarantee the safety of patients, improve the working efficiency, optimize the radiotherapy process, provide data support for medical research and promote medical informatization, and has important clinical value and wide application prospects.
Owner:THE FIRST AFFILIATED HOSPITAL OF FUJIAN MEDICAL UNIV

Television control system capable of remotely adjusting child safety distance

The invention relates to the technical field of myopia prevention and control, and discloses a remotely adjustable child safety distance television control system, which comprises a multi-sensor fusion module used for detecting the distance between a child and a television in real time, and cutting off a television power supply when detecting that the distance between the child and the television is smaller than a set early warning distance; the posture recognition module indicates the child to adjust the sitting posture through voice when the posture does not meet the health standard; the eye fatigue detection module is used for judging the fatigue degree by detecting the blinking frequency and the eye closing duration of the child; the environment sensing module is used for detecting indoor light intensity and noise level; and the loudspeaking module is used for sending a prompt and an instruction to the child through voice. The watching distance, the sitting posture and the eye using state of a child are monitored in real time through the multi-sensor fusion module, the posture recognition module and the eye fatigue detection module, intervention is conducted in time, asthenopia and myopia caused by short-distance watching, poor postures and long-time eye using are avoided, and the eyesight health of the child is effectively protected.
Owner:DEZHOU LINGCHENG DISTRICT JIUSHIYOU VISION SERVICE CO LTD

Human motion posture recognition method and system based on multi-modal data fusion

The invention discloses a human motion posture recognition method and system based on multi-modal data fusion, and relates to the technical field of posture recognition, and the method comprises the steps: firstly, synchronously obtaining a human motion posture video frame and an IMU segment, then carrying out the feature extraction of the two kinds of heterogeneous data in a shunt parallel mode, and carrying out the feature extraction of the two kinds of heterogeneous data; and respectively capturing visual space attitude information and dynamic inertial characteristics of the IMU. Afterwards, specific features of the modals are uniformly expressed through a mixed Token and embedding mechanism, and a space-inertia collaborative attention fusion mechanism is further introduced to realize dynamic association and deep fusion of cross-modal information; and finally, classifying the multi-modal fusion representation vector obtained by fusion so as to realize accurate recognition of the human motion posture. In this way, the defect that traditional fusion is insufficient in capturing subtle action differences can be overcome, and the accuracy and stability of action recognition in a complex scene are improved.
Owner:ZHEJIANG FUBAO INTELLIGENT TECH CO LTD

Transform fusion-based multi-modal posture recognition system

The invention relates to the technical field of multi-modal posture recognition, and relates to a multi-modal posture recognition system based on Transform fusion, which fully excavates the complementary advantages of visual information in spatial detail representation and inertial information in time sequence dynamic capture through space-time alignment of multi-modal data and deep fusion based on an attention mechanism. The accuracy and the stability of attitude estimation under the conditions of visual occlusion, rapid movement and complex illumination are obviously improved; posture optimization is carried out by introducing physical constraints such as bone length constancy and joint movement range limitation, and time domain smoothing and contact state correction are applied, so that the precision of the generated three-dimensional posture sequence is ensured, a solid technical foundation is laid for improving the naturalness, safety and intelligent level of man-machine interaction, and the method is suitable for popularization and application. And meanwhile, reliable application and deep development of the intelligent robot in key fields of service robots, virtual reality, remote cooperation and the like are powerfully promoted.
Owner:ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY

Physical training posture correction method based on machine vision

The invention provides a physical training posture correction method based on machine vision, which comprises the following steps: acquiring an athlete training image sequence through a multi-view image acquisition system and preprocessing the athlete training image sequence, extracting three-dimensional posture key points of a human body by utilizing a depth posture recognition model, constructing a skeleton model and calculating real-time kinematics characteristic parameters, and performing multi-dimensional comparison with standard parameters to generate a posture deviation evaluation report, thereby generating a personalized multi-modal correction feedback scheme, and establishing a personal athlete movement feature database to realize adaptive standard parameter optimization. According to the method, the training postures of athletes can be accurately recognized and corrected in real time, the training effect can be improved, sports injuries can be prevented, and training individuation and scientificity are improved.
Owner:JILIN NORMAL UNIV

Dance posture recognition and interaction method and system based on binocular data acquisition equipment

The invention relates to a dance posture recognition and interaction method based on binocular data acquisition equipment, and the method comprises the steps: synchronously recording dance accompanying music and a student dance video when an acquisition instruction sent by a teacher end is received; detecting dance accompanying music beats, identifying sticking point positions and time of dance accompanying music, and synchronously extracting dance video frames of the students; extracting student limb key points from the student dance video frames; based on a stereo matching algorithm, depth information of the student limb key points is calculated; based on the depth information, outputting the specific position of the student; based on a preset standard dance video, judging whether the extension degree and the motion amplitude are standard or not; focusing the target student based on the spatial position of the target student when any one of the extension degree and the motion amplitude is judged to be non-standard; and generating a feedback report and sending to the teacher end. The method and the device have the effect of quickly focusing the students with nonstandard dance postures.
Owner:GUANGZHOU LOGANSOFT TECH CO LTD

Intelligent personnel falling monitoring method and system based on TOF camera hardware

The invention is suitable for the technical field of artificial intelligence, and provides a TOF camera hardware-based personnel falling intelligent monitoring method and system, and the method comprises the following steps: collecting three-dimensional point cloud data of a monitoring region through a ToF area-array camera, carrying out the data preprocessing and background subtraction of the three-dimensional point cloud data, and obtaining the point cloud data of a human body; personnel existence detection and personnel static detection are carried out based on the three-dimensional point cloud data; performing posture recognition, performing normalization conversion on the human body point cloud data to obtain a human body depth map, and performing posture detection on key points of the human body depth map to obtain human body key point data; and predicting the human body key point data based on the trained LSTM model to obtain a person posture state, and when the person posture state is that the person falls down, generating early warning information. The method is wide in application range and suitable for personnel falling detection in public areas and private spaces, the point cloud data only comprises the attitude key points of the personnel, and personnel falling reasons can be known under the condition that privacy is not invaded.
Owner:BEIJING LIANPING TECH CO LTD +1

Training method and device of image recognition model and image recognition method and device

The invention provides an image recognition model training method and device and an image recognition method and device. The training method comprises the steps that a generative adversarial network algorithm model based on feature space distortion is adopted to expand an original human body posture training sample to obtain a target human body posture training sample, the generative adversarial network algorithm model comprises a generator and a discriminator, the generator comprises a distortion module, and the discriminator comprises a discriminator; a distortion module generates distortion image features according to the random noise vector and the distortion module parameters and a preset feature deformation algorithm, and obtains a target human body posture training sample based on the distortion image features; inputting the target human body posture training sample into the initial image recognition model; and according to the output of the initial image recognition model in each training period, parameter adjustment is performed on the initial image recognition model until the target image recognition model meeting the training stop condition is obtained, so that the generalization ability of the target image recognition model and the accuracy of human body posture recognition are improved.
Owner:CHENGDU KAIYUAN COMPUTING ECOLOGICAL TECHNOLOGY CO LTD

Three-dimensional human body posture estimation method and system

The invention discloses a three-dimensional human body posture estimation method and system, and relates to the technical field of computer vision, and the method comprises the steps: extracting two-dimensional human body posture key points from a monocular video picture sequence, and generating a two-dimensional human body posture key point sequence; projecting the two-dimensional key point sequence to a feature space through nonlinear high-dimensional mapping to generate a high-dimensional feature space matrix; and inputting the high-dimensional feature matrix into a three-dimensional human body posture recognition model fusing motion constraints and frequency division spatial-temporal features to obtain a three-dimensional human body posture key point sequence, and realizing three-dimensional human body posture estimation through three-dimensional coordinates. According to the method, the robustness and the detection precision of the monocular three-dimensional human body posture estimation method are improved. Error values of relative movement speed, skeleton length and skeleton direction of the key points are calculated, so that training is easier to converge, and the training process is more stable.
Owner:TONGJI UNIV

Multimodal three-dimensional hand grid reconstruction method based on diffusion model

The invention belongs to the technical field of human body posture recognition, and discloses a multi-modal three-dimensional hand grid reconstruction method based on a diffusion model, and the method comprises the steps: collecting a depth map and point cloud data through a feature extraction model, and extracting hand joint features according to the depth map and the point cloud data; the initialized standard Gaussian distribution noise and the extracted hand joint features are input into a diffusion model together for iterative denoising, and the hand joint positions are recovered from the noise step by step through multiple iterations; and reconstructing a three-dimensional hand grid through a grid reconstruction module according to the hand joint position. According to the method, based on the color image, the depth map and the three-dimensional point cloud data are fused, so that high-precision three-dimensional hand grid reconstruction is realized, and the speed and accuracy of hand posture reconstruction are remarkably improved.
Owner:JIANGXI AGRICULTURAL UNIVERSITY

Intelligent driving behavior identification method and system based on video analysis

The invention provides a driving behavior intelligent identification method and system based on video analysis, and the method comprises the steps: obtaining a driver face video stream and a road environment video stream collected by a vehicle-mounted camera, and reading the driving information recorded by a whole vehicle communication network; recognizing an eyelid closing state, a sight line direction and a head posture in the driver face video stream based on a posture recognition model, and performing fatigue distraction analysis to obtain driver state information; performing motion trail analysis on the road environment video stream and the driving information, and performing driving risk assessment in combination with the driver state information to obtain driving assessment information; and performing early warning construction according to the driving evaluation information, generating early warning prompt information, and synchronously writing the early warning prompt information, the driving evaluation information and the driver state information into a safety data protection memory. The fatigue and distraction states of the driver can be recognized more accurately, and the accuracy of state judgment is improved.
Owner:SHENZHEN ZHIJU CLOUD SERVICE TECH CO LTD

Standing long jump examination system based on AI vision

The invention relates to the field of AI vision algorithms, and provides an AI vision-based standing long jump examination system, which comprises an image acquisition module for acquiring an image of a standing long jump examination area and transmitting the image to an image processing module, and the image processing module is used for carrying out image distortion correction and horizontal perspective transformation operation; the processed image information is transmitted to an AI analysis module; the AI analysis module performs an AI human body posture recognition technology and an AI object recognition technology according to the information transmitted by the image processing module, and sends calculation and analysis results to the data storage module and the result output module; the data storage is used for storing data information and report information transmitted by the AI analysis module; the result output module performs real-time output according to the information transmitted by the AI analysis module; according to the method, distortion correction, horizontal transformation and AI algorithm analysis are carried out on the image, so that image data in the standing long jump process are better processed and analyzed, and accurate recognition and evaluation of examinee actions are achieved.
Owner:BEIJING TIMES DIGITAL TECH CO LTD

Human-computer interaction method and system based on three-dimensional coordinate measurement

The present invention provides a solution of a human-computer interaction method and system based on three-dimensional coordinate measurement, and a plurality of solutions for applying same to solve technical problems. An operation body and / or an operator performs input and operation interaction by means of a virtual keyboard and a virtual mouse, or integrates a display picture space and carries out various participatory and interactive direct operations and experiences on object components and objects in virtual and real scenes. Virtual handwriting input, body movement posture recognition, and lip recognition interaction methods are further provided, and virtual mode control and interaction methods such as gesture recognition and virtual touch screen interaction are supported. Contact is not needed and there is no need to touch the screen, and mobility is achieved. The present invention is suitable for the two-dimensional conventional computing field, and particularly suitable for three-dimensional space computing fields (comprising VR, MR, AR, meta-universe, virtual simulation, software games, three-dimensional graphics, three-dimensional animation, and other three-dimensional scenes). Human-computer interaction operations in work and life of people can be greatly facilitated and optimized.
Owner:JIANG XIANWEI

Private data sharing for extended reality systems

Techniques and systems are provided for performing data transfers. For instance, a process can include receiving an indication to perform a data transfer; determining, based on a feature map of an environment, a location of an extended reality (XR) device in the environment; determining a first pose of the XR device; obtaining, from the feature map, location information for a target device in the environment; identifying the target device based on the location and the first pose of the XR device; transmitting, to the target device in response to the indication to perform the data transfer, a request to initiate the data transfer; receiving a second pose of the target device; and performing the data transfer based on the received second pose and the first pose of the XR device.
Owner:QUALCOMM INC

Human body posture recognition method based on millimeter wave radar sparse point cloud

The invention discloses a millimeter-wave radar sparse point cloud-based human body posture recognition method, which belongs to the technical field of human body posture recognition, and comprises the following steps of: acquiring three-dimensional point cloud data of human body actions through a millimeter-wave radar, and preprocessing the three-dimensional point cloud data; and training a lightweight neural network model by using the preprocessed point cloud data, wherein the model comprises an edge convolution module and a grouping sparse Transform encoder module. The edge convolution module extracts spatial geometric features and detects dynamics, static postures are directly classified, dynamic postures capture a time sequence dependency relationship through a grouping sparse Transform module, attention calculation is only carried out on frames with feature changes exceeding a threshold value, and mean pooling aggregation is carried out on other frames. And finally, classifying the human body postures based on the spatial geometric features and the time sequence dependency relationship to obtain a classification result. The device is simple in structure, accurate in recognition and suitable for efficient deployment of edge equipment.
Owner:LINYI UNIVERSITY

Camera parameter adjustment method and device, equipment and storage medium

The invention provides a camera parameter adjustment method and device, equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of an original image, and obtaining an enhanced image; inputting the enhanced image into a preset posture recognition model for feature extraction and posture analysis, and outputting a posture information data set; performing environmental factor analysis on the enhanced image and the attitude information data set to obtain an environmental characteristic parameter set; based on a preset multiple linear regression function, establishing a posture-environment-camera parameter mapping relation according to the posture information data set and the environment characteristic parameter set, and adjusting the weight of camera parameters to obtain a camera parameter adjustment value set; synthesizing real-time captured images, performing quality scoring on the real-time captured images, and adjusting the camera parameter adjustment value set according to a quality scoring result to obtain a camera parameter optimization value set; and according to preset operation preference information, adjusting the camera parameter optimization value set to obtain a personalized camera parameter set for shooting.
Owner:SHENZHEN PINKUO INFORMATION TECHNOLOGY CO LTD

Intelligent warehouse goods posture recognition and automatic sorting method and system

The invention provides an intelligent warehouse goods posture recognition and automatic sorting method and system, and the method comprises the steps: S2, extracting the edge contour and surface features of goods from point cloud data for a preliminary value set, calculating the direction vector and shape distribution characteristics of the goods through a principal component analysis method, and obtaining a quantitative result of shape feature extraction; s6, historical sorting data and real-time sensor data are extracted from the warehousing system database according to the classification basis adapted to the complex scene, the dynamic posture change trend of the goods is predicted through a time sequence analysis method, and optimization parameters of real-time processing are obtained; and S7, the movement track and the grabbing angle of the sorting mechanical arm are adjusted through the optimization parameters subjected to real-time processing, a deep reinforcement learning algorithm is adopted to conduct iterative optimization on the sorting action sequence, and an execution scheme of sorting accuracy is determined. According to the method, the accuracy of goods posture recognition and the automatic sorting efficiency in the complex storage environment are remarkably improved.
Owner:GUANGDONG WULIU DIGITAL TECHNOLOGY CO LTD

Human body posture recognition method based on multi-modal neural network framework

The invention relates to the technical field of computer vision and neural network processing, in particular to a human body posture recognition method based on a multi-modal neural network framework. Comprising the following steps: collecting event data, and representing the event data by using a five-channel event representation method; dividing the preprocessed five-channel event data into three channels, namely a space channel, an event characteristic channel and a point cloud channel; after channel splitting is completed, feature extraction is carried out respectively, and features of different modals are optimized and integrated through dynamic feature enhancement and cross-modal fusion; a skeleton constraint module and a space-time joint processing module are adopted to enhance understanding of the network on a human body structure and modeling of a space-time dependency relationship; a prediction head module is adopted to output final human body key point coordinates; and carrying out training optimization by adopting a multi-task learning framework to obtain a posture recognition result. The method has the advantages that the sparse asynchronous characteristic of event data is effectively processed, the blind spot problem of static limbs is solved, low power consumption is kept, and high-precision human body posture estimation is achieved.
Owner:CHANGCHUN INST OF OPTICS FINE MECHANICS & PHYSICS CHINESE ACAD OF SCI

Binocular camera-based cattle body size performance measurement system

The invention relates to the field of livestock breeding, in particular to a cattle body size performance measurement system based on a binocular camera, which comprises a binocular camera acquisition module, a posture recognition and key point extraction module, a point cloud processing module, a posture correction module and a data processing and optimization module. According to the invention, the binocular camera is combined with an advanced algorithm, so that the measurement efficiency in the cattle breeding process is greatly improved; through cooperative work of multiple modules, reliable data support is provided for cattle breeding; manual measurement is not needed in the whole process, manual operation errors are avoided, the labor intensity of workers is reduced, meanwhile, stress reactions of cattle caused by manual fixing and measurement are reduced, and healthy growth of the cattle and scientization and humanization of breeding management are facilitated; the system can adapt to different light conditions, cattle body types and motion states, can stably and accurately complete body size performance measurement tasks no matter in an indoor breeding environment or in an outdoor pasture environment, and has a wide application prospect.
Owner:BEIJING PHILISENSE ELECTRONICS TECH CO LTD

Intelligent shooting examination training system and method

The invention relates to the technical field of intelligent training, in particular to an intelligent shooting examination training system and method.The intelligent shooting examination training system comprises a posture recognition module, a track monitoring module, a hit analysis module, a rhythm comparison module and a label output module. According to the method, on the basis of action images in the process from gun holding to firing of a trainee, synchronous angle tracks of shoulders and elbows are recognized in real time, comparison is conducted in combination with a standard action combination, the matching difference in each time period is accurately screened and quantified, and the action control stability is dynamically evaluated by analyzing laser track coordinate points and direction changes in the aiming period; structured scores are formed by using a hit point sequence and combining path ductility and hit area density, action unit starting and ending time in a training process is compared with rhythm arrangement one by one, advanced and delayed phenomena are identified, performance scores are flexibly adjusted according to multi-dimensional index weights, and accurate matching between training performance evaluation and actual ability requirements is realized.
Owner:XIAMEN UNIV OF TECH

Human pose recognition using abstract images and viewpoint / pose encoding

A device receives a real image (e.g., photograph or video frame) that includes a human. The device creates a synthetic image corresponding to the real image. The synthetic image includes a synthetic environment and a humanoid shape that correspond to the human. The device predicts, using a trained viewpoint neural network and based on the synthetic image, a predicted viewpoint heatmap. The device predicts, using a trained pose neural network and based on the synthetic image, a predicted pose heatmap. The device provides, as input to a random synthetic environment, the predicted viewpoint heatmap and the predicted pose heatmap and creates a reconstructed three-dimensional pose based on the predicted viewpoint heatmap, the predicted pose heatmap, and the random synthetic environment. The device classifies the reconstructed three-dimensional pose as a particular type of pose of the human in the real image.
Owner:RGT UNIV OF CALIFORNIA