503 results about "Image flow" patented technology

The invention relates to the technical field of PCB welding spot defect detection, and discloses a PCB welding spot defect detection system and method based on image recognition, and the system comprises an image preprocessing module which is used for obtaining an original image flow and dividing an interested detection area; the feature fusion module is used for extracting multi-modal features to form a fusion set; the defect judgment module is used for establishing a mapping index and obtaining a judgment result; the parameter calibration module is used for verifying the detection parameters and adjusting the mapping index; and the report output module is used for generating a defect detection report. The method comprises the steps of image preprocessing, feature fusion, defect discrimination, parameter calibration, report generation and the like. According to the system and the method, the PCB welding spot defects can be efficiently and accurately detected, the detection precision and stability are improved, a structured report is generated, and an effective solution is provided for PCB quality detection.

The invention relates to the technical field of electrical equipment defect detection, in particular to an electrical equipment defect detection system and method based on deep learning, which are characterized in that a three-dimensional model of a power grid region is constructed, and based on historical defect data, a neural network model is adopted to mark an importance score of an inspection object in the three-dimensional model; quantitative evaluation of the equipment fault risk level is completed, and the matching degree of inspection resources and defect risk distribution is improved. A power grid three-dimensional model and importance scores are combined, a reinforcement learning model is utilized to construct an unmanned aerial vehicle inspection route planning strategy, the inspection route comprehensively considers power equipment defect risks and space factors in the planning stage, task allocation is optimized, and the problem that a static route cannot adapt to equipment changes is solved. In the inspection execution process, the unmanned aerial vehicle is dispatched according to the planning strategy, and the image flow is synchronously acquired for defect detection, so that the linkage of the inspection action and the detection process is realized, and the response efficiency and the detection quality of potential defects are improved.

The invention relates to the field of image recognition, in particular to a wind power construction intelligent safety management method and system based on intelligent AI monitoring. The method comprises the following steps: obtaining an omnibearing real-time image flow of a wind power construction area, carrying out super-resolution deep convolution optimization and operator three-dimensional image segmentation, and extracting an operator three-dimensional image frame; three-dimensional point cloud modeling of the construction area is carried out based on the image flow, real-time image frame position positioning rendering is carried out according to a three-dimensional image frame, and a real-time twinborn model of the construction area is constructed; performing operation dynamic behavior analysis and behavior deviation degree quantitative analysis based on a twin model to obtain the behavior deviation degree of the operator; and according to the behavior deviation degree, carrying out early prediction analysis on illegal behaviors, making an adaptive risk early warning decision, and constructing an operation behavior risk early warning strategy. According to the invention, through real-time operation behavior identification and environmental risk analysis, the intelligence and safety level of wind power construction are improved.

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.

The invention provides an industrial product defect automatic classification method and system, and the method comprises the steps: collecting original industrial product defect image data, and constructing a labeled image sample set and an unlabeled image sample set; constructing a training image sample set based on the labeled image sample set and the unlabeled image sample set in combination with a plurality of image synthesis strategies; based on the training image sample set, introducing a transfer learning strategy and fusing an attention mechanism, and constructing and optimizing an industrial product defect classification model; performing semi-supervised joint training and online learning based on the training image sample set and the real-time small-batch image sample set; and constructing an industrial product defect identification log based on the real-time image flow sample set, the classification model parameters and the corresponding classification prediction function. On the basis of multi-strategy image enhancement and semi-supervised training, transfer learning and a channel attention mechanism are fused, expansion of industrial product defect image samples and fine defect identification are achieved, and the method is suitable for an intelligent defect detection system in various industrial manufacturing fields.

The invention provides a humanoid machine control method and system based on model prediction, and the method comprises the steps: firstly obtaining joint sensing data (hip joint movement angle sequences and knee joint stress signals) and environment interaction data (depth image flow data and sole contact pressure data) of a humanoid machine, and generating a dynamic state feature set through feature correlation processing; the feature matrix comprises a joint cooperation feature vector and an environment constraint feature matrix; calling a pre-training model to carry out spatio-temporal joint prediction on the feature set, and outputting a future motion control sequence containing gait cycle features; then, a joint synchronous control model is constructed on the basis, and a driving control instruction set containing time coordination constraint is generated; and finally, the driving control instruction set is transmitted to the distributed execution unit, and joint state feedback data is collected for next round of processing, so that the motion control performance of the humanoid machine in a complex environment is improved.

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 relates to the technical field of sports competition real-time penalty, and discloses a sports competition real-time penalty system and method based on multi-modal sensing and AI algorithms, and the system comprises a monitoring identification module, an instrument tracking module, a rule parameter construction module, a fusion penalty module, an output and snapshot module, and a wireless linkage and energy management module. The method comprises the following steps: acquiring image and instrument data, and constructing a multi-modal sensing structure; calling a rule base to generate a penalty vector and loading a structure constraint; fusing the image and the instrument features to generate a feature tensor; inputting an AI model to judge the legality of the action and outputting a penalty result; driving the snapshot logic to generate an image record and synchronizing the image record to the terminal; and adjusting the energy consumption strategy according to the task load and the equipment state. According to the invention, a multi-modal perception input structure fusing instrument motion data and a visual image flow is introduced, so that the system can synchronously acquire displacement, acceleration and attitude images in the action recognition process, and a penalty basis is checked in a cross manner from multiple dimensions.

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 provides an image acquisition control method, device and equipment based on machine vision. The method comprises the following steps: selecting a high-frame-rate image sensor acquisition mode according to environment state parameters; adjusting exposure parameters of the high-frame-rate image sensor according to the selected acquisition mode; fusing the optical flow speed and the brightness of the image flow into a weighting factor according to the exposure parameters, and injecting the weighting factor into an image space to generate a scene partition mask; and the scene partition mask is aligned with the exposure images with different exposure parameters, and the exposure images are fused into a target acquisition image. Through the implementation of the scheme of the invention, the environment state parameters are generated in real time, the corresponding acquisition mode is selected, the exposure parameters are optimized, the optical flow and the brightness data are fused to generate the weighting factor, the scene partition mask is created, the multi-exposure image is aligned through the scene partition mask, the optimal exposure part of each area is accurately fused, and the high-quality target image is obtained. Therefore, the image acquisition efficiency is improved.

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 provides a spine centrum compression fracture recognition method and system based on artificial intelligence, and the method comprises the steps: receiving original spine CT sequence data, and outputting a preprocessed standardized image; inputting the preprocessed image into a three-dimensional U-Net + + network to obtain a centrum segmentation probability graph; outputting the segmented centrum set and the position code thereof; for each segmented centrum, extracting a corresponding area based on a centrum mask, and splicing all features to form a comprehensive feature vector of each centrum; inputting the three-dimensional image block of each vertebral body into an image flow network to extract visual semantic features; and automatically generating a structured PDF report. According to the spine centrum compression fracture recognition method and system based on artificial intelligence, the problem of image quality difference caused by different CT devices and scanning parameters is effectively solved through the multi-scale residual enhancement technology and self-adaptive window level adjustment, and standardized processing of images is achieved.

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.

Devices, systems, and methods for sharing an image sensor data stream with an active alignment subsystem are provided. An example device includes an image sensor coupled to a first processor. The first processor is coupled to a multiplexer and the image sensor. The first processor is configured to receive an image stream from the image sensor, transmit the image stream to a second processor via the multiplexer operating in a first state, and transmit the image stream to at least one test port of the data capture device via the multiplexer operating in a second state. The multiplexer is configured to connect the second processor to the first processor when operating in the first state, and connect the at least one test port to the first processor when operating in the second state. Responsive to receiving an enable signal, the multiplexer operates in the second state, else the first state.

A method for real-time surgical navigation, including: capturing an intraoperative image stream from a distal portion of an endoscopic instrument inserted into a patient's body; processing the intraoperative image stream with a machine learning-based segmentation algorithm configured to identify anatomical structures; matching segmented images to a patient-specific three-dimensional (3D) model of the anatomy; and outputting navigational data indicating the position of the endoscopic instrument relative to the anatomical structures.

The invention provides a canteen catering compliance real-time monitoring system and method based on image recognition. The canteen catering compliance real-time monitoring system comprises a heterogeneous sensor array. Edge computing nodes; the environment self-adaption module is used for solving the recognition problems in complex scenes such as background color interference, day and night illumination fluctuation and steam shielding through HSV histogram similarity analysis and dynamic weight adjustment; a behavior compliance analysis engine; and a real-time feedback execution module. A multi-source sensor clock is synchronized, a unified space-time coordinate system is established, an illumination-infrared weight dynamic mapping and environment feature compensation algorithm is adopted, a visible light image flow, thermodynamic data and depth information are processed in parallel, multi-modal features are fused for composite operation behavior recognition, and a dynamic response instruction is generated according to a predefined compliance strategy library. According to the method, the recognition accuracy in a background color interference scene can be improved, and the night false alarm rate is reduced. According to the invention, the problem of poor adaptability to complex environments in traditional supervision can be effectively solved, and the food safety management level is significantly improved.

The invention discloses an archive document quality evaluation method and an archive document quality evaluation system based on ConvNeXt V2. According to the method, an improved ConvNeXt V2 model is used for carrying out character density classification on a preprocessed archive document image, and probability distribution is output. Meanwhile, the quality evaluation model of the OCR text-image double-branch structure is adopted to evaluate the quality of the image. The OCR text branch uses a ViT model and a transpose attention module to extract visual features and calculate a document stream score; according to the image branch, image features are extracted by using a convolutional neural network and ResNet, global multi-scale features are formed through residual connection, and an image flow score is calculated. And finally, fusing the image flow score and the document flow score through double-flow dynamic weight to obtain an image quality evaluation score. According to the method, the model architecture is improved, and the dynamic weight algorithm is designed, so that the classification and quality evaluation of the archive document image are improved.

A system comprises an image capture device, a processing device, and a display. The image capture device captures a stream of images of a face of a person showing a current dentition of the person and soft facial tissues of the person. The processing device processes the stream of images to generate a modified stream of images showing a modified dentition of the person and modified soft facial tissues of the person associated with the modified dentition. The display displays the modified stream of images.

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 provides an image generation and style migration method and system based on a large model. The method comprises the following steps: acquiring a content graph, a style graph and a slider parameter uploaded by a user, capturing a sliding track to generate an intensity sequence with a timestamp, and dynamically sampling and compressing the intensity sequence into a frequency domain feature vector; analyzing the semantic contour of the content graph and the texture region of the style graph in parallel by using a large model, and matching target texture features after establishing semantic association; and performing progressive weighted fusion on the target features according to the style intensity parameters, finally injecting the frequency domain vector and the fusion features into a model hidden space as a control signal, dynamically adjusting the hidden space iteration depth according to the equipment performance, maintaining the stability of the output frame rate by constraining a noise attenuation path, and generating a continuous stylized preview stream. According to the invention, through dynamic control signal injection and hidden space depth adjustment, a smooth image flow with continuously changed style intensity is generated while the frame rate is ensured to be stable.

The invention discloses a multi-mode bird monitoring method and system based on end-side artificial intelligence, and relates to the technical field of ecological monitoring and artificial intelligence, and the method comprises the steps: collecting bird voiceprint signals and image streams in real time through an edge device disposed at a monitoring node, and carrying out the local preprocessing; utilizing a voiceprint recognition module to extract bird voiceprint features based on the pre-processed bird voiceprint signals; extracting refined bird image features based on the pre-processed bird image flow by using an image recognition module; carrying out fusion and feature classification on the bird voiceprint features and the bird image features by using a multi-modal fusion module, and obtaining bird positioning information in the image by using a machine learning linear regression method; and locally storing the classification result and the bird positioning information or transmitting the classification result and the bird positioning information to a central platform through a low-power-consumption communication protocol. The system solves the problems of high delay and high false drop rate of a traditional monitoring scheme, is suitable for a field environment without network coverage, and has the advantages of low power consumption and high precision.

The invention relates to the technical field of unmanned aerial vehicle image transmission, and particularly provides an unmanned aerial vehicle flight process image transmission method and system, and the method comprises the steps: obtaining electromagnetic environment information, channel state information and unmanned aerial vehicle internal parameter information; generating a comprehensive state index according to the electromagnetic environment information, the channel state information and the internal parameter information of the unmanned aerial vehicle; querying a pre-constructed mapping relation table about state indexes and transmission parameter combinations according to the comprehensive state indexes to obtain a target transmission parameter combination; according to the target transmission parameter combination, coding, packaging, modulating and sending the image acquired by the unmanned aerial vehicle; the method can effectively solve the problems of image jamming, image frame loss, image mosaic or color distortion and the like of the image flow received by the ground station due to interference or enhanced channel attenuation.

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.

Image augmentation effects are provided on a device that includes a display and a camera. A simplified augmented reality effect is applied to a stream of images captured by the camera, to generate a preview stream of images. The preview stream of images is displayed on the display. A second stream of images corresponding to the first stream of images is saved to an initial video file. A full augmented reality effect, corresponding to the simplified augmented reality affect, is then applied to the second stream of images to generate a fully-augmented stream of images, which are saved to a further video file. The further video file can then be played back on the display to show the final, fully augmented reality effect as applied to the stream of images.