51results about How to "Effective tracking" patented technology

The invention discloses a pollution discharge license post-license management method and system based on environmental compliance management, and particularly relates to the technical field of environmental management. Primary pollutants and secondary pollutants generated by the primary pollutants are determined according to the types of pollutants discharged by an enterprise, and a simulation model is constructed and corrected to predict pollutant conversion rates in different environments, monitor the concentration of the secondary pollutants, calculate the generation rate and evaluate the tracking stability of equipment to the generation process. Comparing the equipment data with the predicted generation rate, analyzing the tracking capability and response delay of the equipment, determining the real-time level of the equipment in combination with fuzzy logic, and dividing the data into real-time pollution data and non-real-time pollution data; real-time data is continuously collected, a supervision department monitors the emission dynamic state in real time, the pollution discharge compliance is judged, the abnormal degree of non-real-time data is analyzed, the monitoring frequency is adjusted, the timeliness and accuracy of the data are ensured, the problem of combined pollution is effectively solved, and the supervision capacity for pollutant generation and emission is improved.

The invention discloses a data management system based on a monitoring video stream, belongs to the field of data analysis, and aims to solve the problems of camera connection acquisition, image quality optimization, pedestrian related information analysis and data storage retrieval and backup in video monitoring. The system comprises a data acquisition module, a target detection module and a data storage module. The data acquisition module is used for identifying and connecting a video monitoring camera, performing video stream data acquisition, adjusting an acquisition frame rate by estimating a data size, and evaluating and optimizing image quality to obtain a detection image data set; the target detection module is used for carrying out feature extraction, classification and marking on pedestrians in the detection image data set, recording pedestrian trajectory information, carrying out real-time tracking and updating, identifying a behavior mode according to the trajectory information, dividing a gathering area and obtaining the pedestrian flow; and the data storage module is used for classifying and labeling the data, constructing an index structure to guarantee efficient retrieval, dividing data grades according to multi-dimensional features, and dynamically adjusting a backup time interval.

The invention discloses a target tracking method and system based on visual identification and an underwater robot, and relates to the technical field of underwater robots. According to the invention, automatic tracking and monitoring of an underwater target are realized by using a visual identification technology, operations such as an image identification technology of YOLOv5, a motion tracking technology of an optical flow and a Kalman filter, a target re-identification algorithm of deep learning, image enhancement and the like are specifically combined, and the intelligent level and the working efficiency of underwater operation are comprehensively improved. According to the method, the diver can be efficiently tracked in a complex underwater environment, and high recognition and tracking precision is ensured under the condition that the diver disappears or the motion trail is complex.

The invention relates to the technical field of permanent magnet synchronous motor control, in particular to a diagnosis-free adaptive fault-tolerant control method and system for a six-phase permanent magnet synchronous motor under an open-circuit fault, and discloses the following steps: S1, converting the voltage and current of the six-phase permanent magnet synchronous motor from a three-phase static coordinate system to a two-phase static coordinate system through Clark conversion, voltage and current in the two-phase static coordinate system are converted into a two-phase synchronous rotating coordinate system through Park conversion; s2, acquiring a current relation between q-axis current of the six-phase permanent magnet synchronous motor and the two-phase static coordinate system according to the two-phase synchronous rotating coordinate system, and further acquiring two-phase static coordinate system reference current for realizing fault tolerance under an open-circuit fault; and S3, optimizing the control signal of the reference current through a phase-locked loop of a second-order generalized integrator. According to the method, diagnosis-free adaptive fault-tolerant control under the open-circuit fault of the six-phase permanent magnet synchronous motor can be realized, and the problems of misdiagnosis and time delay are reduced.

The invention discloses a brain-computer interface system based on audio-visual matching error monitoring, which is characterized in that: according to EEG data obtained by three feedback paradigms of audio-visual matching errors, important ERP components related to the audio-visual matching errors are extracted by applying ERP analysis, so that neural responses in a specific time window are interpreted; then, on the basis of time-frequency analysis, dynamic changes of the electroencephalogram signals in different wave bands are captured, and the reliability and stability of the electroencephalogram activity in different feedback modes are revealed by combining ITPC of the electroencephalogram activity; and finally, through an improved EEGNet model, automatic feature extraction and efficient classification of the signals are realized, and the robustness and generalization ability of the system are improved. The electroencephalogram signals have high nonlinearity and specificity, by combining ERP analysis, time-frequency analysis and a deep learning model, potential neural mechanisms of audio-visual matching errors can be more effectively understood, the performance of a brain-computer interface system is improved, and the method is applied to clinical research of error processing related obstacles.

The invention discloses an anti-shielding single-target long-time tracking method and system combined with trajectory prediction, and the method comprises the steps: firstly, manually appointing the position and size of a target, determining a region needing to be tracked, carrying out the feature extraction of the target region, and mapping a feature vector to a high-dimensional feature space, thereby obtaining an initial target template; according to the feature information of the initial target model, positioning a target in a tracking area, calculating the similarity between a target candidate area and an initial target template, selecting the most probable target position, entering a search state when the target is shielded by combining a shielding judgment algorithm, and performing prediction by using historical trajectory data of the target; and dynamically updating the template information of the target according to the obtained target position in combination with the current state and motion condition of the target. The system comprises a target initialization module, a target positioning module and a target template updating module. According to the invention, the target search range can be updated in real time to realize accurate and stable long-time target tracking.

The invention discloses an adaptive coagulation nerve tracking control method for a nonlinear space-time system. The method comprises the following steps: establishing a mathematical model of the nonlinear space-time system and a tracking signal; constructing a coagulation neural network, approximating the nonlinear space-time uncertainty of an open-loop error system into a form of multiplying a coagulation weight by a network base vector, and representing bias input by time-varying disturbance and space-time approximation errors; and constructing a Lyapunov function, counteracting residual bias terms based on a sliding-mode-like smooth function, and designing a virtual control law, a parameter adaptive law and a controller on the basis of a backstepping method. The control scheme designed based on the method can realize effective tracking of any micro-traceable signal by a nonlinear space-time system, and ensures an adjustable bounded tracking error. Meanwhile, when adjustable parameters in the sliding mode function meet the square integrable condition, the tracking error is gradually converged to zero.

The invention discloses a low-complexity channel estimation method and device based on an MIMO system, and the method comprises the steps: recovering a complete matrix through an approximate low-rank matrix, carrying out the singular value decomposition of the complete matrix, building a large-scale spatial multiplexing MIMO system model, carrying out the conversion processing of a received signal on a kth antenna, and obtaining a transmission signal estimation value, and performing channel matrix recovery on the transmission signal estimation value by using an approximation algorithm to obtain a channel matrix estimation value, finally performing signal detection on the channel matrix estimation value by using a zero-forcing technology, and performing iterative updating to obtain an optimal transmission signal estimation value, thereby effectively reducing the algorithm complexity and effectively reducing the calculation amount. The estimated channel matrix is effectively equivalent to the complete channel matrix, and the channel matrix is updated through iterative updating, so that the dynamic change of the channel can be effectively tracked, and the final demodulation signal precision is ensured.

The invention relates to a sea area management and control early warning evidence obtaining method based on video intelligent analysis, and the method comprises the steps: collecting equipment parameters: collecting internal and external parameters of equipment and environment parameters; equipment screening control is carried out, controllable and controllable equipment with a good detection effect is selected through equipment state analysis and target detection effectiveness analysis, and follow-up monitoring of a target area is realized through pan-tilt control; performing video intelligent analysis, determining a follow-up concerned target through mapping matching of a video intelligent analysis model and different coordinate system positioning information, and performing accurate linkage and video snapshot by fine tuning equipment; according to early warning and evidence obtaining association, structured attribute analysis is performed on a target and an area detected in a video capturing process, and an evidence obtaining result is added to early warning information with an association relationship, so that repeated evidence obtaining is avoided. According to the invention, the accuracy and efficiency of early warning evidence obtaining can be effectively improved, the utilization efficiency of data and resources is improved, and powerful technical support is provided for sea area management and control.

The invention provides a dynamic scene positioning and mapping method and related equipment, and the method comprises the steps: determining an RGBD image, carrying out the target detection and feature point extraction of the RGBD image, and determining a target object and a static feature point; determining a 3D bounding box according to the target object, and determining a dynamic pose according to the 3D bounding box and the RGBD image; calculating a depth pyramid and an image pyramid according to the RGBD image; according to the depth pyramid and the image pyramid, performing camera pose estimation through an optical flow tracking method, and determining a camera pose; and according to the static feature points, the dynamic pose and the camera pose, performing positioning and map construction.

The invention discloses a clinical test ethical examination system which comprises a submission application end, an examination process management end, a file management end, an examination cooperation end, an examination recording and tracking end, a notification and reminding end, an ethical examination report generation end, a data analysis and statistics end and a privacy and security end which are in data communication through a private network and a private line network. The clinical test ethical examination system aims at simplifying and optimizing management and processes of ethical examination, researchers can more effectively manage and track the ethical examination process through the clinical test ethical examination system, it is ensured that tests meet ethical principles and related regulation requirements, the rights and interests of test participants are protected, and the clinical test ethical examination system has the advantages that the research efficiency is improved, and the research cost is reduced. And the proceeding and development of scientific research are promoted.

The invention belongs to the technical field of robot teleoperation and haptic interaction, and provides a multi-mode force feedback control method and system for nuclear facility robot operation, and the method comprises the steps: collecting the state information of a master arm and a slave arm in real time, and dynamically scheduling a haptic calculation strategy according to a task state; a fast estimation strategy is enabled in the fast transit mode. Further, real environment interaction force is obtained based on dynamic model compensation and net interaction force extraction; combining the dynamically selected multi-mode force feedback parameters, and synthesizing and outputting a touch instruction to the main arm. Meanwhile, admittance correction and feed-forward compensation are carried out on a slave arm motion instruction through net interaction force and dynamic internal force, synchronous output is carried out after safety optimization, and the slave arm is controlled to move. The problems of poor task adaptability, force sense distortion and insufficient safety in nuclear facility teleoperation are solved, and intelligent, high-fidelity and safe robot teleoperation is achieved.

This invention relates to the fields of machine learning and edge computing technology, specifically to a blockchain-based trusted distributed hybrid expert model edge computing system. The system includes a task publisher for publishing learning tasks, which may be training or inference tasks; a blockchain network for receiving learning tasks and evaluating expert weights to obtain sparse activation expert index results; a blockchain network for receiving learning task processing results from the edge layer and achieving consensus; a gating network deployed within the blockchain network; an edge layer for downloading the corresponding expert model from the storage layer based on the sparse activation expert index results to process the learning tasks and uploading the processing results to the blockchain network; and a storage layer for storing all expert networks, each with a CID. This invention significantly improves the defense capability of the distributed MoE network against malicious edge node data tampering attacks, thereby ensuring the learning performance of the MoE system.

The present invention provides a Kalman filter parameter setting method, device, electronic device and storage medium. The method comprises: obtaining the variance between the angular velocity measurement value and the true angular velocity value measured by the MEMS gyroscope when the MEMS gyroscope is at different angular velocities, and establishing a first mathematical relationship for characterizing the mapping relationship between the true angular velocity value and the variance; when the angular velocity data collected by the MEMS gyroscope is filtered in real time using the Kalman filter algorithm, the measurement noise variance at the current moment is determined based on the angular velocity estimation value at the previous moment output by the Kalman filter algorithm and the first mathematical relationship, so as to determine the angular velocity estimation value at the current moment based on the measurement noise variance at the current moment. The present invention can reduce the amount of calculation in the Kalman filter parameter setting process and effectively track the dynamic performance of the MEMS gyroscope.

The utility model relates to communication field discloses a kind of unmanned aerial vehicle signal receiving device and communication base station, unmanned aerial vehicle signal receiving device includes: body, body includes processor;With the first omnidirectional antenna, second omnidirectional antenna and third omnidirectional antenna of body connection, wherein the angle between the first omnidirectional antenna, second omnidirectional antenna and third omnidirectional antenna is in the range of 60 degrees to 120 degrees.The utility model can ensure that the antenna lobe diagram after superposition is close to spherical by the combination of at least three omnidirectional antennas arranged in different directions, so as to reduce the detection blind area, expand the detection range, to realize the effective tracking and supervision of unmanned aerial vehicle.

The invention relates to the technical field of self-adaptive wave trap groups, in particular to an improved cascade structure self-adaptive wave trap group and an instantaneous frequency detection method thereof, which can overcome the respective defects of CANFB, TCANFB and PPANFB and realize more efficient multi-frequency detection. According to the invention, the method is a series-parallel adaptive wave trap group (Cascade Pre-filled and Parallel Update ANFB, CPANFB), the calculation efficiency is high, and the calculation amount is obviously reduced while the detection precision is ensured; compared with the PPANFB, the CPANFB does not need to accurately set an initial value, so that the robustness and adaptability of the system are enhanced; by optimizing the design of pre-filtering and main filtering, the CPANFB can maintain high frequency estimation precision in various signal-to-noise ratio environments.

The invention discloses a clamping device and an automatic bearing disc carrying device. The clamping device is used for clamping at least one bearing disc. The clamping device comprises a fixing piece, a fixing frame, a first buckling piece, a second buckling piece, an actuating element and an abutting assembly. The fixing frame is fixed to the fixing piece. The first buckling piece and the second buckling piece are connected to the two opposite sides of the fixing piece and arranged in the first direction. The actuating element is configured to actuate the first buckling piece and the second buckling piece to move face to face and back to back in the first direction. The pressing assembly comprises two pressing rods, two pressing parts and a pivoting part. The two pressing rods are connected to the fixing frame. The two abutting parts are connected to the ends, away from the fixing frame, of the two pressing rods respectively and are configured to abut against at least one bearing disc. The pivoting part is located between the fixing frame and the two abutting parts. The two pressing rods are pivoted to the pivoting part. According to the method, the existing framework of the existing final test classification processor in a factory does not need to be additionally modified, so that the import cost can be greatly reduced.

The application discloses a method for electronic countermeasure cooperative jamming suppression in a frequency offset scene, which comprises the following steps: S1. At the jammer, after the interference data x(n) is converted by a digital-to-analog converter and up-converted, a transmission jamming signal is generated and transmitted; S2. At the authorized receiver, after the jamming signal is transmitted through a wireless channel, the jamming signal is received simultaneously with an expected signal, down-converted to obtain a baseband receiving signal, and analog-to-digital converted to obtain a baseband digital signal; S3. The baseband receiving signal is expressed in a matrix form; S4. The fast-changing cooperative jamming joint channel coefficient is estimated, and the cooperative jamming is reconstructed and cancelled to complete the interference suppression. The application can effectively cancel the cooperative jamming under a frequency offset multipath channel, and does not need to accurately estimate the frequency offset value, but sets a frequency offset value interval, and uses multiple adaptive recursive filters in parallel to estimate the cooperative jamming coefficient.

This method for managing competition platforms based on collaborative code hosting platforms includes the joint collaboration between the regular competition platform user system and the code hosting platform user system, as well as the creation and permission management of code hosting platform repositories. The joint collaboration between the regular competition platform user system and the code hosting platform user system includes: S1. Accessing the code hosting platform user system, including two basic operations: user registration and user login and binding; S2. Processing existing users. The code hosting platform repository creation and permission management includes: maintaining the code hosting platform repository permission list; submitting competition code from the code hosting platform repository address; and managing read permissions and open-source permissions. This method can simultaneously improve the efficiency of participating users, expert judges, and platform administrators, which is of great significance for promoting the vigorous development of online scientific research competitions.

The present disclosure relates to a wafer classification method and device, electronic equipment and computer readable storage medium, and belongs to the technical field of semiconductor production and manufacturing, and can be applied to the scenario of classifying wafers. The method comprises: obtaining associated information of a wafer to be classified; the associated information comprises repair circuit information of the wafer to be classified and historical reference wafer information corresponding to a historical reference wafer; and based on the repair circuit information and the historical reference wafer information, the wafer to be classified is compared with the historical reference wafer one by one to obtain a current wafer category; the current wafer category comprises a current reference wafer and a current abnormal wafer. The present disclosure can quickly classify wafers according to the repair circuit information of the wafers to provide subsequent problem tracking of failed wafers.

The present invention discloses a low-altitude bird detection method and system based on radar optoelectronic information fusion, which simultaneously uses radar equipment and optoelectronic equipment to track low-altitude bird targets in real time, and matches and fuses the radar track and the optoelectronic track to obtain a fused track, that is, the bird track. First, the radar track and the optoelectronic track are aligned in time and converted to the same coordinate system, and then the radar track and the optoelectronic track are cyclically found to match and fuse the radar track and the optoelectronic track that meet the matching judgment conditions to obtain a fused track. Then, as time goes by, the fused track is updated according to the radar track and the optoelectronic track at the next moment, that is, the time t+1, to complete the real-time tracking of low-altitude bird targets. For the two tracks at the next moment, that is, the time t+1, there will be a situation where there is no matching fusion, and these remaining tracks are re-matched and fused to generate a new fused track to ensure the continuity and real-time nature of the fused track information.

The present invention provides a planar image tracking method, a terminal and a storage medium. The logic control system generation method includes: S101: obtaining the global pose of the first three frames of images and the relative pose between two adjacent frames of images according to the corresponding relationship of the feature points of the target image in the first three frames of images, and obtaining the 3D coordinates of the feature points; S102: calculating the global pose of each frame of images after the first three frames of images and the relative pose between two adjacent frames of images according to the 3D coordinates, and optimizing the global pose and 3D coordinates; S103: respectively calculating the relative pose through the feature points and the global pose of the two adjacent frames of images, optimizing the relative pose according to the error of the relative pose, obtaining the optimal global pose through the relative pose, and using the global pose for real-time tracking. The present invention avoids the problem of using a large number of parameters for calculation and increasing the amount of calculation, has low requirements on hardware, realizes efficient and stable tracking of images, and reduces the cost of motion tracking.

The utility model discloses a kind of energy storage load tracking control architecture, it is related to energy storage control technical field, comprising: alternating current incoming line side's current sampling sensor;Power electronic converter, with external current voltage sampling interface;The power electronic converter obtains the current signal of alternating current incoming line side in real time by the external current voltage sampling interface, and carries out real-time tracking control, realizes load tracking and prevents reverse flow function, the architecture is suitable for the multi-source fusion system including photovoltaic, charging pile, wind energy, diesel generator at least one, the system tracks single-phase and three-phase load change in the process of charging, discharging. The energy storage load tracking control architecture, by increasing current sampling sensor in alternating current incoming line side and increasing sampling interface for PCS, control function is decentralized to PCS, so that the dynamic response speed of system is greatly improved.

The embodiment of the invention provides a three-dimensional model target tracking method, which comprises the following steps: acquiring current frame three-dimensional model data, previous frame three-dimensional model data and a previous frame three-dimensional target frame, and carrying out data preprocessing to obtain a preprocessing result, the preprocessing result comprising a space-time three-dimensional model and confidence; the preprocessing result is processed through a Transform network, local features are generated, and the local features comprise the features of the previous frame and the features of the current frame; inputting the space-time three-dimensional model into a PointNet network model to generate a global feature; fusing the local features and the global features to obtain fused features; inputting the fusion features into an MLP layer for processing, and generating a target three-dimensional model; and on the basis of the target three-dimensional model, predicting the relative position offset from the previous frame to the current frame through motion prediction, and positioning the target three-dimensional model on the basis of the relative position offset to obtain a three-dimensional target frame of the current frame. And a self-attention mechanism of the Transform network is utilized, so that the method is more adaptive to the three-dimensional model. Global information and motion information are integrated, so that the accuracy of target identification and the stability of tracking are improved.

The application provides a PLC device alias identification and online authorization method and system. A device alias mapping network is constructed based on a red-black tree to record original PLC devices and corresponding original model information. The system generates an authentication code according to the original model information of the customized device. A user inputs the authentication code and obtains a user PLC device customized model. The original PLC device is upgraded to the customized model by using a firmware upgrade tool. A server randomly generates a salt value. The PLC device performs MD5 encryption on the randomly generated salt value and a unique identifier. The encryption result is used as a complete salt. The PLC device model and manufacturer information are MD5 encrypted as an authentication password. The verification information is AES encrypted. The encrypted verification value is compared and verified. If the verification information is consistent, the authorization is passed. The application can quickly release new device models, reduce operation and maintenance costs, and reduce the waiting time for repeated packaging tests.

The application provides a kind of detection method, device and electronic equipment based on unmanned aerial vehicle for water sports object, which comprises obtaining visible light image, infrared image and radar image by using unmanned aerial vehicle;Visible light image, infrared image and radar image are fused to obtain three-dimensional scene model;Based on three-dimensional scene model, water body boundary contour is extracted, and water area range is determined according to water body boundary contour;The geometric features and texture patterns of the preset water target are obtained, and whether the preset water target exists in the water area range is detected based on the preset target detection algorithm;When the preset water target exists in the water area range, the flight of the unmanned aerial vehicle is controlled according to the motion state of the preset water target.It can better adapt to environmental variables, and can make real-time decisions according to the motion of the target, effectively track, and thus make the detection of water target more accurate.

The invention is suitable for the technical field of computer vision and information security, and provides a face counterfeiting detection positioning and implicit identity tracing method, which comprises the following steps of: extracting multi-modal features through three parallel branches of RGB (Red, Green, Blue), frequency domain and noise; carrying out dynamic weighted fusion on the extracted multi-modal features to generate a fusion feature map; introducing a generalization forgery detection adapter, utilizing a pre-training visual language model CLIP to construct an external general forgery knowledge cache, and performing adaptive linear fusion with an original discrimination result; training a ViT model through comparative learning to distinguish background features, and constructing a background feature library corresponding to the identity tag; and extracting background features of the query image, carrying out similarity calculation on the background features and the feature library, sorting, and finally determining the implicit identity of the query image. The method is accurate in forgery positioning, strong in robustness and strong in cross-domain generalization ability, has identity traceability, and provides a feasible technical scheme for comprehensive treatment of deep forgery contents.

The invention discloses a method for identifying a risk account of a decentralized social media platform, which comprises the following steps of: acquiring data of the decentralized social media platform, converting a data set comprising nodes and side information into a heterogeneous graph, preliminarily calculating statistical characteristics of different types of account nodes, and calculating the risk account of the decentralized social media platform; the features of nodes and neighbor nodes are fused through a graph neural network, more accurate feature embedding representation is obtained, and finally, a classification model is input to obtain a risk classification result of a platform account. According to the method, illegal contents in a social platform can be intensively supervised and a risk propagation chain can be tracked; the problem that account behaviors are difficult to monitor and manage due to anonymity and decentration can be completely monitored and solved.

The present invention discloses a target monitoring method, device, terminal and medium, the method comprising: based on a preset event camera, obtaining multimodal perception data, wherein the multimodal perception data includes optical modal data and radar modal data; inputting the optical modal data and the radar modal data into a multimodal fusion module for multimodal fusion, respectively, to obtain enhanced point cloud features after fusion; based on the enhanced point cloud features after fusion, determining the object bounding box and its corner points of the moving target, and determining the degree of freedom information of the moving target based on the corner points of the object bounding box, so as to realize the monitoring of the moving target. The present invention can realize the monitoring of small targets moving at high speed, and use multimodal perception fusion technology to improve the recognition accuracy and robustness of moving targets.

The utility model belongs to the technical field of warehouse management, and discloses a vertical transportation and warehousing system for semi-finished steel bar products for railroad bridges, which comprises semi-finished product boxes of various specifications with the same width but different lengths, an AGV (automatic guided vehicle) trolley for transporting the semi-finished product boxes and a vertical warehousing shelf for storing the semi-finished product boxes, a conveying belt is arranged in the middle of the vertical storage goods shelf, a storage platform and a delivery platform are correspondingly arranged at the two ends of the conveying belt respectively, the vertical storage goods shelf comprises a plurality of layers of placing frames arranged at equal intervals, each layer of placing frame comprises a plurality of placing plates with a plurality of lengths, and the lengths of the placing plates are gradually increased in sequence in the direction from the storage platform to the delivery platform. According to the reinforcing steel bar semi-finished product vertical transportation and warehousing system for the railway bridge, semi-finished product storage and material box transportation are completed by designing semi-finished product material boxes of different sizes.