109 results about "Multi targeting" patented technology

The invention discloses a code generation method and system based on multi-objective reinforcement learning, and belongs to the technical field of digital integrated circuit design, and the method comprises the following steps: S1, generating an SFT training data set; s2, generating an MORL data set; s3, performing supervision and fine tuning on the model by taking the SFT training data set as input, so that the model masters the basic RTL code generation capability; s4, taking the MORL data set as input to train the model after supervision and fine tuning in the S3, and realizing multi-objective optimization; and S5, according to a user demand, describing a multi-target constraint through vector rewards, screening non-dominated candidate codes by using Pareto optimization to obtain an optimal RTL code, and outputting the optimal RTL code, vector reward details and a PPA equilibrium curve. According to the method and the system, basic constraints are met, and meanwhile generation of RTL codes with PPA indexes capable of being customized according to requirements is achieved.

The invention discloses a flood storage and detention area change pattern spot identification label generation technology based on style decoupling. The technology comprises the following steps: S1, constructing and preprocessing a change detection data set; s2, constructing a conditional diffusion generation network based on a decoupling encoder; s3, decoupling extraction and orthogonalization representation of content-style features are carried out; s4, constructing a multi-target training strategy and two-stage model training; s5, injecting and fusing style features based on cross attention; s6, cross-domain style migration and diversified label generation; and S7, based on label quality screening of physical and semantic double constraints, outputting a high-quality change detection expansion data set. Compared with the prior art, the method has the advantages that by introducing a content-style decoupling mechanism, the style and the content of the generated sample are independently and accurately controlled, and the change detection label which is consistent in ground feature layout, diversified in imaging style and accurately labeled at a pixel level is generated.

The invention discloses a multi-target tracking method for an offshore rain, fog and jitter environment, and the method comprises the steps: obtaining multi-target image data in the offshore rain, fog and jitter environment, and carrying out the target cutting and fusion of the multi-target image data based on a target enhancement segmentation strategy, and obtaining an enhanced sample image; mapping the enhanced sample image and target features in the multi-target image data into a candidate frame set of a pixel scale, and obtaining a sample data set containing adaptive Anchors according to the candidate frame set based on a clustering algorithm; performing model training on the multi-target detection network through the sample data set to obtain an optimal detection model so as to realize target detection; and defining a target state vector and a target observation vector according to a detection result, and realizing multi-target tracking under the marine rain and fog and jitter environment based on an improved Kalman filtering algorithm. The problems that in the prior art, the precision of multi-target detection under the marine rain and fog and jittering environment is insufficient, and a systematic solution for multi-target tracking under the marine rain and fog environment and the jittering scene is lacked are solved.

The invention provides a multi-target seamless tracking method and system based on active prediction and feature pre-fusion, and the method comprises the steps: obtaining real-time video streams of a plurality of intelligent cameras for registration, and obtaining a unified fusion video stream under a global geographic space coordinate system; a plurality of dynamic targets are recognized according to the fused video stream, a globally unique identity label is distributed to each dynamic target, a three-dimensional space prediction track and a virtual relay area of each dynamic target are determined by combining the fused video stream, and a relay intelligent camera is determined according to a shooting condition index; the relay intelligent camera is aligned with the corresponding virtual relay area, when the relay intelligent camera recognizes the dynamic target in the virtual relay area, the master control authority is switched to the relay intelligent camera for seamless tracking, and the virtual relay area where the dynamic target appears is actively predicted in a prospective mode for alignment of the relay intelligent camera; shooting view is ensured, and target losing is avoided.

The invention discloses a multi-target real-time monitoring system and method for rearview mirror lens production and processing, relates to the technical field of automobile part manufacturing, and aims to solve the problem that an existing monitoring system cannot effectively distinguish false abnormity caused by dynamic environment interference in a rearview mirror lens crimping process and the real defect of the crimping process. The system comprises a data acquisition module used for acquiring first monitoring data, second monitoring data and third monitoring data of a crimping process in real time, the first monitoring data being visual image data of the crimping state of a lens and a supporting plate, the second monitoring data being visual image data of the crimping state of the lens and the supporting plate, and the third monitoring data being visual image data of the crimping state of the lens and the supporting plate; the second monitoring data is dynamic environment data of the crimping station, and the third monitoring data is crimping process operation data. The method has the advantages that the environmental interference and the coupling type of the rearview mirror lens crimping process are accurately identified, false abnormity and real defects are distinguished, and the monitoring misjudgment rate and the crimping reject ratio are reduced.

The invention relates to the technical field of power systems. The multi-target power system source-load interaction optimization scheduling method for new energy consumption is provided, and the method comprises the steps: carrying out the analysis processing of inter-region new energy output space-time complementation characteristics in a multi-space-time scale input data set through a preset standardized coordination interface unit, and generating a consumption complementation factor; performing dynamic correction processing on the local scheduling instruction based on the consumption complementary factor and the source-load interaction constraint condition, and generating a cross-regional power mutual aid plan; a preset improved multi-objective evolutionary algorithm is adopted to solve the four-dimensional optimization target model, and a Pareto frontier solution set is generated; and based on the Pareto frontier solution set and the cross-regional power mutual aid plan, processing is carried out through a preset multi-target balance decision-making unit, and an execution scheme is generated, so that the multi-target collaborative optimization capability is improved, the flexible load regulation potential is released, and the robustness of the cross-regional mutual aid plan is enhanced.

The invention provides a multi-target accurate retrieval method and system in a security video, and relates to the field of interdisciplinary application, and the method is characterized in that the method comprises the following steps: carrying out the standardized preprocessing of an original security video, and deploying an improved YOLOv8 model on a preprocessed key frame to carry out the high-precision multi-target detection. The method has the advantages that the appearance, motion and semantic complementary features of the target are synchronously extracted by improving the YOLOv8 model, cross-frame association and trajectory modeling are realized by adopting an enhanced DeepSORT tracker, and a compact feature index database and a three-level progressive retrieval mechanism are constructed in combination with a locality sensitive hashing algorithm; according to the method, the multi-target retrieval precision and efficiency in massive videos are remarkably improved, the target relevance and the complex scene semantic understanding ability are enhanced, meanwhile, the calculation overhead is greatly reduced through rapid approximate matching and a hierarchical retrieval strategy, and the requirements of security application for high accuracy, rapid response and real-time intelligent research and judgment are met.

This invention relates to the field of strategic planning technology, and discloses a strategy generation method and system based on anchor bolt mesh installation. The method includes: acquiring all anchor bolt positions and mesh sizes within the tunnel, and correcting the mesh sizes; digitally twinning the anchor bolt positions in a three-dimensional coordinate system to construct a multi-layered mesh digital twin model; and performing multi-objective strategy optimization on the multi-layered mesh digital twin model to generate a mesh installation strategy on the anchor bolts. This invention can automatically generate mesh installation schemes with high coverage, low loss, and strong stability, reducing manual intervention, material waste and rework rates, effectively improving construction quality and automation levels, and has significant engineering application value and promising prospects for wider application.

Systems and methods are described herein for select content for bid-processing and content placement online placement resources. A computer in an RTB bidding process transmits the selected content to an identified online resource that satisfies the various (and often competing) goal objective thresholds and budget thresholds. The computer transmits the content to the identified online resource, which forwards or transmits the campaign content for display at a user interface of an end-user. The computer analyzes historical data to evaluate the performance of content campaigns against multiple user-selected performance goals and priorities to determine whether to bid for content placement at a given online resource. The computer may generate a blocklist to reject placements at underperforming online resources. The computer may perform optimization functions to determine optimal bid prices that balance the goal objective thresholds and budget threshold and determine whether to bid for the placement.

The application discloses a structure design method of a multi-target cooperative optimization PGNAA device, and the method comprehensively considers the influence of multiple performance indexes, combines a Monte Carlo method, introduces a multi-target cooperative optimization mechanism with constraints, and thus obtains an optimal structure module combination of the PGNAA device meeting engineering application requirements, and can effectively improve the measurement and analysis level of the PGNAA device on samples.

The multi-detection-view-angle target matching method based on the error direction consistency comprises the steps that multiple targets are detected at different angles through multiple aircrafts, and images of the multiple targets at different detection view angles are obtained; detecting each image by adopting a target recognition algorithm, and calculating a sight angle of a target in a camera coordinate system; acquiring a sight angle under an inertial coordinate system, and acquiring position and attitude angle information of multiple aircrafts; calculating direction vectors of the target under different detection view angles and direction vectors among the multiple aircrafts; constructing a target matching model under multiple detection view angles by using the characteristic that the direction vector of the same target under different detection view angles and the corresponding aircraft are in the same plane and have a unique intersection point; according to the characteristic that the error direction of the current multi-target data frame has consistency, target rough matching under multiple detection view angles is completed, and a matching threshold value is calculated; and performing differential matching with the multi-target rough matching value under each detection view angle based on the matching threshold, and coding the successfully matched target.

The invention discloses an elevator safety guard method and system based on cloud side end fusion of multi-target detection, and relates to the field of target detection. Image data are collected in real time through a camera in an elevator, real-time reasoning is conducted through a trained target detection model, and electric vehicle and storage battery targets are detected; once illegal behaviors are detected, an alarm is given immediately, an elevator door is controlled to be kept open, and meanwhile the face detection and feature extraction process is started; face key point features are extracted through a dlib library, Euclidean distance matching is carried out on the face key point features and a preset resident face database, and identity recognition is achieved; a detection result and face feature data are uploaded to a cloud management platform, alarm information is generated and pushed to a property management APP, and property management personnel can remotely check the early warning accuracy and take corresponding measures. According to the method, the false alarm rate is effectively reduced, the recognition precision and the response speed are improved, and a complete treatment closed loop is formed.

The invention discloses a power CPS network attack intelligent positioning method and system based on a multi-target evolution CNN. The CNN is used as a multi-label classification model for power CPS network attack positioning; designing a variable-length hybrid coding strategy by taking architecture parameters such as a convolution layer number, a filter number, a convolution kernel size, a pooling kernel size, a full-connection layer number, a full-connection layer neuron number and a discarding rate in the CNN and hyper-parameters such as a learning rate, a batch size and an optimizer as decision variables; the method comprises the following steps of: taking the minimization of the number of model parameters of the CNN and (1-macro average F1 score) as an optimization objective function, designing a Pareto leading edge selection mechanism based on non-dominated sorting, and a block single-point crossing strategy and mutation operation oriented to hybrid coding individuals, and carrying out offline multi-objective optimization iteration to obtain a compromise optimization CNN giving consideration to attack positioning precision and model lightweight. And on-line deployment is carried out, and accurate detection of the intelligent positioning system for the power CPS network attack is efficiently realized.

The invention discloses a multi-objective dynamic optimization method and device, electronic equipment and a storage medium, relates to the technical field of control, and integrates structured time sequence operation data and environment information of a thermal power plant, and outputs a prediction load curve including a confidence interval during unit load prediction, thereby effectively reducing prediction errors. A control parameter set value can be generated in combination with the prediction curve and a real-time unit operation state, and parameters are prevented from deviating from an optimal interval through safety range verification and smooth processing, so that the limitation of an existing single target optimization algorithm is eliminated; the technical effects of improving the unit load prediction precision, ensuring that the control parameters are in the optimal operation interval, improving the power generation efficiency, reducing the carbon emission intensity, accelerating the frequency modulation response speed and meeting the key index requirements of the novel power system on the thermal power plant are achieved.

The application discloses a multi-target particle swarm optimization-based multi-base SAR space configuration design method, which comprises the following steps: firstly, setting multi-base SAR space configuration design parameters, modeling a multi-base SAR echo model, and then performing multi-base SAR imaging wave number spectrum analysis; secondly, modeling a space configuration optimization design problem, inputting space configuration optimization design problem system parameters and configuration parameters, initializing MOPSO, then updating the speed and position of the particle swarm, and finally outputting the optimized configuration through iterative updating. The method of the application converts the space configuration design problem into a constrained multi-target optimization problem, introduces a multi-target particle swarm optimization algorithm for solving, realizes high-resolution imaging through the optimized space configuration, breaks through the strict limitation of the multi-base SAR space configuration, and can complete the optimization design of the relative positions and flight speed directions of multiple radar platforms under certain time and system resource conditions, so that higher-resolution images can be obtained within a certain observation time.

The embodiment of the invention discloses a multi-target labeling method and device, equipment and a storage medium. The method comprises the steps of obtaining target video data, wherein each target object appearing for the first time has an initial accurate label and a labeling box in a corresponding video frame; detecting each target object appearing in each video frame in the target video data to obtain a detection frame marking a detection result; the target video data, the initial accurate labels, the labeling boxes and the detection boxes are input into a multi-target tracking model together, target objects are tracked and matched through the multi-target tracking model, the highest priority is set for the accurate labels, first labeling labels corresponding to all the target objects in all the video frames are obtained, and the accurate labels comprise the initial accurate labels and the detection boxes; the first labeling labels corresponding to the same target object are the same and are initial accurate labels corresponding to the target object. According to the technical means, the technical problem that the labeling accuracy of a multi-target tracking model is limited when tracking labeling is carried out on a plurality of specific targets in the video data is solved.

The application discloses a CBCT metal artifact removal method and system based on a projection domain metal recognition, which skips a traditional image domain segmentation and orthographic projection process, directly extracts key geometric features of a metal region in original projection images, and realizes high-precision recognition and spatial posture estimation of metal objects by matching with a pre-established metal model library, so that the processing flow is significantly simplified, and the recognition stability and artifact repair effect are improved. In view of the shielding and overlapping problems that may occur in a multi-metal structure, a step-by-step stripping recognition mechanism is proposed, and through round-by-round recognition, fitting and image updating, multi-target interference is effectively avoided, and the accuracy and integrity of model matching are ensured.

This invention presents a knowledge evolution poisoning attack method for graph-enhanced retrieval and generation systems, belonging to the field of retrieval enhancement and generation. Through knowledge evolution forgery attacks and multi-target cross-subgraph collaborative attacks, it can generate evolutionary corpora that satisfy temporal constraints and have stronger structural connectivity without compromising the overall consistency of the knowledge graph. This allows for a more thorough exposure of GraphRAG's vulnerabilities in knowledge extraction, community partitioning, subgraph retrieval, and evidence aggregation stages in authorized evaluation environments. Compared to direct splicing injection, the samples generated by this method more closely resemble the "real knowledge update" distribution and can be used for pre-deployment red team evaluation, post-deployment regression testing, and effectiveness verification and parameter selection for defense modules such as consistency detection, retrieval filtering, and fact verification.

This application relates to the field of gimbal technology, and more particularly to a gimbal multi-target tracking method, gimbal, and medium for live streaming scenarios. The method involves acquiring the first frame image from a live streaming camera, detecting all detected targets and constructing a multi-target identity queue. The image is then input into a multi-target tracking model, which outputs predicted bounding boxes and tracking confidence scores for each target. Based on the confidence scores, the target loss status is determined. A recapture operation is performed on the lost target; if recapture is successful, tracking resumes and parameters are updated; if recapture fails and times out, the target is removed from the queue. This process filters to obtain a set of trackable targets. The gimbal aiming point is determined by combining the current scene type and the predicted bounding boxes of each target. Control commands are generated based on the deviation between the aiming point and the image center to drive the gimbal rotation and calibration. This application enables stable and continuous multi-target tracking in live streaming scenarios, effectively reducing target loss and improving the stability of live streaming footage and viewing experience.

The application relates to the technical field of resource scheduling and discloses an intelligent resource scheduling supply method and system in a heterogeneous computing environment, which comprises the following steps: acquiring core heterogeneous data, performing exponential smoothing denoising to obtain a smooth state value, combining an HAT extended tuple, and analyzing to obtain a comprehensive capability score; automatically adjusting contribution degree by similarity of static characteristics and dynamic characteristics; constructing a coupling correction function, calculating a hybrid precision matching degree, combining an exponential product to reflect nonlinear correlation between targets; constructing a dynamic penalty function, optimizing a quantum genetic algorithm fitness function, and performing multi-target collaborative optimization; constructing a complexity coupling and dynamic adaptation mechanism to dynamically adjust a task segmentation ratio; designing a frequency and reconfiguration time index ratio to optimize FPGA bit stream preloading; constructing a synchronous delay coupling model to perform state synchronization optimization; balancing multidimensional feedback through a combined reward function; and improving explainability by quantifying the influence of decision factors through contribution degree entropy.

The application relates to the technical field of intelligent production scheduling, and discloses a multi-target intelligent production scheduling method combining AI inventory prediction and hybrid programming. The method first standardizes and integrates multi-source data such as enterprise digital factories and warehouses, and constructs a unified production scheduling database; then a linear programming model is established with the target of maximizing profits, and product production quota optimization is completed in combination with constraints such as production capacity and raw materials; based on a switching cost matrix and production constraints, the lowest cost production sequence is solved through dynamic programming; an AI inventory prediction model is constructed by using a random forest regression, and safe inventory calculation and inventory risk grading early warning are realized; finally, multi-target production scheduling is executed according to the multi-level dynamic adjustment principle, and complete schemes such as hour-level plans, Gantt charts, cost and profit, and inventory curves are output. The application can simultaneously optimize production profit, switching cost, demand satisfaction rate and inventory safety, realize active inventory prediction, effectively reduce production loss caused by material interruption and single insertion, and improve the scientific nature of production scheduling and enterprise operation benefits.

A video online recommendation system combined with network information comprises a video quality evaluation module, a network measurement module and a multi-target reordering module; the recommendation algorithm of the video quality evaluation module selects candidate videos; the network measurement module measures the network condition during the request of the video; the multi-target reordering module estimates the residual transmission time of the candidate videos according to the network bandwidth feedback calculated by the network measurement module, reorders the candidate video list selected by the recommendation algorithm, and selects a preset number of video combinations to transmit to the user end. The present application proposes a new short video recommendation system and method, which takes network bandwidth into the video recommendation system. The system can select the video combination that can be successfully transmitted within a specified time and bring the highest actual income. In the case of poor network bandwidth, compared with the traditional recommendation mechanism, the system can improve the video playing time by 160%, that is, the income is improved.

The application discloses a pipe network periphery construction dynamic monitoring method based on multi-target visual identification, relates to the technical field of intelligent monitoring intersection, and comprises the following steps: integrating and analyzing the environment of a construction site and a future moving path, identifying potential construction damage risks, and generating a potential risk list through classified processing; classifying and sorting the potential risk list according to severity and urgency, and generating a pipe network monitoring report through an integrated data analysis method. Convolution, feature transformation and time sliding are used to extract visual features, terrain features and temperature distribution features and to realize weighted fusion, so that unified representation of multi-source heterogeneous data is realized, and the comprehensive perception result can comprehensively reflect the static structure and dynamic change of a construction scene.

The application provides a low-altitude visual angle multi-target detection method based on YOLOv12s, adopts an improved C3k2 feature extraction module to replace a native C3k2 module in a native YOLOv12s backbone network, and extracts multi-scale features of P2 to P5 levels; the improved C3k2 feature extraction module is internally provided with a feature extraction unit of double parallel branches; features of P3 feature layers, P4 feature layers and P5 feature layers output by the backbone network are input into a multi-scale feature depth interaction module, after input features are aligned in terms of channel number and spatial scale, a three-dimensional feature is constructed by adding a scale dimension, spatial and scale joint information interaction of different scale features is realized through three-dimensional convolution, and multi-scale fusion features are output; the multi-scale fusion features are fused with native P3 features output by the backbone network, enhanced P3 features are generated, and the enhanced P3 features are fused with native P2 features output by the backbone network, enhanced P2 features are generated; multi-scale joint prediction is adopted, and target detection results are output.

The application relates to the technical field of model construction, in particular to a non-heritage craft digital modeling system and method based on multi-modal perception, which comprises the following steps: acquiring action data and environment data of an artisan operation, wherein the action data and the environment data are collected through a sensor system; performing multi-modal data synchronization and feature fusion based on the action data and the environment data to generate a process parameter correlation model; constructing a digital twin model of the non-heritage craft based on the process parameter correlation model and optimizing process parameters; generating real-time operation guidance information based on the digital twin model and performing quality evaluation and feedback optimization on process results. Through a multi-modal data synchronization algorithm optimized by dynamic time warping (DTW), a process parameter correlation model based on a non-Euclidean space graph convolution network and a multi-objective Bayesian optimization framework, the application realizes digital preservation and intelligent optimization of a traditional process.

The invention provides an automatic pseudo label generation method for a multi-target tracking system. The automatic pseudo label generation method comprises the following steps: dividing an acquired video sequence into a plurality of video clips; generating a reference trajectory on each video clip in the plurality of video clips through a plurality of candidate detection models; setting a plurality of tracking parameter schemes, and generating candidate pseudo-labeling trajectories corresponding to the tracking parameter schemes on the video sequence through the mixed feature tracker; comparing the reference trajectory with the candidate pseudo-labeling trajectory, and calculating a consistency score of each tracking parameter scheme in the plurality of tracking parameter schemes through a PLCS algorithm; selecting an optimal tracking parameter scheme from the plurality of tracking parameter schemes according to the consistency score; and according to the optimal tracking parameter scheme, generating target pseudo-annotation data used for detector scheduling model training. According to the invention, automatic generation of high-quality pseudo labels is realized, and intelligent selection of detectors in different time periods and scene conditions is realized.

The application provides a kind of end-to-end foggy image multi-target detection model based on knowledge embedding, and relates to pattern recognition technical field.The end-to-end foggy image multi-target detection model based on knowledge embedding includes image defogging sub-network, target detection sub-network and knowledge embedding based semantic association feature learning, the image defogging sub-network includes public module and feature recovery module, the feature recovery module includes upsampling sub-module, multi-scale mapping sub-module and image generation sub-module.The application can obtain higher target detection precision under limited small amount of data training set in the case that multiple different class targets exist in scene simultaneously, has positive significance to promote foggy image scene understanding application, and has high detection quality and fast efficiency.

The application provides a space-based and air-based multi-target detection and correlation method, device and equipment, and relates to the technical field of remote sensing information processing. The method comprises the following steps: acquiring a space-based target set detected by space-based detection and an air-based remote sensing image; inputting the space-based target set and the air-based remote sensing image into a pre-trained target search network, extracting a space-based target correlation feature set corresponding to multiple space-based targets and air-based data basic features through a shared backbone network in the target search network; performing target detection on the air-based data basic features based on a target detection head in the target search network, determining an air-based target set in the air-based remote sensing image, and screening the space-based target correlation feature set from the air-based data basic features based on multiple air-based targets included in the air-based target set; and correlating the multiple space-based targets and the multiple air-based targets based on the similarity between the space-based target correlation feature set and the air-based target correlation feature set, so that the multi-target correlation efficiency can be improved.