665 results about "Video recognition" patented technology

The invention discloses an operating room intelligent monitoring method and system based on monitoring video recognition, and relates to the technical field of medical safety supervision, and the method comprises the steps: collecting a video through an operating room camera array, and constructing an operation region panoramic sequence through a residual neural network and an optical flow field; a double-branch target detection network is adopted to extract the position of a medical worker, the body position of a patient and the characteristics of surgical instruments, and a surgical scene model is constructed; performing trajectory tracking based on skeleton key point extraction and Kalman filtering, and constructing a dynamic graph of the operation process; generating an operation process state report by using the time sequence diagram convolutional network and a multi-head attention mechanism; and comparing the operation specification library through a knowledge distillation algorithm, and carrying out grading recording on abnormal events. According to the invention, efficient abnormal event tracking and recording functions are realized, technical support is provided for operation quality control and safety management, and the overall performance of operating room intelligent monitoring is improved.

The invention provides a multi-mode cooperative sensing power station high-risk operation inspection method and system, and relates to the technical field of video recognition, and the method comprises the steps: activating an unmanned plane and a quadruped robot after a power station operation task is started; starting a video acquisition unit, and establishing a synchronous video stream; carrying out fusion alignment with the global reference coordinate system through an external synchronization signal; inputting the video sequence of the fused view angle into a multi-view angle action behavior recognition network, and establishing a dangerous behavior grade score; auditory data and olfactory data of the quadruped robot are obtained, and linkage abnormity is established; and polling abnormity is reported according to linkage abnormity and dangerous behavior grade scores. Through the method and the device, the technical problem of low inspection efficiency caused by difficulty in comprehensively identifying potential risks in a dynamic environment due to limitation of a single sensing mode is solved, and the inspection efficiency of a power station is improved by fusing multi-mode data, timely finding and processing the potential risks and improving the accuracy of video and audio identification.

The invention relates to an ICU patient dysphoria video recognition method based on space-time motion detection. Compared with the prior art, the defect that dysphoria video recognition is difficult to carry out on an ICU patient is overcome. The method comprises the following steps: acquiring and preprocessing a data set; constructing an ICU patient dysphoria identification model; training an ICU patient dysphoria identification model; obtaining video stream data to be identified; iCU patient dysphoria atom action recognition; and performing dysphoria quantitative classification based on an RASS score table. According to the method, the Slowfast basic model is improved, the detection precision and speed of the model are remarkably improved, the dysphoria behavior of the patient is automatically and accurately detected and understood from the perspective of space-time motion detection, the dysphoria condition of the patient is automatically scored according to the RASS score table, and accurate recognition of the dysphoria video of the ICU patient is achieved.

A system and a method for modeling local and global spatio-temporal context in a video for video recognition includes obtaining an input feature map and transforming the input feature map using linear functions to generate a spatial feature map and a temporal feature map corresponding to a video. The method further includes generating hierarchical contextual feature maps based on the spatial feature map and the temporal feature map that represent a context of the video at multiple levels of granularity. The method further includes aggregating the hierarchical contextual feature maps based on gating weights to obtain a spatial modulator and a temporal modulator that are representative of an aggregated context across the multiple levels. The method further includes obtaining an output spatio-temporal feature map based on the spatial modulator, the temporal modulator, and a query token associated with the video.

The invention relates to the technical field of image and video recognition, in particular to a trajectory tracking method and system based on laser radar and camera fusion perception. The method comprises the following steps: monitoring motion parameters of a target object; when the motion parameter of the target object reaches a preset monitoring threshold value, judging that the target object enters a monitoring state, and recording initial motion planning information; the three-dimensional motion direction information of the target object is obtained through the laser radar, and the two-dimensional dynamic image information of the target object is obtained through the camera. Through a data processing technology, an image processing technology and a video identification technology, three-dimensional motion direction information and a two-dimensional dynamic image of a target object are obtained, space-time correlation is carried out, and target fusion track information is constructed; and the trajectory deviation of the target fusion trajectory information is timely and accurately identified, and dynamic trajectory correction is performed on the trajectory deviation, so that the trajectory tracking accuracy is improved.

The invention discloses a behavior analysis method based on video recognition, a processor and a storage medium, and belongs to the technical field of data processing, and the method comprises the following steps: obtaining an image and a video clip with an operation behavior in an electronic manufacturing process; performing static behavior recognition on the image through a static behavior recognition model in the fusion model, and extracting potential static illegal behaviors in the image; extracting a skeleton point sequence from the video clip through a dynamic behavior recognition model in the fusion model so as to perform dynamic behavior recognition, and extracting potential dynamic illegal behaviors in the video clip; and outputting a behavior category code according to the static violation behavior and the dynamic violation behavior. According to the behavior analysis method based on video recognition, the processor and the storage medium, the problems that in an existing student operation behavior analysis mode, behaviors in operation are difficult to comprehensively capture in real time, and scoring objectivity is difficult to guarantee are solved.

The invention relates to an active train obstacle detection method and apparatus based on a positioning technique. The active train obstacle detection method comprises the following steps: S1, acquiring an electronic map; S2, correcting initial parameters; S3, performing parameter calibration of a video camera; S4, detecting a train obstacle; and S5, outputting an obstacle recognition result. The apparatus comprises a positioning module, a laser radar detection module, a video recognition module, an operational host and an interface module, wherein the operational host is connected to the positioning module, the laser radar detection module, the video recognition module and the interface module respectively. Compared with the prior art, the invention can increase the obstacle detection rate and reduce report failures and errors.

The invention provides an image text recognition method and system based on a mask diffusion model, a storage medium and equipment, and belongs to the technical field of image or video recognition or understanding. According to the method, multi-scale visual features of an image are extracted through a visual encoder, a mask diffusion decoder is combined, a diversified mask strategy and random character replacement disturbance are adopted in a training stage, denoising loss and auto-reflection loss are calculated respectively, and a model is optimized in a combined mode; in the reasoning stage, starting from a full mask state, a complete text sequence is recovered through multi-round iterative denoising. According to the method, the one-way modeling limitation of a traditional autoregression model is broken through, all-around context-dependent modeling is achieved, an autoreversion error correction mechanism and a block low-confidence mask strategy are introduced, and the recognition accuracy and reasoning efficiency in complex scenes such as shielding and fuzzy scenes are remarkably improved. The method provided by the invention reaches a leading level on a plurality of public data sets, and has the advantages of high precision and high speed.

The invention discloses an intelligent security and protection management system based on 5G, AI and UWB positioning technologies. The intelligent security and protection management system comprises an image video acquisition device, an environmental factor acquisition device, a UWB positioning module, a 5G communication network module and an intelligent security and protection management platform, the intelligent security and protection management platform comprises an AI video identification subsystem, a cockpit subsystem, a virtual electronic fence subsystem, an operation risk security management and control subsystem, an operation ticket visa subsystem, a video linkage subsystem and a query statistics subsystem. The intelligent security and protection management system based on the 5G, AI and UWB positioning technologies has the advantages of high-precision positioning technology, intelligent video analysis, highly integrated system architecture, flexible expansibility and customizability, safe and reliable data transmission and storage and the like.

The invention is suitable for the technical field of hydrographic survey, and provides a river and channel water flow velocity measurement method based on video recognition and CFD simulation, and the method comprises the steps: S1, completing data collection and constructing a data set, S2, building a three-dimensional water flow model of a target river or channel, S3, generating a vertical flow velocity distribution model, S4, carrying out the image preprocessing of an obtained video stream, and S5, carrying out the calculation of a vertical flow velocity distribution model. S5, performing target detection on the preprocessed image and calculating an area of the flow velocity, S6, performing optical flow calculation on the extracted specific area and calculating the surface velocity, S7, establishing a distribution relationship between the surface velocity and the vertical velocity, and S8, calculating the real flow velocity of the river channel according to the surface velocity and the vertical velocity distribution. According to the method, the relation between the cross section vertical flow velocity obtained through simulation and the surface flow velocity obtained through calculation of the optical flow method is established, the real flow velocity is finally obtained, multi-source fusion of data is achieved, and the calculation accuracy and the flow velocity measurement precision are remarkably improved.

The invention relates to the technical field of machine learning, and particularly discloses an intelligent parking guidance and reverse vehicle searching system based on multi-source heterogeneous data fusion. The system comprises a data perception fusion layer, a dynamic prediction decision-making layer and a user service interaction layer, realizes multi-step advanced probability prediction and dynamic optimal path planning of a parking space state through fusion of geomagnetic detection, video identification, payment flow, traffic situation and activity information, and realizes the optimal path planning of the parking space state based on multi-mode induction and live-action AR reverse vehicle searching guidance. And the parking efficiency and the user experience are improved.

The invention discloses a deep counterfeit video detection method fusing ViT and spatial features, belongs to the technical field of video identification, and is used for detecting a deep counterfeit video. The method comprises the following steps: constructing a neural network fusing ViT and spatial features; training a deep counterfeit video detection network; acquiring face data information in the deep forged video; and inputting the processed video information into the trained deep forged video detection network, and outputting whether the video information belongs to a forged video or not. According to the method, the advantages of the convolutional neural network in image counterfeiting detail extraction in video counterfeiting detection are fully utilized, thoughts of orthogonal convolution, an attention mechanism, residual connection and the like are combined, the accuracy of deep counterfeiting video detection is improved while the complexity of the model is maintained, and the detection efficiency of the deep counterfeiting video is improved. And moreover, the method has relatively stable detection performance in videos generated by various counterfeiting technologies.

The invention relates to the technical field of video identification, in particular to a video content structured disassembly analysis method and system based on time sequence segmentation. The method comprises the following steps: firstly, acquiring a video and metadata, and performing time sequence segmentation by using a first artificial intelligence model integrating a space-time attention mechanism and a sliding window mechanism to generate time slices; cutting the video into a plurality of video clips by utilizing an FFmpeg tool, and extracting text description of each clip by adopting a second artificial intelligence model integrated with multi-modal fusion and timestamp embedding to realize semantic alignment of actions and texts; meanwhile, key frames are extracted by using FFmpeg to generate a picture group, semantic analysis is performed by a third artificial intelligence model combining target detection and cross-frame consistency constraint, and an action label is generated; and finally, integrating the time slice, the key frame, the text description and the action tag to generate a complete structured output. According to the invention, the identification precision of the video content can be improved.

The invention relates to the technical field of intelligent operation and maintenance of photovoltaic power stations, in particular to an AI video recognition system for photovoltaic power station equipment inspection, which comprises a data acquisition unit, a data preprocessing unit and a defect recognition unit, and is characterized in that characteristics from one mode are used as query, evidence information serving as keys and values is searched from corresponding area characteristics of other modes, and the data acquisition unit is used for acquiring data; the method is used for synergistically diagnosing compound and early defects with weak or invisible characteristics in a single mode. According to the method, cross-modal collaborative reasoning can be realized: when a suspicious feature is found in one modal, whether evidence features capable of mutually verifying exist in the same position in other modals or not can be inquired, the diagnostic logic of field experts is simulated, different physical phenomena can be associated, and the probability of mutual verification is reduced. Therefore, early-stage or composite defects which are extremely difficult to find in any single mode can be accurately identified. Therefore, the problem that the recognition performance is reduced due to environmental interference such as illumination and shadow can be fundamentally solved.

The invention relates to the technical field of video recognition, in particular to a construction safety real-time high-precision detection method and system based on environmental characteristics. Arranging a plurality of sensors in a to-be-detected area to collect field environment data in real time; analyzing the illumination change of the to-be-detected area through the light and shadow analysis model, calculating a light-safety misjudgment index, and identifying a potential light misjudgment area; a visual processing model is utilized to analyze the worker video, human skeleton key points are recognized in real time, personnel behavior safety indexes are obtained, and potential dangerous behaviors are detected; detecting local wind speed and turbulence conditions and vibration and resonance phenomena of a to-be-detected area in real time through a local breeze and vibration detection model, and evaluating a local environment stability index; and the safety level of the to-be-detected area is calculated in real time by using the light-safety misjudgment index, the personnel behavior safety index and the local environment stability index, so that multi-dimensional and real-time construction safety risk assessment is realized.

The invention relates to the technical field of circuit breaker switch monitoring, and provides a method for monitoring the position state of a circuit breaker switch based on a video recognition technology, and the method comprises the steps: collecting a real-time image of a circuit breaker through a camera device, judging the physical state of the circuit breaker, and determining a first judgment result; acquiring real-time data of the relay protection device, recording the operation state of the circuit breaker, and determining a second judgment result; inputting the first judgment result and the second judgment result into a preset signal response device to generate a corresponding response action; wherein the response action comprises an opening action, a fault action and a closing action.

The invention relates to the technical field of video recognition and analysis, and discloses a video recognition and analysis method based on physical characteristics. Video frame pixels are mapped to a two-dimensional coordinate system with the upper left corner as an original point, and mirror image expansion and median filtering are carried out on a gray level image; constructing a binary image based on a gray threshold value, and analyzing and extracting a target region by using a four-neighborhood connected domain; using neighborhood search and polar angle sorting to close the tracking contour, and generating equidistant re-sampling points based on Euclidean distance and an interpolation method; the curvature of the re-sampling points is estimated through a three-point difference algorithm, and zero denominator is avoided through numerical protection; performing discrete Fourier transform on the curvature sequence to extract a frequency spectrum, and normalizing an amplitude to form a standardized feature vector; and finally, inter-frame similarity is calculated based on the feature vector, and the most similar frame is automatically retrieved. By processing unified data standards in stages, edge noise is suppressed, sampling uniformity is ensured, and feature stability and cross-frame comparability are improved.

The invention discloses an encrypted video identification method in a Tor environment. The method comprises the four steps of collecting flow, extracting an AU-burst length sequence, extracting upstream features and classifying downstream tasks. Firstly, real-time Tor traffic is captured at a network information service center of a local area network entrance, then features are extracted from the real-time Tor traffic by using a corresponding TREFS i T segmentation strategy according to Tor video traffic characteristics to obtain an encrypted ADU-burst length sequence, then noise filtering and secondary feature extraction are performed by using a 1DCNN model, and finally classification is performed by using a random forest. According to the method for identifying the encrypted video in the Tor complex environment, the encrypted video does not need to be decrypted, the video played by the client through the Tor network can be identified through the video traffic characteristics so as to supervise harmful videos, and the method has wide application scenes and good supervision effects.

The invention relates to the field of image or video recognition, in particular to a local learnable query enhancement video recognition method, which comprises the following steps of: establishing a frame for adding video space-time modeling and migrating to a video task on the basis of an image large model; constructing a video behavior recognition model in the framework; constructing a training mechanism of large model main branch freezing and only new parameter learning, training a video behavior recognition model by using a server, and optimizing an objective function until network convergence to obtain a trained video behavior recognition model; and inputting a video sequence to be recognized into the trained video behavior recognition model to recognize human behaviors. The method has the beneficial effects that a video behavior recognition task can be quickly and efficiently migrated by only adding a small number of learnable parameters on the basis of an image model, human behaviors in a video can be recognized with high precision, and the method has high robustness and effectiveness in the aspect of processing action related details.

An analytical recognition system includes a video camera configured to capture video data of a subject and an antenna configured to capture mobile communication device data relating to the subject's mobile device. The system further includes a data analytics module configured to: analyze the video data to determine one of a physical attribute or a movement attribute of the subject and generate a first certainty match value based on this attribute perform facial recognition analysis of the subject to obtain facial recognition data and generate a second certainty match value based on the facial recognition data; generate a third certainty match value based on the mobile device data; and combine the first, second, and third certainty match values to produce a combined certainty match value, which enhances the accuracy of identifying the subject by integrating multiple data sources, including physical attributes, facial features, and mobile device information.

A system and method for training, assessing, and providing feedback on cardiopulmonary resuscitation (CPR) performance based on at least one video of a CPR training session performed by a trainee on a non-mannequin training object. A preprocessing module is configured to process the at least one video to generate a standardized video. A marking module is configured to use pose estimation to mark points for body movements during the CPR training session based on the standardized video, and a computing module configured to compute body movement parameters for CPR based on the marked points. A classification module implements a machine learning model that classifies CPR compressions on the non-mannequin training object based on the computed body movement parameters, thereby generating compression classifications, wherein the machine learning model is trained to extract CPR-specific features. An editor module maps metrics over the standardized video based on the compression classifications and generates a feedback video based on the mapped metrics. An analysis module identifies deviations from CPR guidelines based on the feedback video and generates analysis results based on the deviations. A feedback module provides performance feedback to the trainee based on the analysis results.

The invention discloses a personnel state monitoring method and system based on a YOLO algorithm, and belongs to the field of image or video recognition. According to the method, a real-time image or video stream is acquired through a camera, human body detection and key point positioning are performed by using an optimized YOLO algorithm, and a motion model is established in combination with human body posture estimation so as to judge the state of a person. According to the optimization algorithm, a CBAM attention mechanism and a multi-scale feature fusion technology are introduced, and the detection precision and robustness in a complex scene are improved. The system supports correction of personnel key point information, and noise is eliminated through historical frame data and a prediction model. For abnormal behaviors, such as falling or illegal intrusion, the system can generate an alarm signal by comparing an action model with a normal behavior sample library and notify a management terminal. According to the invention, efficient and real-time monitoring of the state of the personnel in the natural gas station is realized, and the safety management level is effectively improved.

The invention relates to the technical field of image feature extraction, in particular to a cross-camera multi-vehicle tracking method, system and equipment, and the method comprises the steps: obtaining videos of a plurality of cameras, recognizing a target vehicle in each frame of image in the videos, outputting the basic information of the target vehicle, and distributing an image token, a category token and a partial token for the images; the historical features of each part token form a fusion feature; adding the global features to generate combined features; constructing historical track characteristics of the target vehicle before the current frame, and converting the historical track characteristics into a time token through linear transformation; reasoning according to the time token to generate a prediction track of the current frame of the target vehicle, and further reasoning to obtain a complete track; and clustering the complete tracks of the target vehicle of the plurality of cameras to complete cross-camera vehicle tracking. According to the method, the problems of difficulty in cross-camera matching, shielding, motion blur, track repair and vehicle re-identification precision of vehicle tracking in a multi-camera scene can be solved.

The invention relates to the technical field of image processing, and discloses a sorting video recognition processing method and system based on YOLO. The method comprises the steps of processing mask data by adopting a YOLO-Inpaint algorithm, embedding image restoration loss calculation in a YOLO network, and inferring a mapping relation of complete article features from incomplete features through adversarial training learning to obtain a restoration feature graph. And calculating an article integrity score based on the repair feature map, and integrating the ratio of the visible pixel area to the predicted total area and the similarity of the repair area and the real area. And the integrity score and the detection confidence coefficient are fused according to the adaptive weight of the shielding degree, and a compensated recognition result is generated. And constructing a time-sequence-labeled identification data stream which comprises an article category, a position coordinate, a shielding state and a confidence coefficient, and outputting a processing report. According to the method, the problems of accuracy and robustness of object shielding recognition in the sorting video are solved, and the recognition success rate and the processing efficiency under the shielding condition are improved.

The invention discloses a video recognition method based on dynamic space-time full-scale feature fusion, which comprises the following steps: a video data set used for training a deep neural network model is acquired, the video data set comprises a plurality of video sequences, and each video sequence is composed of a plurality of time frames; training a pre-defined video recognition deep neural network model by using the video data set, wherein the video recognition deep neural network model comprises a parallel space-time adapter and a self-prompt generator; and applying the trained video recognition deep neural network model to a video recognition task, inputting a to-be-recognized video sequence, and outputting a classification prediction result of the video. The method has the advantages that through cooperative work of the parallel space-time adapter and the self-prompt generator, efficient modeling of dynamic changes in the video is achieved, the accuracy and robustness of video recognition are remarkably improved, and the method is suitable for various video recognition tasks such as supervised learning, few-sample learning and zero-sample recognition.

The invention discloses an agricultural greenhouse water and fertilizer management system and method based on video recognition, and relates to the technical field of computer image recognition, and the system comprises a camera which is used for collecting crop images; the environment sensor is used for collecting water and fertilizer environment data of the agricultural greenhouse; the local host is provided with a crop identification model, and the crop identification model is used for identifying the real-time growth state of crops in the crop image; the cloud server is deployed with a growth decision model and a growth regulation model, the growth decision model formulates a growth control strategy according to the types and growth stages of crops in the agricultural greenhouse and the water and fertilizer environment data, the growth regulation model calculates an income value, and a regulation scheme for the growth control strategy is solved by taking the maximum income value as a target; and forming an adjusted growth control strategy. According to the method, the growth state of the crops is considered on the whole instead of achieving the optimal state of some crops, and the benefit of the agricultural greenhouse is improved.

The invention relates to the technical field of image or video recognition or understanding, and discloses a bus driver driving state evaluation method, which comprises the following steps: acquiring a face image, an electrocardiosignal and voice audio data of a bus driver, performing timestamp alignment and preprocessing, and constructing a multi-mode driving state data set; extracting multi-modal features of the collected data, and mapping the multi-modal features to a unified feature space; fusing multi-modal features through a cross-modal attention mechanism, dynamically adjusting attention weight based on an emotional change difficulty index, and extracting emotional change key features; and predicting a two-dimensional continuous emotion value of the driver by using the fusion features, calculating a long-time-sequence emotion driving risk score based on an emotion stimulation dynamic model, and performing evaluation and early warning of a driving state. The problems of single-mode analysis, lack of long-period early warning and driving state static recognition in the prior art are solved, and the purposes of accurate evaluation, high safety, multi-mode fusion and long-time-sequence prediction are achieved.

The invention discloses a berth positioning system and method based on video recognition, and relates to the technical field of intelligent transportation, and the system comprises a calibration module which generates berth calibration data based on a berth type, and stores the data to a cloud server; the edge calculation service module is configured to judge the spatial relationship between the vehicle and the berth through a berth type adaptive algorithm based on the real-time latitude and longitude coordinates of the inspection vehicle and the berth calibration data; and the vehicle identification module records license plate information when determining that the vehicle is in the berth, and actively snapshots an empty berth image when no vehicle is in the berth and uploads the empty berth image to the cloud. According to the scheme of the invention, the accuracy, environmental adaptability and long-term operation stability of parking state recognition can be remarkably improved, and a comprehensive solution with high robustness and low misjudgment rate is provided for urban intelligent parking management.

The invention provides a spinach cleaning quality detection method based on image recognition, and relates to the technical field of image or video recognition. A closed-loop control framework integrating active detection, cross-modal sensing, physical modeling decoupling and intelligent decision optimization is constructed; cleaning efficiency and quality bottlenecks caused by single information dimension and passive control mode in the prior art are fundamentally solved; the self-adaptive cleaning device has the final beneficial effects that the energy consumption and the water consumption of a unit product are greatly reduced by precisely putting water flow energy according to requirements while the cleaning cleanliness stability under complex working conditions is remarkably improved, and self-adaption and self-optimization of the whole cleaning process are realized.

The invention discloses a large video model training method and a related device, and relates to the technical field of video recognition, and the method comprises the steps: collecting a training video data frame to obtain an image frame, inputting a preset prompt word, a user question and the image frame into a large image model, and obtaining a thinking chain and a question answer. Performing cold start on the video large model based on the thinking chain and the question answer to enable the video large model to have thinking chain output capability; and combining training video data and questions to generate space and time disordered data and thinking chain data. And inputting the three types of data into the model to obtain corresponding outputs, calculating the accuracy of each output, obtaining space and time accuracy reward values, and training the model through a group relative strategy optimization algorithm in combination with a thinking chain consistency reward value to obtain an inference video large model. According to the method, the trained video large model can have thinking reasoning capability based on thinking chain implementation.