383results about How to "Eliminate noise interference" patented technology

In order to prevent double-shadow and cavity phenomena from occurring in a target and rapidly obtain a complete outline of a moving target in a video sequence, the invention provides a moving object rapid detection method based on the video sequence. The method comprises the steps of denoising the video image sequence through a gaussian filter and solving an inter-frame differential image of any three frames of filtered adjacent video images through differential operation; carrying out iteration update on an initial background image through utilization of an inter-frame differential binary image and extracting a background image corresponding to a current frame; reestablishing a reference image corresponding to the current frame of image according to an inter-frame differential result of the three frames of adjacent video frames, thereby obtaining an inter-frame differential target detection image, and obtaining a moving target outline difference value image of the current frame through a background differential method; and combining target images extracted by a three-inter-frame differential method and a background differential method through an OR operation, and outputting a final moving target image. According to the method, noise interference can be effectively removed and the complete moving target can be detected rapidly and accurately.

The invention relates to a method for detecting and tracking an infrared small target in a complex background. In consideration of problems of low SNR (Signal Noise Ratio), great noise and instability of tracking based on single feature of an infrared image, the method provided by the invention comprises the following steps of: firstly, extracting an interested target region as a detection result by using variance weighted comentropy, creating a target template according to gray level and textural features, and implementing the aim of tracking the infrared small target through Mean Shift algorithm. With the method, the problem of instability of tracking based on single feature in complex background is effectively avoided, and the availability of the method is checked in tracking experiments of a plurality of infrared video sequences.

The invention discloses an active vibration absorber with a flexible structure and a control method thereof. The active vibration absorber comprises a signal acquisition unit and a control vibration absorption unit; in the signal acquisition unit, the flexible structure is provided with an ICP acceleration transducer, and a signal is transmitted to a constant current source, a data acquisition device and an analog/digital converter in turn and then transmitted to a computer to be processed; and in the control vibration absorption unit, a computer control signal is transmitted to the analog/digital converter and a first power amplifier and then transmitted to an actuator to execute vibration absorption. In order to simulate external excitation, the active vibration absorber is provided with an exciting force output unit, a signal generator of the unit is connected with an input end of a second power amplifier, a signal generated by the signal generator is amplified by the second power amplifier and then input to a vibration exciter, and the vibration exciter is connected with the flexible structure through a post rod to provide external disturbance. The method mainly comprises an off-line recognition process and a real-time control process. A random walk and input estimation method is introduced into active vibration control of the flexible structure, and good control effect is acquired from an experimental angle.

The iris recognition method based on image segmentation and 2D wavelet transformation comprises: dividing the iris positioning into the key-point inner edge and an outer edge positioning; by mapping technology from Cartesian coordinate to polar coordinate, normalizing positioned image into a fixed gray matrix; then taking image segmentation for two times into 18 sub-areas finally; taking 2D wavelet transformation to extract the wavelet coefficient and variance as feature values from main wavelet channel; in matching and recognition algorithm, using reciprocal variance sum and different weighing values to obtain final result. Compared with prior art, this invention has well noise-proof feature and high recognition ratio without losing real-time.

The invention discloses a ground point cloud segmentation method based on a three-dimensional laser radar. The method comprises the following steps that: S100: obtaining ground point cloud data, carrying out scanning on the basis of the ground three-dimensional laser radar to obtain spatial information data, and meanwhile, combining with a GPS (Global Positioning System) to obtain ground data; S200: carrying out data processing, establishing a rectangular coordinate system, converting the coordinate of the obtained ground data into the rectangular coordinate system, and meanwhile, adopting equal-thickness layering according to contour line and contour interval properties; S300: carrying out ground point cloud information segmentation, and classifying the ground laser point cloud information obtained by scanning; S400: carrying out denoising processing, classifying noise data, and independently carrying out noise processing on the noise data; and S500: carrying out image segmentation display, and directly extracting building elevation information through a gridding way. Through a way of combining positioning with laser scanning, more comprehensive ground point cloud data is obtained, meanwhile, the accuracy of the point cloud data is improved through the ways of classified segmentation and step-by-step denoising, and convenience is brought to subsequent modeling and simulation.

The invention relates to a power system transient stability evaluation method based on a deep learning technology. Firstly, a time domain simulation method is used to generate a sample set {x<0>, y<0>}; characteristic variable vectors are then extracted according to the sample set, and a training set {x<1>, y<0>} is formed, wherein the training set is the characteristic variable vector set; training parameters are determined, a stacked automatic encoder is trained based on the training set, characteristic extraction is carried out on the training set to generate a calculation set {x<2>, y<0>};and finally, based on the calculation set, classification model training is carried out on a convolution neural network, and a power system transient stability evaluation model is formed. The stackedautomatic encoder is used to carry out layer-by-layer characteristic extraction on the characteristic variable vectors, a hidden data mode is mined, high-order characteristics more facilitating transient stability evaluation are formed, the convolution neural network is further used to build a stable classification model, the evaluation performance of the model is thus ensured, the misjudgement rate of unstable samples can be reduced, noise interference in a wide area measurement system of the power system can be effectively overcome, and an important significance is provided for online safeand stable evaluation on the power system.

The invention discloses a video heart rate detection method removing interference of ambient light variation. Firstly a face area-of-interest data set and a background area data set are obtained, a united blind source separation technology is utilized to process the two data sets, and signal sources of ambient light variation that the data sets both have are extracted and set to zero, thereby obtaining a face area-of-interest data set free of interference of ambient light variation; secondly, face area-of-interest data of an optimal color channel is selected, and an ensemble average empirical mode decomposition method is utilized to obtain intrinsic mode components; and then all local intrinsic mode components of which frequency corresponding to maximum amplitude values are in a set heart rate range are determined to be a candidate intrinsic mode component set, the intrinsic mode component corresponding to the largest maximum amplitude value is determined to be the optimal intrinsic mode component, and a video heart rate is obtained through a peak detection algorithm. The video heart rate detection method provides a relatively accurate algorithm for non-contact heart rate detection, and has important application prospects in the aspects of clinical disease diagnosis and daily medical care.

The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence-based hot-rolled strip steel scabbing defect detection method and system. The method comprises the following steps: acquiring an RGB image of hot-rolled strip steel and converting the RGB image into a grey-scale map; filtering the grey-scale map, carrying out straight line detection and edge detection on the processed grey-scale map, carrying out overlap ratio judgment on an obtained straight line and a first edge line, and filtering out an isolated straight line and an error edge line to obtain a second edge line; performing intersection point screening on the second edge lines, so that the second edge lines capable of obtaining the complete contour through intersection points and/or the second edge lines forming the complete contour with the gray-scale map boundary are/is reserved and recorded as third edge lines, and a scabbing area is determined; and judging whether the edge of the scabbing area has a warping part or not according to whether a shadow exists on the third edge line of the scabbing area or not, and obtaining the warping degree of the scabbing area. According to the embodiment of the invention, noise interference can be greatly eliminated, and the scarring defect of the strip steel can be accurately and quickly detected.

The invention provides a remote sensing target detection method based on sparse guidance and significant drive. The method comprises the steps of (1) dividing an input remote sensing image into sub blocks, extracting global color feature clusters to form a global dictionary and extracting the color feature clusters of the image edge sub blocks to form a background dictionary, (2) carrying out sparse expression on all input image sub blocks by using the global dictionary and the background dictionary and obtaining global and background sparse expression coefficients, (3) clustering the sparse expression coefficients obtained in the step (2) to generate global and background significant maps, (4) carrying out smooth denoising on the global and background significant maps obtained in the step (3) and then obtaining a final significant map by using Bayesian fusion, and obtaining a significant target area, (5) extracting a color feature and a texture feature for the significant target area detected in the step (4) and a collected training sample, and carrying out sparse expression by using a maximum value restraint sparse coding model, and (6) carrying out target type identification on the significant target area by using a sparse expression coefficient obtained in the step (5). According to the method, an interested remote sensing target can be accurately and rapidly detected and identified in a complex background, and the effect is outstanding.

The invention relates to a multi-group image classification method based on two-dimensional empirical modal decomposition and wavelet denoising, belonging to the filed of image processing. The invention aims at solving the problems of insufficient utilization of image essential characteristics and low classification precision of the traditional classification method. The method comprises the following steps of: firstly, respectively carrying out two-dimensional empirical modal decomposition on each wave band in multi-group images to obtain the former K two-dimensional components and one residual error; secondly, summarizing the former K two-dimensional components as a characteristic value, and obtaining a denoised characteristic value after wavelet denoising; thirdly, randomly and proportionally selecting the denoised characteristic values of a plurality of multi-group images as training samples and test samples of a support vector machine, carrying out parameter training of the support vector machine on the training samples, and then carrying out attribution judgment to form a plurality of sub-classifiers of the support vector machine; and fourthly, constructing multiple classifiers based on a one-to-one strategy by utilizing the sub-classifiers of the support vector machine, and determining the attribution classes of the test samples according to a strategy function to complete the classification of the multi-group images.

The invention discloses a method of obtaining underwater acoustic channel reciprocity by using compressed sensing and relates to underwater acoustic communication. The method is used for obtaining accurate channel parameters from OFDM (Orthogonal Frequency Division Multiplexing) received signals and ensuring the reciprocity of underwater acoustic channels. According to a compressed sensing theory, an OMP algorithm is used for reconstructing time domain impulse noise interference and wide single frequency noise interference, and eliminating the noise interference by observed quantity. For the time domain impulse noise interference, the time domain impulse noise interference is estimated by virtual subcarrier at a receiving end, is reconstructed by the OMP algorithm and is eliminated; the wide single frequency noise extracted at the receiving end has sparsity at a frequency domain, domain conversion is not needed, a measurement matrix is utilized, and the wide single frequency noise interference is reconstructed according to the OMP algorithm and is eliminated. The upper row and the lower row of underwater acoustic channels after the time domain impulse noise interference and the wide single frequency noise interference are eliminated are identical in channel states, namely, the underwater acoustic channels are provided with the reciprocity.

This invention discloses one wireless signal relay process method and device, which comprises the following steps: adding down relay frames into signal frame and using down relay frame to base station to send down business information; the relay device receives down relay frame to extract down business information and using down frame to send the down relay signals with down business information; adding upper relay frame in upper signal frame and using upper frame receive terminal to send upper business information to base station.

The invention provides a motion target super-resolution image reconstruction method based on an optical flow field. The motion target super-resolution image reconstruction method comprises the following step: first, performing motion target tracking and motion estimation based on the optical flow field; second, utilizing an inhomogeneous interpolation method to perform image fusion of low-resolution image sequences; and third, utilizing a wiener filtering method to perform image reconstruction to preliminarily-fused high-definition images to obtain clear high-definition images. In the first step, a motion target image is first captured from a first frame image, a motion target image at the same position in a next frame image is captured according to the position of a motion target image in a reference frame image, the optical flow field between the two motion target images of two frames is calculated, then motion parameters of the motion target images are obtained by utilizing the optical flow field, the positions of the motion target images in the next frame image of the reference frame image are changed according to the motion parameters, and finally adjacent frame images are performed and the motion target images of frame images are tracked or captured by means of the same method.

The invention discloses a video super-resolution reconstruction method based on deep learning and self-similarity, which belongs to the field of video processing technologies. The video super-resolution reconstruction method comprises the steps such as video frame extraction, preliminary estimation, preliminary reconstruction, secondary reconstruction and video frame integration. The video super-resolution reconstruction method makes use of apriori constraint conditions provided by an external training set and the internal self-similarity comprehensively, and has good reconstruction effect on some smooth regions, irregular structure information which seldom occurs in a video frame sequence, and some situations such as unique and singular characteristics which rarely occur in the external training set but repeatedly occur in the video frame sequence; in addition, the video super-resolution reconstruction method does not rely on precise sub pixel motion estimation, thus can adapt to a complicated motion scene, and achieves large multiples of super-resolution reconstruction.

The invention provides a small-diameter directional gyro inclinometer for drilling. The small-diameter directional gyro inclinometer consists of an aboveground control device and an underground measurement device. The underground measurement device comprises an inertial short section based on a flexible gyro, wherein the inertial short section of the gyroscope includes a sensor consisting of two small flexible gyros with two degrees of freedom and three orthogonal quartz accelerometers; the two small flexible gyros with two degrees of freedom are orthogonal to each other and are connected with each other through a rotary frame; the three orthogonal quartz accelerometers are connected with one another through the rotary frame; and the gyros and the accelerometers are directly mounted on an inertial body through a location plane to constitute an inertial measurement assembly which is supported on a casing through a pair of bearings. The angles of the inclinometer in the three axial directions can be obtained by resolving an inertial navigation equation during logging so as to obtain the real-time well measurement information and output the azimuth information of an oil well. The small-diameter directional gyro inclinometer has the advantages of small size, low cost, high accuracy, high measurement speed, continuity in measurement, high reliability, high resistance to temperature and pressure, and wide application range.

The invention provides a shifting register unit and a driving method thereof, a scanning drive circuit and a display device. The shifting register unit comprises an input end, an output end, a reset end, a first noise-amplifying end, an output drop-down module, an input module, an output module, a reset module and a first noise-amplifying module, wherein the input module, the output module, the reset module and the first noise-amplifying module are connected to a first node; the input module is used for raising the voltage of the first node under the control of a signal received by the input end; the reset module is used for lowering the voltage of the first node under the control of a signal received by the reset end; and the first noise-amplifying module is used for releasing the noise voltage of the first node to the first noise-amplifying end under the control of a third clock signal, and used for disconnecting the electric connection between the first noise-amplifying end and the first node when the voltage of the first node is raised. According to the invention, the stable output of removed noise jamming of GOA units can be realized by relatively less circuit components.

The invention discloses a level adjusting device and a method thereof. The level adjusting device includes a support plane, an execution mechanism and a control unit. The execution mechanism and the control unit are located below the support plane respectively. The execution mechanism includes a fixing support foot and two shear-type jacking driving devices. The level adjusting device adopts a PD closed-loop control algorithm to use a parameter obtained by an inclination-angle sensor as a feedback of driving of the execution mechanism by an embedded-type controller so that the level can be adjusted rapidly and accurately and the shear-type jacks are used as the execution mechanism and through reduction gearboxes, stepping motors drive lead screws of the shear-type jacks to rotate so as to adjust the ascending and descending of the support foot. The level adjusting device and the method thereof have the characteristics of being high in adjustment speed, high in adjustment precision and great in bearing performance; and the level adjusting device is simple and compact in structure, high in stability and wide in practicality.

The invention provides a somatic action identifying method. The somatic action identifying method includes steps of 1) acquiring effective data segments of the somatic action by a speed sensor in the somatic device; 2) calculating DTW distance between the acquired effective data segments and the standard data segments and matching a sample library according to the DTW distance between the acquired effective data segments and the standard data segments; 3) calculating the DTW distance between the acquired effective data segments and each sample data segment in the matched sample library of the step 2), and using identifiers of the somatic action indicated by the minimum sample data segment of the DTW distance as the identifying results of the acquired effective data segments. The invention further provides a corresponding man-machine interaction device. On the premise of guaranteeing identifying accuracy, identifying efficiency is improved; high identifying accuracy is guaranteed on the premise that holding ways of the device during action identification are not limited.

The invention discloses a diagnostic method of an aero-engine rotor fault. According to the method, an eddy current acceleration sensor is firstly utilized to collect a vibration acceleration signal of an aero-engine rotor, then noise reduction processing is performed on the vibration acceleration signal of the aero-engine rotor, and the signal characteristic quantity of the aero-engine rotor after the noise reduction is extracted, and then clustering analysis is performed on the signal characteristic quantity based on automatic density peak clustering of Mahalanobis distance. According to thefault diagnosis method, wavelet decomposition is utilized, threshold processing is performed, and then noise interference is removed from a signal by lifting wavelet reconstruction; the signal characteristic quantity after the noise reduction is extracted, and the clustering analysis is performed on the signal characteristic quantity based on the automatic density peak clustering of Mahalanobis distance, so that the noise interference can be eliminated to a minimum value, the diagnosis of fault information of the aero-engine rotor can be realized, and fault results of various aero-engine rotors can be quickly obtained.

The invention discloses a method and a system for performing snore recognition and strength output and a breathing machine. The system mainly comprises a breathing flow collector, a breathe recognizer, a snore feature recognizer and a snore strength output device which are connected in sequence, wherein the breathing flow collector collects expiration and inspiration flows in the breathing process and sends the flows to the breathe recognizer. The breathe recognizer is used for recognizing an inspiration starting point and an inspiration ending point in a breathing period. When the inspiration starting point is detected, the snore feature recognizer is started, and the snore strength output device is closed. When the inspiration ending point is detected, the snore feature recognizer is closed, and the snore strength output device is started. The snore feature recognizer analyzes flowing speed change characteristics in an inspiration period and recognizes whether snoring occurs or not. The snore strength output device judges recognized snore and then outputs normalized snore strength indexes. By adopting the method and the system for performing the snore recognition and the strength output, the success rate of accurate judgment is improved, the hardware cost is saved, and the achieving complexity is reduced.

The invention discloses an intrinsic-safe type electronic detonator initiation system. An intrinsic-safe type protective circuit is arranged in a control system of the detonator, comprising an anti-interference circuit, a low-voltage DC conversion protecting circuit, a surge protecting circuit and an insulation stabilizing initiation control circuit, wherein, the surge protecting circuit is arranged between an electronic detonator energy-storage capacitor and an SCM control circuit, the output of the surge protecting circuit is communicated to the serial interface of the SCM control circuit through a level shifter circuit and an MAX485 chip and the input terminal of the surge protecting circuit is connected with the output terminal of the energy-storage capacitor; the low-voltage DC conversion protecting circuit and a voltage-stabilizing protecting circuit are arranged between the energy-storage capacitor and the initiation circuit of the electronic detonator; and simultaneously the insulation voltage-stabilizing circuit is arranged between the energy-storage capacitor and an electronic switch of the initiation circuit of the detonator.

The invention discloses an ultra-wideband positioning method of a single receiver in an indirect path environment. The method includes the steps that first, initialization is conducted; next, ultra-wideband signals are sent by a fixed base station, and a non-directional antenna of a mobile base station receives the signals from the fixed base station and detects transmission time delay, the arrival azimuth angle and the pitch angle; then, a directional antenna of the mobile base station adjusts the self transmitting angle according to the previous arrival azimuth angle and the previous pitch angle and reflects the ultra-wideband signals; the fixed base station receives the signals from the mobile base station and detects the arrival azimuth angle and the pitch angle, and then measurement of five parameters of a first reflection channel is completed; then, five parameters of a second reflection channel are detected; whether the two sets of parameters meet requirements or not is checked with an auto-diagnosis algorithm, and the coordinates of the mobile base station are calculated through a positioning algorithm. The ultra-wideband positioning method effectively solves the problem that because direct signals cannot be detected, positioning is inaccurate, and improves the indoor ultra-wideband positioning accuracy, and the indoor positioning technology has very high promotional value.