613 results about "Target type" patented technology

The invention relates to the field of image processing, and discloses an object monitoring method and device based on multi-source data and a storage medium, and the method comprises the steps: synchronously collecting multi-channel video streams, environment parameters and equipment position information, and carrying out the time alignment and data association processing, and forming associated data; performing feature matching on the multiple paths of video streams, fusing position information and environment parameters, and establishing a mapping relation between video feature points and a unified space coordinate system; splicing the multiple paths of video streams in real time according to the mapping relation to generate a panoramic video stream; performing dynamic scene analysis based on the panoramic video stream and the environmental parameters, and identifying a target type and a state to obtain an analysis result; and generating an equipment regulation and control strategy based on the analysis result, and generating and issuing a regulation and control instruction for adjusting the working parameters of the multi-view image acquisition device based on the equipment regulation and control strategy. According to the invention, the splicing precision, the real-time performance and the target identification accuracy of panoramic monitoring can be improved, and the dynamic adaptive regulation and control of the equipment can be realized.

The invention provides an image processing method and device and electronic equipment, and the method comprises the steps: obtaining a continuous frame image, carrying out the motion detection of the continuous frame image, obtaining each motion region in the continuous frame image and the speed of each motion region, determining the target type of each motion region through semantic recognition, determining a priority corresponding to each motion area according to the speed and the target type of each motion area, and performing perception recognition on the motion areas with different priorities by adopting corresponding perception strategies to obtain a perception result; according to the method, perception identification is focused on a dynamic area and differentiated processing is carried out, a large amount of redundant calculation in a static or non-key area is effectively avoided, system calculation resources are saved, hardware loads are reduced, key targets can be ensured to be preferential, the real-time performance and response speed of the system are improved, and vehicle driving safety is ensured.

The invention relates to the technical field of electric digital data processing, and provides a secondary development code cross-product transplantation method and device, computer equipment and a medium. The method comprises the steps of loading a source project, screening a to-be-transplanted source code file, identifying an original API type, determining a mapping relation between the original API type and a target API type, and generating an adaptation layer code framework according to the mapping relation; copying the to-be-transplanted source code file into the target project; on the premise of keeping the project hierarchical structure of the source project, replacing the calling node of the original API type with the calling node of the adapter type, and replacing the namespace reference with the corresponding namespace in the target project to obtain a migrated source code file; and obtaining a secondary development project of the target project based on the second product API according to the adaptation layer code framework and the migrated source code file. According to the method and the device, the transplantation efficiency and accuracy of the transplantation of the cross-product secondary development codes are improved.

The invention relates to the technical field of rail traffic equipment maintenance and artificial intelligence image recognition, in particular to a rail vehicle cloud edge cooperative detection method and system and inspection equipment. The method comprises the following steps: acquiring image data of an area to be detected, synchronously recording attitude information of shooting equipment, carrying out image quality scoring on the image data, if the image quality score reaches a preset threshold value, calling a local target detection model to carry out defect identification on an image, and outputting an identification result containing a target type, a position and confidence; if the confidence coefficient of the recognition result is lower than a set threshold value, the image data and the posture information are uploaded to a cloud server, a cloud high-precision recognition model is called for secondary recognition, and a cloud recognition result is obtained. The real-time requirement is met through quick response of the local model, the cloud model rechecks a low-confidence result, efficiency and precision are both considered, and the contradiction that in the prior art, manual judgment standards are different, and speed and precision are difficult to consider is solved.

The invention discloses a method for realizing holographic traffic at an intersection. The method comprises the following steps: acquiring a real-time video stream at the intersection; motor vehicles, non-motor vehicles and pedestrians in the video are identified based on a deep learning target detection algorithm, a continuous motion track of each target is generated through a multi-target tracking algorithm, identity association is carried out on cross-camera targets in combination with a re-identification algorithm, and structured traffic data including target types, real-time speeds and motion directions are output; obtaining coordinate points of each lane of the intersection based on a geographic information system, and constructing a lane network topological relation; combining with the structured traffic data to generate target trajectory data; and constructing an intersection three-dimensional model based on an unreal engine, generating a virtual target in the three-dimensional model according to the target trajectory data, and driving the virtual target to move in real time. According to the method, a holographic traffic implementation scheme is provided for a business scene which is free of radar and only monitored by a video.

The invention discloses a data processing method and device for a power distribution network and a nonvolatile storage medium. The method comprises the following steps: acquiring environment data of a power distribution network; determining a data change rate of the to-be-collected data based on the environment data; based on the data change rate, determining a target sampling frequency of the sensor, a target type of the target computing device and a target sensing frequency of the sensor in a sampling period when the age of the target information reaches a predetermined target; and based on the target sampling frequency and the target sensing frequency, controlling the sensor to collect target data of the power distribution network, and processing the target data collected by the sensor based on the target computing device of the target type. The technical problem that the data real-time performance is poor due to the fact that a traditional sensor data processing method is difficult to adapt to distributed energy access is solved.

The invention relates to the technical field of wireless, and provides a target sensing method, device and equipment, a storage medium and a program product, the target sensing method is applied to network equipment, and the method comprises the following steps: determining type information of a sensing target in a sensing result based on the sensing result and RID information under the condition that the sensing result and the RID information exist; wherein the sensing result is obtained by performing target sensing by the network equipment; the RID information is sent by the RID receiver. According to the invention, under the condition of determining that the sensing result and the RID information exist, the RID information can be used as the auxiliary information to assist the base station to carry out data processing in the sensing result, and the type information of the sensing target in the sensing result is accurately determined, so that the sensing result and the RID information are fused, and the sensing accuracy is improved. The method can solve the problem that the general sensing integrated system is easy to mistakenly recognize the target type when detecting the target, thereby improving the credibility of the detection result, and guaranteeing the reliability of the general sensing integrated system.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a target data sample set construction and screening method, device, equipment and medium, and the method comprises the steps: obtaining a target type description, carrying out semantic extension to generate an extension description, generating a reference image sample based on an image generation model, real data units are screened through feature extraction and similarity comparison, and a target data sample set is constructed in combination with knowledge base verification. According to the method, by introducing semantic extension, reference image generation, cross-domain feature comparison and knowledge base consistency verification, real samples highly fitting target type semantics are automatically screened from massive original data, so that the manual annotation dependence is reduced, the illegal sample construction efficiency is improved, and the manual annotation time is shortened. And the training quality and the expansion capability of a subsequent detection model are enhanced.

The invention discloses a multi-mode element learning remote sensing reconnaissance target identification method guided by a detection mechanism, and belongs to the field of computer vision and remote sensing image processing. The core of the method is as follows: multi-modal feature extraction and fusion guided by a detection mechanism: aiming at the electromagnetic scattering characteristic of an SAR image, the geometric texture characteristic of a visible light image and the thermal radiation characteristic of an infrared image, respectively designing a special feature extraction network, and introducing a cross-modal fusion module based on an attention mechanism, feature enhancement expression of physical information complementation is realized; according to the meta learning training normal form, an optimization-based meta learning device is constructed, and training is performed on a large number of multi-modal remote sensing task sets, so that the model obtains the capability of quickly learning new target categories from a small number of samples. According to the method, a physical detection mechanism and data-driven meta learning are combined, and the problems that a traditional method is low in recognition precision and poor in generalization ability in a complex reconnaissance scene with scarce samples, variable target types and difficulty in SAR image interpretation are effectively solved.

The invention relates to the technical field of unmanned aerial vehicle autonomous reconnaissance, in particular to an unmanned aerial vehicle reconnaissance decision-making method, device and equipment based on edge calculation and a medium, and the method comprises the steps: obtaining the multi-dimensional data of an environment and a target through an optical camera, an infrared thermal imager and a radar carried by an unmanned aerial vehicle; target identification and strategy reasoning are carried out on the multi-dimensional data, a target type and attributes are identified from the multi-dimensional data through a lightweight convolutional neural network, and a battlefield situation is obtained in advance to generate a strike strategy; obtaining a threat level and a task priority, and dynamically adjusting the flight path of the unmanned aerial vehicle and the strike strategy according to the threat level and the task priority; and obtaining a strike result corresponding to the strike strategy, analyzing the strike result in real time, judging a target destroy state through an airborne sensor, and updating a subsequent task strategy. According to the invention, the autonomy of the unmanned aerial vehicle system is improved.

The invention discloses a low-altitude unmanned aerial vehicle dynamic scene autonomous navigation adaptation method and system, and relates to the field of intelligent navigation, and the method comprises the following steps: 1, continuously obtaining real-time image data in a flight process through an image collection part carried on an unmanned aerial vehicle, analyzing the real-time image data based on predetermined route information of the unmanned aerial vehicle and a preset route attention area, and judging and identifying whether one or more dynamic targets exist in the route attention area; 2, if the existence of the dynamic target is identified, calling a motion risk prediction model which is constructed and pre-trained based on a deep learning algorithm; the motion risk prediction model integrating the relative speed, the motion direction, the target type and the trajectory prediction uncertainty is introduced, and the potential collision risk is quantitatively evaluated, so that the unmanned aerial vehicle can recognize the danger caused by the sudden dynamic target in time, and the safety guarantee in the densely populated area and airspace mixed environment is enhanced.

The invention discloses a multi-mode nonlinear model predictive control method and system for a visual servo-driven arm-carrying unmanned aerial vehicle, and belongs to the technical field of intelligent control of arm-carrying unmanned aerial vehicles. The objective of the invention is to solve the problems of unstable control mode switching and difficulty in unified control modeling of different target structures in existing unmanned aerial vehicle grabbing control. According to the technical scheme, a task-driven modal judgment mechanism is introduced, the current task modal can be judged in real time based on the target type, the image features and the flight state information, control strategy self-adaptive switching between a rod-shaped target and a plane target is achieved, and continuity and stability of control logic are guaranteed. For a rod-shaped structure target, a remote approaching, servo adjustment and compliant contact three-stage control strategy is designed, and a dynamic weight adjustment mechanism is introduced into NMPC control solution, so that smooth transition of control performance from quick response to fine compliant is realized, and the control precision and compliance of the arm-carrying unmanned aerial vehicle in different operation stages are remarkably improved. For a plane structure target, the invention provides an adsorption control strategy based on impact time prediction and angle feedforward compensation, the contact time can be accurately estimated, the attitude of the aircraft can be adjusted in advance, the adsorption stability is effectively improved, and the contact failure probability caused by inclination of a target surface is reduced.

Curvelet-based low level fusion of camera and RADAR sensor information is disclosed and includes processing RADAR data corresponding to a scene to generate a RADAR point cloud and processing camera image data corresponding to the scene using a curvelet transform to identify a target of interest in the scene and generate for the target of interest a target type, (x,y) coordinate values, and a curvelet magnitude per decomposition level. If discrepancies exist between (x,y) coordinate values of the RADAR point cloud and the target type, (x,y) coordinate values, and curvelet magnitude per composition level of the target of interest, a portion of the RADAR data processing is repeated to regenerate the RADAR point cloud; otherwise, the RADAR point cloud to a perception stack of a vehicle.

The invention discloses a multispectral target identification and laser orientation soft and hard damage anti-unmanned aerial vehicle system. Comprising a multispectral signal acquisition module, a multi-modal data preprocessing module, an unmanned aerial vehicle target feature extraction module, an intelligent target identification and classification module, a laser parameter dynamic configuration module, a directional tracking and aiming module, a soft and hard damage execution module and a damage effect evaluation and feedback module. According to the invention, through multi-spectral fusion acquisition and multi-dimensional feature extraction, haze, camouflage and other environmental interferences are effectively resisted, and the distinguishing precision of the unmanned aerial vehicle and the interference target is improved; laser parameter dynamic configuration and soft and hard damage mode switching can be carried out according to target types and scene requirements, and energy waste or excessive treatment is avoided; and a damage effect evaluation and feedback mechanism ensures thorough target disposal, reduces repeated operation, and improves the system combat efficiency.

The invention discloses a digital circuit design method and device, equipment and a medium, and relates to the technical field of digital circuits, and the method comprises the steps: determining a target type of a to-be-designed digital circuit, and collecting a first training set corresponding to the target type; each training sample in the first training set comprises an input feature item used for designing a target type of historical digital circuit and the actual result quality of the historical digital circuit, and the input feature item comprises a high-level language source code and an HLS constraint parameter; constructing an initial prediction model based on the multi-layer perceptron mixed structure, training the initial prediction model by using the first training set, and searching and optimizing the model architecture based on the network structure to obtain a target prediction model; and predicting the actual result quality corresponding to each parameter combination in a target design space of a to-be-designed digital circuit by using the model, and designing the digital circuit by using the parameter combination of which the quality meets the Pareto frontier. And predicting an accurate actual quality result by utilizing a prediction model without intermediate representation so as to carry out digital circuit design.

The invention relates to the field of man-machine interaction, and particularly provides a task processing method, device, equipment and system, a medium and a product. The method comprises the following steps: in response to a first session instruction of a user for a target type task, executing the target type task; the target type task belongs to a task type capable of receiving supplementary information input by a user during task execution; in the task execution period of the target type task, responding to a received second session instruction input by the user, and executing a corresponding task operation according to the intention of the second session instruction; wherein the intention is used for indicating to input supplementary information of the target type task or initiate a new task. Therefore, on the premise of not interrupting the original target type task, the new task instruction of the user can be responded in parallel or the supplementary input of the user to the target type task can be processed, and the problems of interaction blockage and context chaos caused by the exclusive session state under the existing architecture are solved.

The invention relates to a display method and device, electronic equipment and a storage medium, and the method comprises the steps that when multimedia data of a target type is played, a medium card is displayed in a display interface, the medium card comprises target option information, and the target option information comprises object information of a to-be-recommended object; in response to a first trigger operation for the target option information, a dialogue interface corresponding to the target option information is displayed, the dialogue interface is used for displaying dialogue information, the dialogue information comprises a capital reserving panel, and the capital reserving panel comprises consultation information reserved by a target account. By adopting the method and the device, the retention modes of the consultation information can be enriched, and the retention efficiency of the consultation information is improved.

The invention discloses a target detection method and display equipment, and the method comprises the steps: carrying out the target detection of a to-be-detected image through a target detection model, and obtaining a preliminary detection result; for first target detection data of which the confidence coefficient is greater than a first preset value and less than a second preset value, acquiring a context region image of a target frame contained in the first target detection data, and generating a target detection prompt word based on a target type contained in the first target detection data; based on the context region image and the target detection prompt word, determining the validity of the first target detection data by using a multi-modal large model; and under the condition that the first target detection data is valid, constructing a final detection result corresponding to the to-be-detected image based on the target detection data of which the confidence coefficient is greater than a second preset value and the first target detection data.

The invention provides a target identification method and system based on multi-source information fusion, and relates to the technical field of low-altitude target detection. The method comprises the following steps: acquiring target radar track data, interception equipment track data and position area information data; based on target radar track data, extracting a first feature in an RCS form dimension, and extracting a second feature in a motion dimension; based on the target radar track data and the track data of the monitoring equipment, determining a frequency spectrum monitoring correlation factor and regional position information features; performing feature fusion on the first feature, the second feature, the spectrum interception correlation factor and the regional position information feature to obtain a target feature, and identifying a target type; and identifying a target threat level based on the target type and the target radar track data. The method and the device are used in a target identification process based on multi-source information fusion, and the technical problem that the target threat degree cannot be accurately identified in a complex environment in the prior art is solved.

The invention provides an unmanned aerial vehicle task guidance method based on augmented reality, a storage medium and a system, and the method comprises the steps: determining a flight task of an unmanned aerial vehicle, and obtaining a corresponding flight region; determining a target route of the unmanned aerial vehicle; determining target environment information corresponding to the target route from the initial environment information, and performing target identification on the target environment information to obtain a target object passed by the unmanned aerial vehicle in the target route and a target type corresponding to the target object; determining a target operation needing to be executed on the target object by the unmanned aerial vehicle for executing the flight task and an operation type corresponding to the target operation according to the target type, and determining a task identifier of the target object according to the operation type; and performing virtual display according to the target route and the task identifier in combination with the initial environment information to obtain a target virtual display result of the unmanned aerial vehicle. According to the invention, the task identifier and the flight route are displayed virtually, so that the error rate of a pilot during task execution is reduced, and the task execution accuracy of the unmanned aerial vehicle is improved.

The application discloses a kind of geometric error parameterization fast modeling methods for multi-configuration five-axis machine tool.The method comprises the following steps: constructing the parameterized general transfer vector table of the five-axis machine tool of target type;The parameter set of five-axis machine tool is input into general transfer vector table, and general transfer vector table generates the transfer vector of each geometric error term of five-axis machine tool, to construct geometric error model;Geometric error term and five-axis coordinate are input into model, and model outputs the position deviation and attitude deviation of tool, to be used for the geometric error compensation of tool of five-axis machine tool.The transfer vector table constructed by the application can be reused, and the geometric error model constructed can be suitable for most conventional configuration machine tools;The application can realize the parameterization fast modeling of five-axis machine tool geometric error, can reduce the experience requirement of research and operator, and provides convenience for the accuracy design, error compensation research of various conventional five-axis machine tools and the transverse comparison research between various machine tool configurations and layouts.

The invention discloses a cross-platform desktop application barrier-free test method and system based on a containerization environment, and the method comprises the steps: constructing a test container containing an AT-SPI proxy DBus communication module, enabling the read-only of the test container to mount a host machine DBus socket and limit the right, and enabling a host machine to deploy a DBus bridging proxy as a cross-environment channel; the test container communicates with a host machine, other containers or desktop applications of a sandbox through the channel according to a target type, and the bridging agent dynamically analyzes a virtual DBus address forwarding request in a sandbox scene; the test container sends an AT-SPI request, and interface element capture is completed after returned control data is verified by the bridging agent; and finally executing an automatic test based on the element data and verifying a result. The invention aims to realize dynamic capture and automatic test of desktop application interface elements across host machines and containers / sandboxes.

This application relates to a method, apparatus, computer device, and storage medium for displaying medical images. In response to an instruction to acquire a first image sequence, a target type label for the first image sequence is determined. From a sequence of images to be identified containing various type labels, at least one second image sequence associated with the target type label is acquired. The first image sequence and at least one second image sequence are then displayed. Each type label is obtained based on a classification result determined according to each image sequence to be identified and a preset classification model. The embodiments of this application employ a preset classification model to automatically identify the image sequences to be identified, obtaining the classification results of each image sequence to be identified, thereby obtaining the type label for the image sequences to be identified. Compared to relying on manually entering tag information for medical images, the method proposed in this application can significantly reduce the error probability of acquiring the second image sequence based on the target type label, thereby greatly improving the accuracy of image sequence acquisition.

The invention provides a radar waveform optimization method, system and device, a medium and a program product, and the method comprises the steps: transmitting a basic radar signal employing a basic waveform, and receiving an original echo signal formed by the reflection of a target; extracting a radar cross-sectional area of a target from the original echo signal to obtain a target RCS; traversing an RCS allowable range corresponding to each target type in the feature database, and determining a matching result; determining waveform control parameters of the radar waveform; an optimized radar signal employing the optimized waveform is generated and transmitted. According to the scheme, traversal matching is carried out on the target radar cross-sectional area measured in real time and the RCS allowable range in the feature database, adaptive optimization of the radar transmitted waveform on the current target RCS is realized, in addition, the candidate PRF is systematically traversed in the PRF feasible range corresponding to the target type, and the target type is more accurate. The adaptive matching of the PRF parameter with the current target RCS and the propagation condition is realized.

The invention provides a sea target drifting trajectory prediction method and system based on a Transform-GRU and MDN mixed depth model. The method comprises the steps of S1, obtaining initial data of a search and rescue task and constructing a target feature vector about a search and rescue target type; s2, historical environment field data and future environment field forecast data are acquired, data preprocessing is performed, and a historical environment field time sequence feature sequence and a future environment field time sequence feature sequence are acquired; s3, performing dynamic weighted fusion on the target feature vector and a historical environment field time sequence feature sequence; s4, the fusion features are input into a Transform encoder for feature extraction, and context vectors are obtained; s5, taking the context vector as the initial hidden state of a GRU decoder, and predicting the final position of the search and rescue target according to the input by the GRU decoder; s6, enabling the output of the GRU decoder to pass through a mixed density network (MDN), and obtaining a probability distribution parameter representing a future position; and S7, generating and drawing a target probability density contour map in real time according to the probability distribution parameters, and performing visual display.

The invention discloses an unmanned aerial vehicle undercarriage load prediction model training method and device, equipment and a storage medium, and relates to the technical field of computers. According to the method, a model is trained according to a flight parameter data sequence of a whole landing period and undercarriage load data, flight parameters of time sequences before and after a landing process are covered, multi-source time sequence data fusion is adopted, and the flight parameter data sequence of the whole landing period is also adopted for prediction during prediction. The method is suitable for structural damage accumulation and fatigue life analysis; target type flight parameters are screened out through the Pearson correlation coefficient and mutual information, principal component analysis is carried out on the target type flight parameters, and the accuracy of real time sequence characteristics is improved; moreover, the sample size is expanded through the time sequence condition generative adversarial network, different landing stages are dynamically adapted in combination with the multi-stage long-short-term memory neural network sub-model, the prediction reliability under the complex working condition is improved, and the accuracy of landing gear load prediction is improved.

This invention proposes a deep learning-based visible light-infrared modal target detection method, belonging to the field of infrared detection. The method includes: obtaining a visible light image or infrared image to be detected; inputting the visible light image or infrared image into a convolutional neural network to obtain original visible light image features or original infrared image features; inputting the original visible light image features or original infrared image features into a corner attention module to extract visible light corner features or infrared corner features; inputting the original visible light image features or original infrared image features into a neighborhood attention module to extract visible light edge features or infrared edge features; inputting the extracted features into a trained YOLO target detector, which outputs the target type, confidence score, and bounding box position, and outputs the final target detection result. This invention effectively improves the ability to find general target features, while enabling the model to learn more robust feature representations, thus enhancing the model's generalization ability.

The invention discloses a scheduling strategy determination method and device of a power distribution system and electronic equipment. The method comprises the following steps: acquiring multi-source heterogeneous data related to a power distribution system; associating the multi-source heterogeneous data by taking the target type data as a link to obtain multi-source fusion data; predicting a plurality of target scenes corresponding to the power distribution system according to the multi-source fusion data; according to the multi-dimensional scene evaluation indexes, respectively determining corresponding multi-dimensional scene evaluation indexes of the power distribution system in the plurality of target scenes; according to the plurality of multi-dimensional scene evaluation indexes, determining whether to update a first update result of the plurality of target scenes; and determining scheduling strategies of the power distribution system in the plurality of target scenes under the condition that the updating result is not updated. According to the invention, the technical problem that it is difficult to timely deal with various conditions and make corresponding scheduling strategies in related technologies is solved.

The present disclosure relates to the fields of large model technology and text processing. Disclosed are file processing methods, an electronic device, a storage medium and a computer program product. A method comprises: in response to an input instruction acting on an operation interface, displaying on the operation interface a file to be processed, said file containing text to be processed of at least one modality; and, in response to a processing instruction acting on the operation interface, displaying a processing result on the operation interface, the processing result being used for representing that said file has been successfully named and stored on the basis of a target processing rule, the target processing rule being a processing rule corresponding to a target type of said file, the target type being determined by comparing said text with preset text contained in a plurality of preset files, and the types of different preset files being different. The present disclosure solves the technical problem in the prior art of relatively low file processing accuracy.

The invention relates to a road risk early warning method and system based on radar-video fusion, and belongs to the technical field of road traffic safety, and the method comprises the steps: collecting multi-source data through a radar, a video and a meteorological sensor, carrying out the denoising of a radar point cloud through a meteorological self-adaptive dynamic density clustering algorithm, and carrying out the early warning of a road risk. Performing weather compensation on the video features by using a generative adversarial network; through a space-time diagram neural network and an attention mechanism, performing high-precision fusion and complementation on the radar and the visual trajectory to generate a unified trajectory with multi-dimensional attributes such as target type, speed, behavior characteristics and the like; and calculating an interaction risk probability of a target and an environment based on a Bayesian network, and realizing graded early warning through a dynamic threshold value of reinforcement learning optimization. According to the method, the target sensing reliability in severe weather, the track continuity in a complex scene and the self-adaptive capability of risk assessment are effectively improved, and continuous optimization of system performance is realized through a federated learning framework.