373 results about "Image flow" patented technology

The invention relates to the technical field of security and protection management, in particular to a campus security and protection management system based on deep learning, which improves the accuracy and robustness of identity recognition by acquiring access control card numbers, face images or fingerprint features and generating standardized identity authentication data. And on the basis of a comparison result of the identity authentication data and the campus database, a behavior chain initialization identifier is generated, and accurate identity binding of the school entering personnel is realized. Furthermore, by collecting multi-camera image stream data, pedestrian re-identification and similarity calculation are executed by using a deep feature matching network, and a cross-camera continuous trajectory data set is generated. And matching the behavior track data set with the conventional path template to generate a behavior offset feature vector. And carrying out joint modeling on the behavior offset characteristics and the identity information through a graph neural network model containing an attention mechanism, and outputting a behavior purpose label and a risk grade score. And a graded security response instruction is generated based on the risk score, so that the missing report rate and the false report rate are effectively reduced.

Embodiments of the present disclosure provide techniques for performing virtual object placement in a video sequence using generative artificial intelligence models. An example method generally includes receiving an input prompt specifying an object to insert into a scene depicted in an input image stream; decoding, using a generative artificial intelligence model, perspective and lighting information for the input image stream; determining, based on the decoded perspective and lighting information, a location in the scene in which the object is to be inserted; and generating, using the generative artificial intelligence model, an output image stream including the object into the scene at the determined location, wherein visual effects for the object are based on the perspective and lighting information for the input image stream.

The invention relates to the technical field of intelligent medical teaching, and discloses a medical intelligent teaching model construction method based on an ultrasonic AI technology. According to the method, ultrasonic image sequence data and corresponding operation records of a target object are integrated to generate an original teaching data set; carrying out multi-dimensional teaching feature analysis on the dynamic teaching feature parameter set, and extracting a dynamic teaching feature parameter set; constructing an anatomical structure evolution feature tensor according to a time evolution rule of the parameter set, and calculating knowledge density distribution of historical typical cases; setting a teaching anomaly discrimination boundary and generating an anomaly feature index set; capturing ultrasonic image flow and operation behavior data in teaching operation in real time, mapping the ultrasonic image flow and operation behavior data to a multi-scale teaching knowledge space, and calculating spatial distribution similarity with the abnormal feature index set to obtain a real-time teaching deviation coefficient; and constructing a teaching risk prediction network model, and generating a teaching operation quality evaluation result and a teaching strategy adjustment scheme.

The invention relates to the technical field of unmanned aerial vehicle intelligent inspection path planning, and discloses an unmanned aerial vehicle intelligent inspection path planning method and system based on visual inspection, and the method comprises the steps: collecting an image, and carrying out the differential superposition processing, and obtaining environment visual data; feature correction is extracted to determine a candidate area, and a template is matched to determine the type and severity of an abnormal event; performing local path planning according to an event generation mode switching instruction; according to the trajectory parameters meeting the minimum turning radius constraint, a safe fly-around path is obtained; the method comprises the following steps of: acquiring a real-time image stream, adjusting a speed parameter to obtain an optimized trajectory, processing the real-time image stream and inertial measurement data generated in the optimized trajectory through a visual inertial odometer technology to obtain environment three-dimensional point cloud data, and performing cyclic verification according to the environment three-dimensional point cloud data to obtain an event processing verification result. According to the invention, hierarchical response and dynamic local path re-planning of abnormal events can be realized.

The invention discloses a power grid intelligent inspection method and system based on an unmanned aerial vehicle, and the method comprises the following steps: collecting image flow data of a target region, constructing a three-dimensional point cloud model, and generating an initial inspection path based on a fast marching tree method in combination with spatial position information; controlling the unmanned aerial vehicle to fly according to a path and collect image frames in real time, and executing an optical flow estimation algorithm through an edge calculation chip to obtain a pixel motion vector; associating the motion vector with a space coordinate corresponding to each inspection point in the inspection path, dividing an optical flow detection area and distributing an initial detection weight; recognizing a dynamic abnormal area according to the motion features, extracting image data and space coordinates, and driving an acousto-optic load assembly carried by the unmanned aerial vehicle to respond; and based on the space coordinates of the abnormal region, re-executing the fast marching tree method to generate a local update path, and adjusting the detection weight of the related region. According to the invention, dynamic sensing and path updating linkage in the unmanned aerial vehicle inspection process can be realized.

The invention discloses a real-time pose updating method based on feature prediction and point cloud registration, and belongs to the technical field of image registration, and the method comprises the steps: extracting a bone surface point cloud which at least covers a feature region and an adjacent region from a three-dimensional model of a bone tissue of a patient, the point cloud is used as a target point cloud for registration with a real-time ultrasonic image; an ultrasonic image collected by the ultrasonic patch in real time is obtained, and a two-dimensional ultrasonic image with a spatial position is obtained; predicting the two-dimensional ultrasonic image by using a pre-trained artificial intelligence model to obtain bone-soft tissue interface features, and extracting a plurality of points on a bone-soft tissue interface from the bone-soft tissue interface to form a source point cloud for registration; and registering the source point cloud to the target point cloud to realize real-time pose updating. According to the invention, the pose monitoring in the operation can be realized through the real-time image flow under the non-invasive condition.

The invention provides a multi-head gun-type camera multi-angle intelligent tracking method and system, and the method comprises the steps: obtaining image flow data through a multi-head gun-type camera, building a D-NeRF model through combining with an improved multi-layer perception mechanism, outputting a virtual viewpoint image, a scene depth image, a shielding relation image and a motion vector field according to the D-NeRF model, obtaining a volume density field, and carrying out the multi-head gun-type camera multi-angle intelligent tracking. Analyzing the volume density field, acquiring a continuous aggregation area and performing cutting operation, generating a target instance, acquiring a bounding box and a centroid coordinate in combination with a scene depth map, acquiring appearance characteristics and morphological characteristics and performing matching, generating an identity recognition result, performing trajectory prediction through physical constraint, generating a probability space-time trajectory and performing evaluation, and performing identification on the probability space-time trajectory. According to the method, the uncertain area is obtained, the motion of the camera is subjected to joint optimization in combination with the probability space-time trajectory, the intelligent control instruction is generated, and multi-angle intelligent tracking is performed according to the intelligent control instruction, so that the intelligent level of multi-camera monitoring and tracking in a complex scene is improved.

The invention relates to the technical field of construction safety management, and discloses a construction safety penetration type management multistage linkage early warning system. The system comprises a management layer node, an execution layer node and a job layer node. The management layer generates a global security strategy, the execution layer is used for decomposing task issuing, and the operation layer is used for collecting field multi-mode security data including equipment vibration characteristics, environment image flow, personnel positioning tracks and security operation records. The system firstly analyzes equipment vibration characteristic changes, divides stable and abnormal working condition time periods, and screens high-risk areas according to difference quantities; in each high-risk area, calculating a safety state deviation degree of a job layer node in combination with the task identifier and the environment image flow; a responsibility tracing weight is generated according to the time-space relevance and the deviation degree of the personnel track and the operation record in the abnormal time period; and finally, screening root nodes, associating multi-modal data to construct a security risk propagation tree, and realizing accurate security management of multi-level linkage.

The invention relates to a multi-view three-dimensional human body posture estimation method and system based on double-flow space-view-time sequence modeling. The method comprises the following steps: inputting a multi-view multi-frame image sequence, and performing human body detection and cutting; performing two-dimensional human body posture estimation on the input image at each view angle and each frame, and extracting image features; constructing an image-attitude bimodal alignment expression; sequentially executing sequential modeling of intra-visual space interaction, cross-visual-angle interaction and intra-visual time interaction on the image flow representation and the attitude flow representation in the same layer to obtain attitude flow fusion features; performing regression on the attitude flow fusion features by using a three-dimensional regression head to obtain three-dimensional skeleton coordinates; training the three-dimensional skeleton by adopting supervised learning; and inputting a to-be-estimated image sequence into the trained model and the regression head to obtain a three-dimensional human body posture estimation result. According to the method, the precision, robustness and deployability of three-dimensional attitude reconstruction can be remarkably improved under the condition of not depending on camera calibration parameters and human body priori.

The invention discloses a digital dangerous cargo transportation supervision system and method, belongs to the technical field of vehicle supervision, and aims to solve the problems that in digital dangerous cargo transportation, loading and unloading links are insufficient in authenticity verification, abnormal fluctuation in the transportation process is difficult to recognize in real time, and abnormal handling response is delayed. After a dangerous cargo transportation electronic waybill is obtained, loading and unloading scene verification is completed by delimiting a compliance area, shooting an initial scene image and dynamically constructing an image flow sequence, and a carrying password is generated for cargo encryption storage and unloading unlocking; a passing route is segmented, a vehicle operation base line is established based on historical data, data delay and loss are distinguished by monitoring the conformity and transmission interval of transportation data and the base line, abnormal fluctuation is recognized, and early warning is triggered; and during early warning, a target verification position is selected based on positioning, and the vehicle is guided to the verification area to complete abnormity verification. And cheating behaviors in loading and unloading links are avoided, transportation risks are identified, abnormities are quickly handled, and dangerous cargo transportation safety and supervision efficiency are effectively improved.

The invention discloses a tunnel face geological information acquisition and image processing method based on machine vision, which belongs to the technical field of image processing, and comprises the following steps: resolving the pose of a terminal in real time through a visual inertial odometer, generating augmented reality guide information, and guiding the terminal to move to a standard acquisition point; at each acquisition point, performing multi-stage verification of scene semantic compliance, motion blur and defocus and illumination uniformity on the image flow to ensure the acquisition quality; for tunnel high-dynamic illumination, adopting an adaptive brightness segmentation and multi-resolution fusion technology based on an improved Otsu algorithm to perform high-dynamic range reconstruction on a single-frame image so as to recover details; and finally, performing clustering optimization based on the feature matching similarity, and screening out an optimal image subset for three-dimensional reconstruction. According to the method, the problems of subjective and random acquisition process, many image quality defects, detail loss under extreme illumination and large image data redundancy are solved.

The invention provides a vehicle target tracking method and system based on natural language anaphora, and the method comprises the steps: inputting a standardized image data stream and key semantic information into a semantic anaphora initialization module, and outputting a target mask through cross-modal feature extraction, deep fusion and semantic consistency verification; the target mask is input into a full-time-history identity maintenance system of language enhancement and memory driving, and short-time identity maintenance and long-time recovery mechanisms are fused to ensure identity consistency and track integrity; inputting the multi-view-angle original image flow into a cross-view-angle semantic unification layer, and providing a unified semantic representation basis; and inputting the multi-view-angle image data after unified semantic representation and processing, all target information and long-term recovery target information into a cross-view-angle semantic unified association module, solving semantic mapping differences under different view angles through coordinate system conversion and semantic direction standardization, and realizing accurate association and track fusion of cross-view-angle targets. The method can track the vehicle target.

Systems and methods for detecting artificial intelligence generated images are provided. The system accepts an input image (e.g., a digital still image, or a frame from a digital video file or image stream) and subdivides the input image into a set of patches using a patch partitioning algorithm. The system then processes each patch and produces a feature embedding for each patch within a high dimension space. The system then utilizes these patches with further processing as input to machine learning models, which allows the system to achieve image, patch-level, and video-frame generated image classification and localization alongside identification of the generative model used to synthesize the image.

The invention relates to an impregnated paper production quality detection method and system based on deep learning, and the method comprises the following steps: S1, obtaining an industrial camera image flow, sensor and process parameters, and event and work order information, and constructing a synchronous data packet; s2, preprocessing the synchronous data packet to obtain preprocessed image data, process data and an ROI mask; s3, obtaining a detection frame set and a segmentation mask set based on multi-model AI detection and segmentation according to the preprocessed image data, the process data and the ROI mask; s4, segmenting the mask set according to the detection frame set, and performing track clustering along the paper feeding direction to form a defect event flow; s5, on the basis of the defect event stream, performing online quality prediction and root cause analysis, and obtaining future interval quality prediction and key factor sorting; and S6, according to future interval quality prediction and key factor sorting, adaptive process optimization is carried out, and an optimal control instruction is obtained. According to the invention, the detection accuracy and fineness are effectively improved, and intelligent identification and cross-frame tracking of defects are realized.

An electronic device is provided. The electronic device includes a display, an image sensor, an image signal processor for processing frames transmitted from the image sensor, a scaler arranged between an output end of an image pipeline and an input end of the display, memory, comprising one or more storage media, storing instructions, one or more processors operatively connected to the display, the image sensor, the image signal processor, the scaler, and the memory, wherein the instructions, when executed by the one or more processors individually or collectively, cause the electronic device to acquire, from the image sensor, a first frame of a first zoom magnification, control that a second frame to Nth frames are image-processed at the first zoom magnification through the image signal processor while the first frame of the first zoom magnification processed through the image signal processor is output to the display, receive a user input for requesting the display of a second zoom magnification, which differs from the first zoom magnification at the time of N+1 frame acquisition, request the image signal processor to process the N+1 frame, set to transmit, to the scaler, a second zoom magnification request at the time of N+1 frame acquisition, and allow the scaler to scale, in a second frame output order, at the second zoom magnification requested at the time of N+1 frame acquisition, a second frame processed at the first zoom magnification in the image signal processor so as to transmit same to the display.

The invention belongs to the technical field of intelligent patrol of substations, and particularly relates to a positive and negative sample collaborative patrol method and system based on time sequence state evolution analysis. The objective of the invention is to solve the problems of high state jump misjudgment rate, high slow change fault omission rate and poor environmental adaptability caused by independent operation of positive and negative sample algorithms and lack of time sequence state evolution analysis in an existing substation intelligent patrol system. According to the main scheme, the method comprises the steps that firstly, a system obtains and preprocesses equipment image flow and historical data, and a standardized time sequence set containing timestamps, state tags and change vectors is constructed; recent data is aggregated for each equipment state to form a time sequence state chain, and operation logic is embedded to identify illegal hopping; then, through a double-stage cooperation mechanism, a preliminary screening stage inhibits low-confidence-coefficient false alarm, and a trend stage fits a slowly-varying slope to trigger early warning; and finally, dynamically weighting and fusing positive and negative sample outputs according to environmental parameters, and generating a credible score and making a decision. The method is suitable for intelligent operation and maintenance scenes under complex working conditions.

The invention relates to the technical field of augmented reality, in particular to a 24-solar-term astronomical space-time presentation method and system based on mixed reality. The method comprises the following steps: firstly, reading augmented reality scene initialization data, configuring virtual scene parameters, and executing three-dimensional scene registration to generate a registration matrix; executing visual tracking by collecting an image stream, and generating a viewpoint transformation matrix; the system performs real-time sky semantic segmentation on an image stream to generate a binarized sky mask, and constructs an augmented reality rendering pipeline: synthesizing registration and viewpoint matrix calculation rendering operators, using the sky mask as an Alpha mask to perform pixel-level fusion of a virtual starry sky and a real sky, and combining sparse point clouds to perform depth occlusion synthesis, so as to obtain an augmented reality rendering pipeline. An atmospheric optical coloring model and a dynamic volume particle system are loaded for environmental atmosphere enhancement; and optical consistency fusion of a virtual image and a real environment is further realized through HDR luminosity alignment and tone mapping, and finally high-fidelity augmented reality superposition is realized.

A mobile device is capable of being carried by a user and directed at a target object. The mobile device may implement a system to dimension the target object. The system, by way of the mobile device, may image the target object to and receive a 3D image stream, including one or more frames. Each frame may include a plurality of points, where each point has an associated depth value. Based on the depth value of the plurality of points, the system, by way of the mobile device, may determine one or more dimensions of the target object.

A mobile device is capable of being carried by a user and directed at a target object. The mobile device may implement a system to dimension the target object. The system, by way of the mobile device, may image the target object to and receive a 3D image stream, including one or more frames. Each frame may include a plurality of points, where each point has an associated depth value. Based on the depth value of the plurality of points, the system, by way of the mobile device, may determine one or more dimensions of the target object.

The invention discloses a student physical health dynamic monitoring system based on deep learning. Student eye image data passing a quality threshold is used as qualified student eye image data; cutting according to the face key point positioning result to obtain student eye image data of the interested areas of the eyes and the sub-orbital area; generating CLAHE enhanced student eye image data; extracting an original image stream student eye feature map and a CLAHE enhanced stream student eye feature map; obtaining a fused student eye feature map; outputting a student eye fatigue area pixel-level mask map and a student eye fatigue area pixel-level confidence coefficient heat map; and generating a student eye fatigue sub-item index result, and outputting a student individualized eye fatigue index. According to the invention, large-scale, non-contact and fine-grained physical health monitoring for student groups is realized, and the refinement and traceability of health intervention are improved.

An intravascular therapy guidance system includes a processor circuit in communication with an extravascular imaging device. The processor circuit receives, from the extravascular imaging device, an extravascular image stream. The processor circuit determines a therapy region of a blood vessel in the extravascular image stream and outputs a screen display to a display in communication with processor circuit. The screen display includes the extravascular image stream of the blood vessel including movement of an intravascular therapy device within the blood vessel to deliver an intravascular therapy to the therapy region and a graphical representation of the therapy region overlaid on the extravascular image stream. The processor circuit determines, based on the extravascular image stream, whether the intravascular therapy device is aligned relative to the therapy region to deliver the intravascular therapy and modifies the screen display to indicate whether the intravascular therapy device is aligned to deliver the intravascular therapy.

It is provided a people detector (1) for detecting when people pass through a doorway. The people detector (1) comprises: a first image source (11); a second image source (12): a processor (60); and a memory (64) storing instructions (67) that, when executed by the processor, cause the people detector (1) to: receive a first stream of images from the first image source (11); determine, based on the first stream of images, a confidence indicator that a single person passes through the doorway; when the confidence indicator indicates confidence, determine that a single person has passed through the doorway; and when the confidence indicator indicates non-confidence, receive a second stream of images from the second image source (12), and determine, based on the second stream of images, how many people has passed through the doorway.

The application discloses a kind of digital dangerous goods transport supervision system and method, belong to vehicle supervision technical field, to solve the authenticity of digital dangerous goods transport in loading and unloading link is insufficient, transport process abnormal fluctuation is difficult real-time identification and abnormal disposal response lag problem.After obtaining dangerous goods transport electronic transport note, by demarcating compliance area, shooting initial scene image, dynamic construction image flow sequence is completed loading and unloading scene verification, generates carrying password for goods encryption storage and unloading unlocking;To the section of route, establish vehicle operation baseline based on historical data, by monitoring the compliance of transport data and baseline and transmission interval, distinguish data delay and loss and identify abnormal fluctuation, trigger early warning;In early warning, based on positioning selection target check position, guide vehicle to check area to complete abnormal check.Eliminate the cheating behavior of loading and unloading link, identify transport risk and dispose abnormality quickly, effectively improve dangerous goods transport safety and supervision efficiency.

The invention discloses a multi-rotor unmanned aerial vehicle target guidance method and device combined with visual detection, and relates to the field of guidance. The method comprises the following steps: receiving target initial information sent by a superior system; analyzing the target initial information, generating a preliminary target waypoint, and controlling the multi-rotor unmanned aerial vehicle to autonomously fly to a preset target airspace where the preliminary target waypoint is located; in a preset target airspace, driving the multi-rotor unmanned aerial vehicle and the airborne holder to execute a composite search action, and collecting a real-time image stream by using an airborne visual camera; establishing a stable tracking state; in a stable tracking state, continuously tracking the aerial target through a target tracking algorithm, and generating three-dimensional relative position and motion state data of the aerial target relative to the multi-rotor unmanned aerial vehicle in real time; and determining an interception route and judging whether a preset interception condition is met or not, and if yes, sending an execution instruction to the airborne physical strike load. By implementing the technical scheme provided by the invention, the cost of the low-altitude target guidance method is reduced.

The invention discloses a real-time obstacle sensing method for a sonar image, and relates to the technical field of sonar image processing, and the method comprises the following steps: collecting a time sequence sonar image flow of a target water area, carrying out the inter-frame alignment processing of the time sequence sonar image flow, and screening out an effective sonar image with a signal-to-noise ratio meeting a preset threshold value; a suspected obstacle area in the effective sonar image is extracted, and morphological features, gray level distribution features and texture features of the suspected obstacle area are obtained to form a suspected feature database; and performing similarity matching on standard features in the suspected feature database and the obstacle feature database to obtain a feature matching degree, so as to intuitively present the position, the type and the movement track of the obstacle by constructing an obstacle real-time distribution map under a three-dimensional coordinate system, and integrate a safety distance early warning mechanism, thereby improving the safety of the obstacle. And timely and comprehensive obstacle information support can be provided for underwater operation or navigation, and the operation safety and efficiency are ensured.

The invention discloses a new energy station safety inspection management method and system, and relates to the field of inspection management, firstly, an airborne Bayesian network model is introduced, uncertainty reasoning is performed on real-time image flow, and a visual uncertainty map is generated, so that the system can go deep from what judgment to where uncertain quantitative perception. Furthermore, a blind detailed investigation strategy is abandoned, the optimal detailed investigation viewpoint capable of obtaining the highest-quality diagnosis information is autonomously decided by evaluating expected information gains of different candidate viewpoints based on the uncertainty map, and the problem that viewpoint value evaluation is missing is solved. And finally, through dynamic trajectory generation and adaptive camera parameter adjustment, a sensing-decision-planning-action closed-loop intelligent inspection system is constructed, an execution barrier between a traditional flight platform and an intelligent load is broken, the problems of slow response and rigid decision of the system are solved, and autonomous and accurate detailed inspection in a real sense is realized.

The embodiment of the invention discloses a safety monitoring method for vehicle unloading and a related device, and the method is applied to edge node equipment, and comprises the steps: collecting an image flow of unloading work of a monitoring object in a target monitoring region through an image sensor; determining target information of a monitoring object of a single-frame image in the image stream; according to the target information and a preset safety rule, the safety state of a single-frame image in the image flow is evaluated, the safety state is associated with a safety monitoring event, and the safety monitoring event comprises the personnel safety helmet wearing state, the driving state of the unloading vehicle, the unloading frame state of the unloading vehicle and the personnel space position; and if the number of continuous images of which the security states do not conform to the preset security rule in the image stream is greater than a preset frame number, generating an alarm record and triggering an alarm operation. Therefore, through real-time analysis of the image, all-directional and real-time dynamic monitoring can be realized, the monitoring accuracy and reliability are improved, meanwhile, the manual dependence is reduced, and the safety monitoring efficiency of unloading operation is improved.

A gaming system comprising at least one transparent display where at least two gamers are standing on opposite sides of the display. The first gamer is wearing a first pair of filtering glasses that limit the first gamer to seeing only a first stream A of images comprising video being emitted by the transparent display. The second gamer is wearing a second pair of filtering glasses that limit the second gamer to seeing only a second stream B of images comprising the emitted video. Each gamer perceives different augmentations of the opposing player as the game is operated causing the video comprising the A and B streams. The system further comprises an additional display functioning like the first display but separated to form an interior corridor, where a projector is running on rails within the corridor to create a movable ghost image via a pepper's mill apparatus.

The invention discloses a surface damage positioning method suitable for an ultrahigh-strength concrete wind power mixing tower. The surface damage positioning method comprises the steps that benchmark identification pieces containing radio frequency chips and visual recognition patterns are annularly arranged at the preset height of a tower at intervals; the inspection equipment carries a millimeter wave radar, a binocular vision camera and a radio frequency identification module to spirally cruise along the tower drum, and synchronously obtains initial coordinates, real-time image streams and radar reflection signals; correcting the image flow and extracting features, establishing pixel and physical space mapping in combination with the size of the reference identifier, and generating an initial three-dimensional grid model; radar signals are analyzed, mutation feature points are extracted, and a suspected damage area is preliminarily positioned in combination with a three-dimensional grid; controlling equipment to perform fixed-point shooting, extracting damage contour features and calculating actual geometric parameters; the parameters and the physical coordinates are imported into a cylindrical coordinate system conversion model, the damage height, the circumferential angle and the distance between the damage height and the nearest reference identification piece are output, and accurate positioning is achieved; and reliable data support is provided for operation and maintenance of the wind power mixed tower.

An example method comprises: capturing one or more images of a real-world scene, the scene including an assembly; identifying the assembly using an optical fiducial corresponding to the assembly imaged in at least one of the captured images of the scene; retrieving, from a context repository, data associated with the assembly, the data including a virtual model of the assembly and one or more known processes associated with the assembly; selecting a selected known process from the one or more known processes; displaying an image feed representing the scene and the model of the assembly overlaid over the scene; and outputted one or more instructions corresponding to the selected known process.