951 results about "Temporal information" patented technology

A system and method for multi-scale temporal attention processing in multimodal technology deep learning systems. This system processes time-series, textual, sentiment, and structured tabular data across three hierarchically-organized temporal streams—quarterly, weekly, and intraday levels—with bidirectional cross-temporal information flow. Scale-specific attention mechanisms are optimized for respective temporal granularities, while an adaptive controller dynamically weights each temporal level based on real-time market volatility indicators. A multi-scale fusion processor integrates attention-weighted representations to generate temporally unified representations preserving both short-term market dynamics and long-term trends. This approach enables superior forecasting and risk assessment by leveraging temporal correlations across multiple time scales while automatically adapting to changing market conditions. The system facilitates interpretable AI analysis through attention visualization and enables synthetic scenario generation for model testing.

The invention provides an unmanned cluster brain-like navigation map fusion construction and cooperative positioning method. The method comprises the following steps: acquiring multi-modal perception data, respectively acquiring vision, sound wave and pose information through a binocular camera, a radar and an inertial sensor, simulating a human brain nerve coding mechanism, and generating a pulse sequence and a feature vector in combination with spatio-temporal information; constructing a multi-modal coding unit into a hypergraph node, and based on a dynamic hyperedge connection topological relation, aggregating spatial-temporal characteristics through a heterogeneous hypergraph convolutional network to generate a high-order brain-like semantic map of a single agent; sharing a local brain-like map by multiple agents through distributed communication, detecting geometric and semantic conflicts of an overlapped region, performing space-time alignment based on an anchor point reference, eliminating feature contradictions by utilizing probability distribution matching, and generating a global consistent high-confidence brain-like map; and outputting the optimal position estimation. Through bionic neural coding, heterogeneous hypergraph modeling and multi-agent collaborative optimization, establishment and positioning of a high-order brain-like map in a dynamic unknown environment are realized.

The invention discloses an insurance claim settlement-oriented multi-modal image video evidence analysis method and system. The method comprises the following steps of: acquiring video / image and multi-source data such as metadata, audio, IMU (Inertial Measurement Unit), GPS (Global Positioning System), OBD (On-Board Diagnostic) and the like; calculating content Hash of the video and the audio according to frames, connecting the content Hash with time information in series to form chained Hash, and adding a verification digital signature and a credible timestamp; realizing cross-modal time sequence alignment based on self-adaptive time anchor-attitude coupling; tampering detection is carried out in combination with PRNU fingerprints, noise field consistency, dual compression, copy-movement and the like; multi-view geometry and monocular depth are fused, IMU scale constraint and micro rendering are introduced, three-dimensional reconstruction and re-projection optimization are completed, and collision dynamics verification is carried out; and constructing an event cause and effect graph, judging responsibility in combination with traffic rules, outputting a confidence coefficient vector and a structured report, and generating a verifiable evidence packet. The scheme has the advantages of high efficiency and traceability in the aspects of space-time restoration and interpretable responsibility judgment.

The invention provides a personalized recommendation system and method for an intelligent terminal, and belongs to the technical field of artificial intelligence and big data, and the system comprises a five-element multi-mode dynamic perception module, a space-time attention feature fusion unit, a hierarchical federal transfer learning framework, a context perception enhanced recommendation engine and an edge-cloud co-evolution mechanism. The five-element multi-mode dynamic sensing module is used for synchronously collecting physiological features, environmental parameters, behavior data, spatio-temporal information and a social relation graph; and the space-time attention feature fusion unit is used for fusing the multi-modal data by adopting an ST-Transform model. According to the system, on the premise of ensuring the privacy of the user, the recommendation accuracy and real-time performance in a complex scene are remarkably improved, and a new technical normal form is provided for the personalized service of the intelligent terminal; according to the personalized recommendation method, cross-device transfer learning enables the time consumption of new user feature mapping to be greatly shortened, environment-driven brightness adjustment effectively reduces the visual fatigue of the user, and incremental learning obviously reduces the data volume updating demand of the model.

A computing system is described herein that implements a diffusion-based framework for animating reference images. The computing system includes a video diffusion model that is utilized to encode temporal information. The computing system further includes a novel appearance encoder that is utilized to retain the intricate details of the reference image and maintain appearance coherence across frames. The computing system further employs a video fusion technique to smooth transitions between animated segments in long video animation. Potential benefits of the computing system include enhanced temporal consistency, faithful preservation of reference images, and improved animation fidelity in the generated animation sequences.

The embodiment of the invention discloses a community governance decision generation method and device based on a knowledge graph. The method comprises the following steps: collecting community governance data; performing information extraction and text processing on the community governance data by adopting a data extraction model to generate structured data; constructing a causal analysis atlas, a decision treatment atlas and a space-time correlation atlas by using the structured data; fusing the causal analysis graph, the decision governance graph and the space-time association graph to obtain a community governance knowledge graph, wherein the community governance knowledge graph supports semantic-based query and reasoning; acquiring resident appeal information, and performing risk reasoning based on a preset reasoning rule to obtain a risk reasoning result; and based on a risk reasoning result, in combination with spatio-temporal information defined by a spatio-temporal association graph, querying in the community governance knowledge graph, and generating a community governance scheme according to a query result. According to the invention, the dynamism, the accuracy and the intelligent level of community management can be improved.

The invention relates to the technical field of permission adaptation, in particular to a CRM-GIS-oriented multi-protection permission dynamic adaptation method and system. The method comprises the following steps: firstly, defining in a CRM-GIS platform and acquiring a multi-dimensional authority attribute related to an access request in real time; based on a preset permission policy rule in the platform, processing an access request by using a policy decision engine; then, based on the current spatio-temporal information and behavior pattern information of the user, an artificial intelligence risk assessment module is utilized to analyze the real-time risk level of the current operation of the user; thirdly, dynamically judging and adjusting a final permission adaptation decision aiming at the access request by integrating the multi-dimensional permission attribute, the permission strategy rule and the risk level; according to the final permission adaptation decision, the CRM-GIS platform compulsorily executes corresponding access control operation, and limits or allows access to data and functions in the platform; according to the invention, the reliability of multi-dimensional right dynamic adaptation can be improved.

The invention relates to the technical field of crop growth monitoring, in particular to a crop growth monitoring method based on unmanned aerial vehicle remote sensing, which comprises the following steps of: acquiring a time sequence remote sensing image through an unmanned aerial vehicle and performing time phase processing to solve the problem of data inconsistency of a traditional method; a crop segmentation network based on wavelet transformation and edge guidance is constructed, high-frequency details and low-frequency semantic features are captured through wavelet decomposition, multi-scale dynamic interaction is achieved through cross-resolution feature fusion, and the problems of high-frequency detail loss and fuzzy segmentation are solved; based on a twin network, extracting dual-temporal global semantic features, and combining a difference compensation module to enhance the significance of the growth change, suppress noise interference and improve the weak change detection capability; and finally, fusing the segmentation mask and the difference characteristics through a multi-task framework, synchronously generating a pixel-level spatial distribution diagram and a time sequence thermodynamic diagram, realizing spatio-temporal conjoint analysis of the crop growth state, solving the problem of spatio-temporal information segmentation in a traditional method, and providing high-robustness monitoring decision support for precision agriculture.

The invention provides an industrial fault feature adaptive extraction and multi-mode detection system and method, and belongs to the technical field of industrial fault detection. Comprising the steps of collecting multi-source data of industrial equipment, performing timestamp alignment and processing on the multi-source data to obtain a standardized feature sequence, inputting the standardized feature sequence into a dynamic convolutional neural network, extracting signal local features through a deformable convolution kernel, calculating feature weights in combination with a self-attention mechanism, and screening feature channels to obtain feature vectors of all modes; a graph structure with modals as nodes and correlation as edges is constructed, cross-modal features are aggregated through a graph attention network, and global state descriptors fused with spatio-temporal information are generated; and performing time sequence modeling on the global state descriptor through a bidirectional LSTM network, outputting fault type probability distribution, and completing industrial equipment fault detection. According to the method, the problems of insufficient single-modal information, fixed feature extraction, low efficiency of multi-modal correlation modeling and lagging model updating in traditional industrial fault detection are solved.

The invention discloses a nondestructive testing method for infrared thermal imaging spatio-temporal information fusion, which relates to the technical field of nondestructive testing and comprises the following steps: establishing a linear laser heat source scanning infrared thermal imaging nondestructive testing system; collecting a dynamic infrared thermal image sequence; and calculating and analyzing dynamic infrared thermal image sequence data, and carrying out data processing on the acquired dynamic infrared thermal image sequence by using an infrared thermal imaging spatio-temporal information fusion post-processing method to obtain a full-field thermal response image with surface crack defects. According to the method, spatio-temporal information can be fused to obtain data with higher resolution, more comprehensive and accurate full-field thermal response characteristics are obtained while the calculation efficiency is improved, the method has better flexibility and wider applicability, and the purpose of nondestructive detection of metal surface defects is achieved.

The invention discloses a short video network public opinion information identification method based on an image processing technology, and relates to the technical field of artificial intelligence and image processing, and the method comprises the following steps: S001, through obtaining image frames, audio tracks and time sequence information of a short video, constructing a multi-modal fusion model, extracting continuous image frames with suspicious identity features, and carrying out the recognition of the short video network public opinion information; generating a forgery risk area distribution map; and S002, performing semantic consistency verification according to the counterfeit risk region distribution map, and extracting space and time anomaly features existing among facial micro-expressions, pronunciation actions and background semantics in the image frame. According to the method, a multi-modal model is constructed by fusing image, audio and time information, fine abnormal features, traceability forgery starting points and propagation paths in a deep forgery video are identified, and an identification strategy and a public opinion response mechanism are dynamically adjusted, so that accurate identification, adaptive processing and closed-loop control of short video public opinion risks are realized; and the identification accuracy and the treatment efficiency are improved.

The invention relates to the technical field of image recognition, and provides a video target recognition method and device based on artificial intelligence and a storage medium, and the method comprises the steps: obtaining a video frame data sequence of a target video, carrying out the multi-dimensional analysis of the video frame data sequence, obtaining global video frame information and local region-of-interest information, and generating a target feature map based on the global video frame information and the local region-of-interest information, then carrying out time sequence mode analysis to obtain time sequence evolution features, combining the generated semantic representation vector, inputting the semantic representation vector into a preset adaptive Transform model to carry out target recognition, and obtaining a target recognition result. A semantic representation vector is generated through feature fusion, and a self-adaptive Transform model is used for target recognition, so that the target recognition precision in a complex scene is improved, and the problems of low detection precision and insufficient time sequence information utilization during complex scene processing, dynamic change and long-time sequence analysis are solved.

The invention discloses an unmanned aerial vehicle dynamic environment 3D target detection method and device based on multi-modal fusion, and the method comprises the steps: calibrating a 4D millimeter-wave radar and a camera, and obtaining a pose relation between the millimeter-wave radar and the camera; the method comprises the following steps: preprocessing 4D millimeter wave radar point cloud data to obtain a denoised point cloud image, and performing feature extraction on the denoised point cloud image; using hidden space normal estimation to obtain a pose matrix between adjacent frames, and then through global discretization analysis, realizing multi-frame point cloud pose correction and fusion in a motion scene, and enhancing point cloud data; processing the radar point cloud and the camera image, and obtaining a BEV feature map through a feature extraction network; using a double-end channel attention mechanism and a cross attention mechanism to fuse BEV features; a detection head module based on an anchor frame is designed, and differentiation setting is carried out for different detection targets; and verifying by adopting different data sets and different test scenes to obtain a 3D target detection result. According to the invention, the hidden space normal estimation method is provided to correlate spatio-temporal information, multi-frame splicing is carried out, the density of point clouds is increased, and the performance of target features is improved.

Disclosed in the present application are a question answering method and apparatus based on a temporal knowledge graph. The method comprises: acquiring a target question; determining a plurality of first entities in the target question, and determining first semantic role information in the target question, wherein the first semantic role information at least comprises a subject, a predicate, an object and time information; determining from a target temporal knowledge graph a plurality of pieces of first knowledge associated with the plurality of first entities, and determining a first entity relationship between second entities in each piece of first knowledge; determining a piece of first knowledge among the plurality of pieces of first knowledge as target knowledge, which piece of first knowledge corresponds to the first entity relationship matching the first semantic role information; and performing temporal logic reasoning on the basis of the time information and the target knowledge, so as to obtain an answer to the target question.

The invention relates to the technical field of unmanned aerial vehicle detection, in particular to an anti-unmanned aerial vehicle detection method and system, and the method comprises the following steps: scanning a target airspace in real time through broadband cognitive radio, and constructing an environment feature matrix; based on the environment feature matrix, double-flow feature extraction is carried out, and a protocol fingerprint vector is generated; activating a corresponding group behavior analysis model according to the protocol fingerprint vector, and constructing a behavior topological graph; constructing a dynamic threat vector by adopting a game theory in combination with the behavior topological graph and the real-time motion parameters; generating a multi-dimensional interference strategy set according to the dynamic threat vector; according to the invention, an omnibearing and real-time updated threat vector is constructed, a node threat value is calculated through a non-cooperative game model, accurate evaluation is carried out in combination with spatio-temporal information, potential threats are effectively identified, accurate interference on an unmanned aerial vehicle group is realized, the perception capability of unmanned aerial vehicle behaviors in a complex scene is enhanced, and the risk of the unmanned aerial vehicle behavior in the complex scene is reduced. And the execution precision and efficiency of the interference strategy are obviously improved.

An artificial intelligence system based on spatial-temporal information pairs is provided by the present disclosure. By integrally deploying paired vision, auditory and olfactory acquisition devices, a device that can collect the data within a 720-degree area is constructed, and the multi-dimensional continuous spatial-temporal information pairs such as positions, morphologies, motion states, sounds and odors from the ambient environment of the acquisition device or a same spatial object in the environment are recorded in real time. These information pairs can not only contain spatial relationships and a clock attribute, but also contain rich label attributes, for example, identifiers of acquisition devices, and a name, a category and a behavior pattern of the spatial object.

The invention is suitable for the technical field of scenic spot recommendation, and provides a personalized tourist scenic spot recommendation method and system based on a knowledge graph, and the method comprises the steps: collecting preset scenic spot user behavior data, scenic spot attribute data and time-space information data; a dynamically updated knowledge graph is constructed, nodes comprise user entities, scenic spot entities, time entities and space entities, and edges comprise interaction relations between users and scenic spots, attribute association relations between scenic spots and time-space constraint relations; the A3C algorithm is collected to dynamically optimize the knowledge graph, the dynamic optimization comprises exploring nodes and edges in the knowledge graph through a plurality of asynchronous threads, and each thread executes operation comprising network generation recommendation strategy, network evaluation strategy value and adjustment of weights of the nodes and the edges in the knowledge graph; dynamically adjusting A3C algorithm parameters according to the regional features of the preset scenic area; and a personalized recommendation scheme adaptive to the user demand is generated based on the optimized knowledge graph and parameter configuration, so that the accuracy of the recommendation scheme is effectively improved.

The invention provides an equipment log fault trend prediction method and system based on deep learning, and relates to the technical field of fault prediction, and the method comprises the steps: building equipment, fault and maintenance entity nodes and associated edges thereof through obtaining equipment operation historical data; and performing information propagation and aggregation on the node attribute information and the time sequence attribute information of the edge by using a graph neural network to obtain a node representation vector, performing time sequence segmentation by using a sliding time window to obtain a node dynamic feature, calculating a time sequence autocorrelation coefficient to identify a fault rule and an evolution mode, and constructing a fault prediction model to output a prediction result. According to the method, the graph structure and the time sequence information are fused, the accuracy of fault prediction is improved, and effective guidance can be provided for equipment maintenance decisions.

The invention discloses a surgical robot dynamic compensation method based on multi-mode real-time 4D digital twinning and a related device. The method comprises the following steps: acquiring preoperative three-dimensional and four-dimensional image data of a patient, synchronously acquiring optical body surface movement data and in-vivo ultrasonic data during an operation, inputting the data into an end-to-end modular network in combination with current state data of a surgical robot for feature extraction and fusion, generating a 4D twinborn space containing spatio-temporal information, and generating a compensation instruction based on the space to control the surgical robot. According to the method, real-time fusion and dynamic modeling of multi-modal data in an operation can be realized, the self-adaption and compensation capability of a surgical robot in a complex surgical environment is improved, and the surgical precision and safety are enhanced.

The invention discloses a group behavior identification method and system based on cross-feature interaction Transform, and the method comprises the steps: firstly extracting the appearance and posture dual-branch features of a video clip, inputting the features into a cross-feature correction module for coding interaction, and generating a correction vector through pooling splicing and MLP to achieve feature optimization; a correction result is input into a cross-feature interaction Transform module; spatial information and gating bottleneck block dynamic calibration features are integrated through position coding, and interactive perception features are generated by using a cross attention mechanism; the features are integrated with spatio-temporal information through an asymmetric convolution fusion module, and standard symmetric convolution is replaced to enhance local details and global context; and finally, through full-connection layer dimension transformation, the Softmax layer outputs probability distribution of group behavior categories. Through three innovations of feature correction, interactive Transform and asymmetric fusion, complementary information of multi-modal features is effectively mined, and the recognition precision is remarkably improved.

The invention discloses an intelligent bidding document auditing method based on a block chain, and belongs to the technical field of data processing, and the method specifically comprises the following steps: analyzing a technical clause dependency relationship by means of a natural language processing technology, and generating a semantic link; establishing a mathematical constraint network and a dynamic verification condition for the parameter data; extracting spatio-temporal information from the qualification file, and dynamically binding the spatio-temporal information with project geographic coordinates; then, scanning a semantic link breakpoint matching missing pattern library, positioning a parameter value domain conflict range, verifying qualification file validity and a space-time matching degree, and obtaining a file defect marked with a risk level; secondly, extracting peripheral semantic features of defect nodes, screening candidate terms from a knowledge base, carrying out progressive transformation, retaining a framework, injecting quantitative indexes, and adding territory restriction clauses; and finally, simulating different correction combinations in a virtual environment, comprehensively evaluating technical feasibility, cost fluctuation and risk probability, and screening out an optimal correction scheme.

The invention discloses a pavement crack detection method based on a three-dimensional and time crack model, and relates to the field of pavement crack intelligent detection. On the basis of an existing 3D detection structure special for power pavement crack information acquisition, depth information is added on the basis of two-dimensional information, a crack expansion model based on three-dimensional point cloud and time information is established in combination with time sequence data, and a crack expansion model is established according to the depth increase, width change and time change trend of the crack. And predicting the expansion speed and direction of the crack so as to analyze a potential risk area of future expansion of the crack, and dynamically monitoring the crack expansion.

The embodiment of the invention discloses a safety monitoring method and system for building construction, and the method comprises the steps: collecting the original video data of a construction site, carrying out the denoising, illumination correction and frame rate adjustment, and outputting a standardized video data stream; extracting attitude features of the constructors and representing the attitude features as a feature matrix to form an attitude feature matrix set containing spatio-temporal information; the sensitivity and correlation of the feature matrix are analyzed, calibration noise is added after dimension reduction, and feature data conforming to differential privacy are generated; and extracting data advanced representation by utilizing a pre-training model, and completing behavior classification, dangerous area judgment and safety violation detection. And the violation risk is evaluated in combination with the risk level of the construction area, graded early warning is generated, and meanwhile violation information is recorded to form a traceable management mechanism. According to the embodiment of the invention, accurate and efficient safety violation behavior detection is realized, and intelligent technical support is provided for safety management of building construction.

The invention relates to the field of municipal communication pipelines, and discloses a municipal communication pipeline-based laying construction management system, which comprises the following steps of: acquiring images, position information and voice data of a construction site, preprocessing the acquired content by utilizing a lightweight edge calculation model, and judging whether data exception exists or not; on the basis of spatio-temporal information matching and an image content recognition algorithm, construction data collected on site are compared with the engineering plan model, and whether areas which are not constructed according to specifications are recognized or not is judged; uniformly converting the unstructured data into construction record items in a standard format by using a multi-modal feature fusion method, and judging whether the unstructured data is successfully converted or not; dynamically updating a construction progress state in combination with a project construction plan and real-time acquired data, and generating a visual Gantt chart display; and training the historical engineering data based on a machine learning model, and automatically pushing early warning information to a management terminal. The method has the advantage of improving the communication pipeline construction management capability.

The invention discloses an event camera and Transform-UNet combined video denoising method in a low-light environment. The method comprises the following steps: firstly, dividing a video event frame data set into a training data set and a test data set; then reconstructing an event frame by using a UNet network, designing an Encodex network based on the UNet to perform down-sampling operation on a low-illumination video frame in a DID data set, designing an Encodey network based on Transform and the UNet, and further enhancing detail and texture information in a video through a fusion module in combination with a self-attention mechanism; and finally, enabling the gradual brightness enhancement task and the fusion task of the low-illumination video to reach an optimal balance state in the training process. According to the method, the limitation that time domain information is not fully utilized in the denoising process in the prior art is solved, so that the video denoising effect is remarkably improved, and the overall visual quality of the video is greatly optimized.

The invention belongs to the technical field of power grid fault prediction, and particularly relates to a power transmission line fault prediction method, system and terminal based on spatio-temporal information fusion, and the method comprises the steps: collecting a transient signal of a power transmission line and multi-dimensional environment data of a region where the power transmission line is located in real time, and the multi-dimensional environment data comprises meteorological parameters and geographic parameters; time periods are divided based on 24 solar terms, a dynamic weight matrix is constructed, and initial weights of all environmental factors under different solar terms are trained through historical fault data; according to the method, the transient signals of the power transmission line and the multi-dimensional environment data of the area where the power transmission line is located are collected in real time, the dynamic weight matrix is constructed based on 24 solar terms, and the influence of meteorological parameters, geographic parameters and time factors on the line fault is fully considered. According to the method, the actual operation state of the line can be reflected more comprehensively, so that the accuracy of fault prediction is improved.

The invention relates to a pet-searching geographic information matching method based on machine learning and natural language processing. The method comprises the following steps: acquiring a pet image, text description and loss space-time information input by a user, wherein the loss space-time information comprises loss position coordinates and loss time; extracting visual features of the pet image and semantic features of text description through a deep learning model; coding the lost spatio-temporal information into a spatio-temporal joint vector, fusing the visual features and the semantic features, and calculating a dynamic matching degree; and generating a visual thermodynamic map according to the dynamic matching degree, performing screening according to a preset screening threshold, and outputting an interactive map interface. According to the method, visual, semantic and spatio-temporal information is comprehensively analyzed through machine learning and natural language technologies, the pet searching accuracy and efficiency are remarkably improved, the problems of insufficient information utilization and low matching accuracy in a traditional pet searching method are solved, and powerful support is provided for quickly finding a lost pet.

The invention provides a secure communication method and system based on a QRNG and a Beidou positioning terminal. A sending end and a receiving end of communication preset a pre-shared initial key, and a space-time reference parameter group is obtained through Beidou positioning; a secret key packaging secret key is generated by using a national secret SM4 algorithm; monitoring time-space parameter deviation in a communication process in real time, and triggering a key updating protocol when the time-space parameter deviation exceeds a threshold value; and after the receiving end verifies the Hash verification value, decrypting to obtain the primary encryption key, and restoring the plaintext data. According to the system, the generated true random number sequence is used as an encryption key, so that the unpredictability and randomness of the key are fundamentally enhanced, and quantum computing attack and man-in-the-middle attack are effectively resisted. The use of the pre-shared key mechanism and the key packaging key improves the response speed and efficiency of the communication system. And meanwhile, the position parameter and the timestamp are deeply fused to the key generation process, so that the spatio-temporal information is more difficult to counterfeit, and the defense capability of the system is further improved.

The invention discloses a multi-mode and multi-unmanned aerial vehicle single-target tracking method based on bidirectional Adapter. The method comprises the steps that S1, input information of each mode / view angle is processed through a double-flow encoder; s2, embedding a bidirectional Adapter module into each layer in each encoder branch, fusing the feature information of any mode with the feature information of another mode from the previous layer by using the bidirectional Adapter module, and transmitting the hidden state of a state space model SSM to a subsequent layer to record the time sequence information of the mode of the current frame; s3, performing time sequence feature fusion on the output of the double-flow encoder, integrating the output of different modes, and sending the output into a prediction head for calculation to obtain a target tracking result; s4, taking the time sequence token of each mode and the hidden state as initialization parameters of a next frame so as to transmit time sequence information of a target tracking trajectory and time sequence information of the modes; and S5, based on the double-flow encoder and the bidirectional Adapter module, realizing multi-mode and multi-unmanned aerial vehicle tracking of a single target.

According to various examples of the present disclosure, there is provided a machine learning image segmentation model for automatically identifying and segmenting structural features of a vessel tree from image frames. The model comprises a 3D encoder and 2D decoder, the 3D encoder and 2D decoder connected by at least one interlinked convolution node and a plurality of temporal extraction nodes therebetween. The model is configured to identify and segment structural features of a vessel tree from the plurality of image frames, by the model being configured to: receive a plurality of image frames as an input to the 3D encoder; provide an output of the 3D encoder as an input to the plurality of temporal extraction nodes to extract temporal information; generate, by the plurality of temporal extraction nodes, a 2D temporal output based on the extracted temporal information; provide the generated 2D temporal output to the at least one interlinked 2D convolution node and 2D decoder; generate, at the 2D decoder, a combined temporal output based on an output of the at least one interlinked 2D convolution node and at least one temporal extraction node, wherein the combined temporal output represents a predicted segmentation of the vessel; and generate an output representative of the segmented structural features of the vessel tree based on the predicted segmentation.