22results about How to "Real-time extraction" patented technology

The invention discloses a BIM-based building full life cycle compliance inspection system and method, and the system can be integrated into each process of a building project, automatically and accurately extracts key data of a plurality of stages, such as design, construction, operation and maintenance, from a BIM model in real time, and forms a complete information chain of the full life cycle of the building project. The system realizes comprehensive coverage of multiple stages of building design, construction, operation and maintenance and the like; in the design stage, the system can assist a designer in compliance review and discover and correct design defects in advance; in the construction stage, the system can monitor the construction progress and quality in real time, and the compliance of the construction process is ensured; in the operation and maintenance stage, the system can continuously monitor the operation state of the building facilities, timely maintenance suggestions and early warning information are provided, and long-term compliance operation of the building project is guaranteed; the comprehensive, efficient and accurate compliance inspection mode provides powerful guarantee for smooth promotion and successful delivery of the construction project.

The invention discloses an engine multi-mode operation identification method and device based on a multi-dimensional internet of things, and a medium, and aims to solve the problem that the driving state cannot be obtained in time due to inaccurate engine monitoring data. According to the method, multiple key parameters in operation of the engine can be comprehensively covered through different types of sensors, rich information basis is provided for multi-modal operation identification of the engine through multi-dimensional data collection, rich feature data is extracted from the multiple sensors, time domain, frequency domain and time frequency features are covered, and the method is suitable for multi-modal operation identification of the engine. Through construction of a multi-modal operation identification model, data of a plurality of sensors can be comprehensively considered, a neural network model is used for training, and a cross validation method is used for model verification, so that the stability and generalization ability of the model are ensured; and the state of the engine is quickly judged according to the multi-mode operation identification model, so that real-time monitoring and early warning of the state of the engine are realized.

The invention relates to the technical field of neural microelectrodes, and provides a stent electrode which comprises a deformation part, the deformation part is provided with wire bodies which are interwoven to form a net structure, an electrode is arranged at the interwoven position of the net structure, and the electrode is communicated with a conductor. And the conductor is laid on the deformation part and is led out of the deformation part from the edge of the deformation part. The invention further provides a preparation method of the stent electrode. The electrodes are arranged on the deformation part, the limitation of the number of the electrodes can be broken through, a higher channel can be formed, the conductors used for leading out electrode signals are arranged on the deformation part, conductor wiring is simple, and mutual entanglement of wires can be avoided; the electrode bracket is manufactured by adopting an integrated preparation process, so that the electrode and the conductor can be integrated, and the sizes of the electrode and the conductor can be adjusted according to specific clinical requirements.

The invention provides an attention-fused remote sensing image road information extraction method and device, and the method comprises the steps: obtaining an original remote sensing image, carrying out the multi-scale feature extraction and global pooling of the original remote sensing image, obtaining the multi-scale local features and global pooling features, and carrying out the global pooling of the multi-scale local features and the global pooling features; fusing the multi-scale local features and the global pooling features by adopting an attention mechanism module to form shallow attention fusion features; different weights are given to the shallow attention fusion features, layered dynamic weighted stacking is carried out, deep attention fusion features in a dynamic weighted stacking result are extracted by using a convolution attention module, and the shallow attention fusion features and the deep attention fusion features are subjected to jump connection to obtain remote sensing image road information. Wherein the convolution attention module calculates a dynamic weighted combination loss value by using a BCE loss value and a Dice loss value, and adjusts model parameters based on the dynamic weighted combination loss value. According to the scheme, the feature information extraction efficiency and extraction precision are improved.

The present invention provides a point cloud depth acquisition method based on normal projection, which performs voxel processing on the digital model of the object to be measured, and stores it and the three-dimensional point cloud in a unified coordinate system; obtains the contour of the feature area and the center position coordinates; stores the point cloud in the feature area into a point set I; obtains the three-dimensional coordinates A of the center position coordinates; uses the three-dimensional coordinates and the camera optical center point to determine as the incident light; obtains the normal vector A at the intersection of the incident light and the digital model; projects the point set I onto the normal vector A, and records the maximum distance between the two projection points as the depth of the feature area; the method is not affected by the surface morphology of the object to be measured, has the characteristics of high accuracy, high efficiency and convenience, and can extract the surface depth information of the object to be measured with any morphology in real time.

The invention provides an airborne cloud precipitation particle measuring instrument which comprises a probe cabin with an elliptical cross section, the top end of the probe cabin is located on one side of an elliptical long axis perpendicular to the cross section, a first supporting arm and a second supporting arm which are oppositely arranged are fixed to the top end, and a fixing seat is arranged on one side face of the probe cabin; reflective mirror cover plates inclined inwards by 45 degrees are arranged on the outer walls of the free ends, away from the probe bin, of the first supporting arm and the second supporting arm, windows are arranged between the top ends of the inner walls of the free ends and the outer edges of the tops of the reflective mirror cover plates, and window glass is fixed through window glass pressing rings; a 45-degree reflector is mounted on the inner side of the reflector cover plate; a laser assembly is arranged in the first supporting arm; a lens group and a camera are arranged in the second supporting arm. The lens group is located at a light inlet of the camera. The overall modeling of the device is streamline, wind resistance is reduced, collision and breakage of particles are reduced, the device has high precision and reliability, and real-time, high-speed and three-dimensional measurement and synchronous extraction of cloud precipitation particles can be achieved.

The present invention discloses a method for predicting silicon content in molten iron based on TD-LightGBM, and belongs to the technical field of industrial process monitoring. The method comprises: first, using the decision tree model structure of a lightweight gradient booster to judge the importance of the feature according to the number of times the feature is used to segment training data; then, combining a time difference algorithm to establish a dynamic feature extraction model; finally, using a local weighted algorithm to establish a local model based on the Euclidean distance between samples. Predicting the silicon content in molten iron during the ironmaking process based on this model can effectively remove redundant items and drift phases in the blast furnace environmental parameters. Compared with the existing prediction scheme for silicon content in molten iron, the present invention further improves the accuracy of the prediction.

The application discloses a network information collection method and system based on real-time text analysis, comprising the following steps: acquiring real-time text data, preprocessing the real-time text data, acquiring first data and second data according to the preprocessed real-time text data, calculating the similarity of the first data and the similarity of the second data, weighting the similarity of the first data and the similarity of the second data to obtain a classification target, constructing a text classification model according to the classification target, inputting the real-time text data into the text classification model to obtain classification data, and outputting the classification data as collected network information. The method can not only improve the accuracy of network information collection, but also has good interpretability and can be directly applied to a network information collection system.

The present invention provides an onboard flood data processing method, device and system based on the aviation emergency mode, the method comprising: based on the ground observation image, performing image mosaicking to obtain the target image; inputting the target image into the water body recognition model to obtain the water body recognition result; based on the water body recognition result and the geographic information data, performing spatial analysis to obtain the comprehensive flood analysis information; when the aircraft lands, the comprehensive flood analysis information is sent to the remote terminal, so that the remote terminal receives the comprehensive flood analysis information, makes a preliminary judgment on the disaster situation, and guides the generation of rescue command decisions. The onboard flood data processing method, device and system based on the aviation emergency mode provided by the present invention can realize the splicing, correction, information extraction and the like of flood data in real time and quasi-real time on board during the flight, and transmit the information to the ground command system after the aircraft lands, so as to improve the efficiency and timeliness of information processing, which is of obvious significance to emergency rescue.

The invention discloses a harmonic suppression method and system under a high background harmonic condition, and the method comprises the steps: carrying out the wavelet transformation of an input power grid voltage signal, and extracting the amplitude information of each harmonic in real time; dynamically determining a target harmonic set which needs to be suppressed at present through a preset threshold judgment mechanism according to the extracted amplitude information of each harmonic; for each harmonic in the target harmonic set, synchronously executing harmonic suppression and phase compensation operation; sending the signal subjected to harmonic suppression and phase compensation into a phase-locked loop to obtain a power grid synchronous phase; the system provided by the invention comprises an extraction module, a determination module, a compensation module and a suppression module, and provides a highly purified input signal for the phase-locked loop, so that the phase-locked loop can still maintain rapid and overshoot-free high-precision phase locking under serious harmonic pollution; and the operation stability and the electric energy quality of the grid-connected inverter in a complex power grid environment are remarkably improved.

The invention provides an intelligent detection and classification method and system for dendrobium officinale diseases and insect pests, and relates to the field of data processing, and the method comprises the steps: obtaining a plurality of pieces of sample data; based on the multiple sample data, establishing an optical flow calculation model, a feature extraction model and a pest and disease classification model; obtaining 3D point cloud data of the dendrobium officinale based on a three-dimensional reconstruction technology according to the three-dimensional data of the dendrobium officinale; through an optical flow calculation model, according to the two-dimensional image sequence of the dendrobium officinale, determining optical flow information of the dendrobium officinale; according to the 3D point cloud data and the optical flow information of the dendrobium officinale, whether an optical flow generation area exists in a leaf area of the dendrobium officinale is judged; if yes, extracting image features of the dendrobium officinale from the two-dimensional image sequence of the dendrobium officinale through a feature extraction model; the pest and disease damage type of the dendrobium officinale is determined through the pest and disease damage classification model according to the image features and the optical flow information of the dendrobium officinale, and the method has the advantage of improving the detection and classification efficiency and accuracy of the pest and disease damage of the dendrobium officinale.

The present application provides a real-time coastline extraction method, which belongs to the field of scene perception and learning technology, and specifically includes the following steps: step 1, based on existing coastline annotation; step 2, training and test data generation, the training data includes coastline annotation map and coastline unlabeled map, and the test data includes coastline annotation map and coastline unlabeled map; step 3, deep learning network construction and training based on semantic segmentation; step 4, using the coastline extraction network to realize real-time coastline extraction of test data. Through the processing scheme of the present application, real-time coastline extraction is realized in complex land and sea scenes.

The present invention relates to the field of intelligent control technology, specifically to a control method, device, equipment and medium for a rotating structure, wherein the method is: obtaining the sound information and somatosensory information of users in the current venue in real time, setting an initial monitoring area; obtaining the number of users in the current venue, setting a user label for each user and associating them; analyzing the expression information included in the sound information of each user and setting a corresponding weight coefficient; dividing the initial monitoring area into multiple sub-areas and adjusting the size and position of the initial monitoring area; extracting specific instruction information from the sound information and somatosensory information, obtaining the corresponding instruction action in the specific instruction information, associating the instruction action with the corresponding user label; based on the weight coefficient and the instruction action, controlling the rotating structure to perform the corresponding action. The present application can extract specific instruction information in real time and dynamically adjust the control strategy, making the operation of the rotating structure more accurate and intelligent, thereby optimizing the overall user experience.

The invention discloses an infrared angiography and recognition method and system, and relates to the technical field of medical images. According to the blood vessel recognition method, the blood vessel signal features of the human body are analyzed according to the infrared image information of the target human body, and then the blood vessel signals are subjected to filtering, denoising, white balance, ROI extraction, local adaptive enhancement, binaryzation, edge extraction and blood vessel segmentation, so that the defects in the prior art are overcome, and the blood vessel recognition efficiency is improved. According to the method, extraction and segmentation of complex blood vessel signals are realized, especially blood vessel extraction under the complex conditions that the blood vessel signals are weak, the signal-to-noise ratio is low, interference is large, the blood vessel signals are not straight, and the blood vessels are thick and thin, the blood vessel signal extraction efficiency and accuracy are greatly improved, automatic and intelligent image recognition and segmentation of the blood vessels are realized, and the blood vessel extraction efficiency is improved. And the method becomes a functional basis of blood vessel intelligent and automatic application scenes (such as blood vessel puncture).

The invention provides a frequency band detection method of an OFDM (Orthogonal Frequency Division Multiplexing) communication system and related equipment. The method comprises the following steps: performing sliding discrete Fourier transform on a received signal sampling sequence to obtain sliding discrete Fourier transform output corresponding to each subcarrier index; constructing a frequency band energy sequence of each candidate frequency band based on the sliding discrete Fourier transform output; defining an adaptive threshold value of each candidate frequency band based on the noise statistical parameter of each candidate frequency band in the preset noise interval; constructing a detection window based on the obtained window starting position; based on the frequency band energy sequence of each candidate frequency band, calculating the detection statistics of each candidate frequency band in the detection window and the corresponding confidence; and if the detection statistical magnitude is greater than the adaptive threshold and the confidence coefficient is greater than a preset confidence coefficient, determining each candidate frequency band as an effective communication frequency band. According to the invention, low time delay, low power consumption and accuracy of communication frequency band detection in the OFDM communication system can be considered.

The invention discloses an ORB algorithm acceleration system and method based on an FPGA, and the system comprises an image feature caching module which is used for storing an input original image in a BRAM storage unit according to an image pixel column form; the FAST feature extraction module is used for performing preliminary feature point extraction on the original image based on a dual-channel parallel processing circuit to obtain feature points and angular points; the Gaussian pyramid module is used for performing down-sampling and Gaussian smoothing filtering processing on the original image to obtain a smoothed image; the rotation angle calculation module is used for carrying out gray centroid calculation according to the coordinate values of the feature points and the smoothed image to obtain the rotation angles of the feature points; and the rBRIEF descriptor module is used for calculating and generating an rBRIEF descriptor according to the rotation angle of the feature point and the smoothed image to obtain ORB feature point data. The hardware resource utilization rate and the calculation speed are improved.

The invention relates to the technical field of laser ranging and photoelectric detection, and discloses an atmospheric attenuation compensation data processing system for a long-distance laser radar, which comprises a signal acquisition module, a signal processing module and a signal processing module, an atmospheric parameter calculation module determines an atmospheric attenuation coefficient according to a signal segment amplitude attenuation slope, a gain control module adjusts a gain curve increase step length, a timing correction module determines a timing starting point offset according to the coefficient, and both gain adjustment and offset compensation respond to the atmospheric attenuation coefficient in real time; according to the invention, a transmissivity in-situ sensing mechanism is established by using a scattering background endogenous by a laser echo, waveform broadening and timing starting point offset caused by non-uniform distribution of a medium are eliminated, and distance measurement consistency and sensitivity are improved.

The invention discloses an auxiliary puncture method and system based on ultrasonic image blood vessel score feedback, and relates to the technical field of medical images. According to the blood vessel recognition method, blood vessel signal features of the human body are analyzed according to ultrasonic image imaging of the target human body, intelligent recognition and blood vessel segmentation are carried out on the blood vessel signals, on the basis that the blood vessel segmentation area is obtained, scoring and feedback of whether the blood vessel is suitable for puncture are carried out, the defects in the prior art are overcome, and the blood vessel recognition efficiency is improved. According to the method, blood vessel extraction and evaluation on whether the current position is suitable for puncture are achieved, especially for blood vessel extraction and puncture fitness score feedback, the position of an ultrasonic probe is adjusted to find the optimal puncture position, and the accuracy and success rate of auxiliary puncture are greatly improved; automatic and intelligent image recognition and scoring of the blood vessel subjected to ultrasonic-assisted puncture are achieved, and the method becomes a judgment basis for optimizing and optimizing the position of the ultrasonic probe subjected to ultrasonic image puncture assistance.

The invention provides an alternating current feeder switch constant value identification method and a related device, and the method comprises the steps: screening an open source data set of an alternating current feeder switch based on a predetermined mode, and obtaining a training set and a test set; inputting the training set into a convolutional neural network for training, and determining a target detection model; and inputting the test set into the trained target detection model to obtain a detection result of the feeder fixed value. According to the embodiment of the invention, the method can reduce the manual inspection of the transformer substation, avoids the error rate, facilitates the real-time and effective utilization of data at different levels, and is more beneficial to the flat management of all devices of the transformer substation.

The utility model relates to the technical field of tailing separation equipment, and discloses a secondary tailing slurry separator which comprises a settling tank, a plurality of supporting columns fixedly mounted on the outer side of the settling tank, a plurality of overflow pipes fixedly mounted on the outer side of the settling tank, a plurality of cross beams fixedly mounted on the settling tank, and a discharge hopper fixedly mounted on the cross beams. The discharging hopper is obliquely arranged towards one side, the lifting pipe is fixedly installed on one side in the discharging hopper, the spiral conveying paddle is movably installed in the lifting pipe, the rack is fixedly installed on the lifting pipe, and the motor is fixedly installed on the rack. Through the arrangement of the conical settling tank, settling of slag materials can be facilitated, real-time extraction of the settled slag materials is achieved in cooperation with the lifting pipe, the spiral conveying paddle, the machine frame and the motor, the material pushing mechanism is arranged on the discharging hopper, and when the slag materials are extracted through the spiral conveying paddle, the slag materials entering the discharging hopper can be automatically pushed, so that the slag materials are conveniently extracted. The slag and the slurry are prevented from being accumulated in the discharge hopper, and high-efficiency slag and slurry separation operation is realized.

The utility model discloses intelligent imaging glasses in the technical field of imaging equipment, and aims to solve the problems that in the prior art, when the intelligent imaging glasses are worn, only two glasses legs are used for playing a fixing role, the falling phenomenon easily occurs, and meanwhile, required modules of the glasses cannot be added according to actual use requirements. The glasses comprise a glasses frame, lenses are detachably connected to the outer wall of the glasses frame, glasses legs and mounting blocks are arranged on the two sides of the outer wall of the glasses frame respectively, fixing devices are detachably connected to the sides, away from the glasses frame, of the outer walls of the mounting blocks, the fixing devices comprise expansion earphones, and the expansion earphones comprise arc-shaped frames matched with human auricles; according to the utility model, the arc-shaped frame is clamped on the outer side of the auricle, and the relative positions of the whole glasses and a person are fixed, so that the glasses are prevented from falling off during movement; according to actual use requirements, required modules can be mounted on the arc-shaped frames, and the arc-shaped frames are mounted on the mounting blocks, so that the actually required modules are carried on the glasses.

The application relates to a multi-dimensional feature real-time extraction method for high-speed network flow, and belongs to the technical field of network security. In view of the technical difficulty of real-time extraction of multi-dimensional flow features of intelligent network threat detection in a high-speed network environment, the application combines the damping increment statistics and sketch two ideas, proposes an incremental statistics sketch ISS architecture, and based on the architecture, proposes a flow feature real-time extraction method in a high-speed network, which is used for real-time extraction of multi-dimensional flow features in a high-load network. The extraction method has high-speed flow processing capacity and flow feature real-time calculation capacity, and can realize real-time extraction of multi-dimensional flow features in a high-speed network environment.