35results about How to "Reduce background noise distractions" patented technology

The invention provides a calibration device and a calibration method for the equivalent self-noise acceleration spectrum level of a low-noise vector hydrophone. It is mainly composed of underwater acoustic tube, vacuum tube, electromagnetic shielding tube, vibration-damping base and upper cover. The noise self-spectrum measured by each vector hydrophone includes the self-noise spectrum and the environmental background noise spectrum, and the cross-correlation calculation of the noise signals of the two vector hydrophones can obtain the environmental background noise spectrum, and then through the known vector hydrophone The transfer function of the earphone can be calculated to obtain the equivalent self-noise acceleration spectrum level of the respective vector hydrophones. The present invention effectively reduces external vibration, electric, electromagnetic and acoustic interference, makes the background noise of the test environment extremely low, and thus better satisfies the calibration accuracy of the equivalent self-noise acceleration spectrum level parameters of the low-noise vector hydrophone It improves the evaluation effectiveness of the self-noise level of the low-noise vector hydrophone, and ensures the engineering application quality of the low-noise vector hydrophone.

The invention discloses an aerial image-based power transmission line detection method. The method comprises the following steps of firstly obtaining two-dimensional enhanced matrix eigenvalue and eigenvector corresponding to each pixel point by utilizing a Hessian matrix, and according to relationships between eigenvalues and eigenvectors, obtaining edge information of an aerial image; secondly according to a power transmission line distribution characteristic in the aerial image, proposing a simplified aerial image power transmission line distribution model; and performing block segmentation on the aerial image, obtaining a boundary of a power transmission line region, and obtaining a region segmentation coefficient; thirdly detecting a power transmission line by applying a Hough transform detection method to the image; and finally performing judgment by using a line spacing and a power transmission line slope, removing line segments not meeting the requirements, and reserving line segments meeting the requirements as a real power transmission line. The method is high in detection speed and high in detection precision, and can detect real power transmission line information in the aerial image with a complex background; by adopting the method, the problems of long consumed time and slow detection progress are solved; and the detection and identification rate of a power transmission line target in the aerial image is effectively increased.

The invention discloses an image synergy significance detection method based on energy optimization, relates to the field of image data processing, fuses three important significance clues, optimizesa fused energy equation, and comprises the following steps: inputting an image group {I1, I2,..., In}, and carrying out preprocessing; Determining an initial candidate simple saliency map (shown in the description), and calculating an initial collaborative saliency map (shown in the description); and calculating an initial collaborative saliency map (shown in the description). setting a simple image Isim according to the formula shown in the specification, wherein the formula shown in the specification is shown in the specification; Respectively extracting color features of the foreground areaand the background area of the simple image; And completing image synergy significance detection. According to the method, the defects of complex manual marking, too much background noise and targetmissing in the prior art are overcome.

The invention discloses a Camshift algorithm for tracking a centroid correction model on the basis of Grabcut and an LBP (Local Binary Pattern). A target object is separated from an environment through the constant value enhancement tracking of a video stream and Grabcut foreground segmentation to cause the Camshift to obtain a pure histogram. Meanwhile, a Kalman filter assists the Camshift to predict a target movement locus. During a tracking period, carrying out LBP transform on an image in a target frame to obtain a template and current LBP histogram data, a judgment coefficient and a frame body change situation are obtained through comparison, and an S-Grabcut algorithm is executed if the target object is blocked by an object with a similar color, a centroid is removed, and normal tracking is continuously carried out. Compared with a traditional Camshift algorithm, the algorithm disclosed by the invention reduces the interference of background noise to a large extent, and the problem of quick movement and blocking is solved since the Kalman filter is added. Meanwhile, interference brought by the blocking of the object with the similar color can be favorably solved by the centroid correction model. Experiment results indicate that the algorithm has good robustness, meets the requirements of instantaneity and accuracy in tracking and causes the target to be more stably tracked under a complex environment.

The invention discloses a combined chemiluminescent detection kit and a detection method. The combined chemiluminescent detection kit comprises a specific conjugate of a to-be-detected substance, a microparticle, a solid-phase film, a chemiluminescent reagent, a centrifugal device and a luminescent detector, wherein the chemiluminescent reagent comprises at least one selected from a group consisting of a chemiluminescent enzyme, a chemiluminescent substance, a chemiluminescent enzyme reaction substrate and a starting luminescent reagent; the microparticle is a particle capable of specifically binding to a protein and/or the chemiluminescent reagent in a direct binding and/or chemically crosslinking way and maintaining stable; the solid-phase membrane is a membranous substance having the characteristic of non-specific binding to a protein; the centrifugal device is a structure capable of centrifugally driving chromatographic flowing of a liquid phase on the solid-phase membrane; and the specific conjugate of the to-be-detected substance is at least one selected from a group consisting of antigen, antibody, avidin, biotin and analogue thereof with specific binding ability. The combined chemiluminescent detection kit and the detection method in the invention have the characteristics of high sensitivity and short detection time, and have good application prospects.

The invention relates to a reference signal constraint-based mechanical characteristic acoustic signal frequency-domain semi-blind extraction method, and belongs to the technical field of operation maintenance of mechanical equipment. The method comprises the following steps: constructing a multi-scale morphology filter for a failure signal characteristic on the basis of a dynamic particle swarm algorithm with higher global optimization capability, and maximally weakening background noise interference; constructing a reference signal in combination with structural parameters of a mechanical part, and further performing complex component blind separation band by band by virtue of a unit reference signal constraint semi-blind extraction method; solving order uncertainty problems to obtain a separated and restored source signal to finally realize the extraction and separation of the mechanical failure characteristic signal by virtue of the improved KL distance between complex components. Different from vibration monitoring requiring the mounting of a sensor on the surface of mechanical equipment, acoustic monitoring only requires the placement of 1 to 2 microphones around the equipment, and then the failure characteristic signal can be extracted from a picked up mechanical acoustic signal for further failure source positioning.

The invention discloses a centrifugal separation immunochromatography detection method. Based on the characteristic that a centrifugal device is utilized for driving a liquid phase to flow in a solid-phase detection film based on an existing immunochromatography technique, the method can be applied to a colloid metal immunochromatography detection method, a fluorescence immunochromatography detection method and a chemiluminiscence immunochromatography detection method. The method has the characteristics of high sensitivity, short detection time, convenience in use, high stability and convenience in storage.

The invention discloses a bird sound recognition system and recognition method, and the system employs a specific directional reception method to achieve the high-precision tracking and recognition ofa target bird sound, reduces the range of a received sound source, can reduce the background noise interference to a greater degree, improves the detection and recognition precision, and achieves theprecise positioning and recognition. The sound spectrum rate aiming at bird sounds is higher, bird sound has the characteristic that a plurality of short high-pitch continuous or discontinuous high-frequency sounds are produced, a subsequent enhancement processing scheme is specified, and high-precision respective identification processing can be realized by utilizing a neural network model, so that the bird sound identification precision is remarkably improved, and a good technical support is provided for bird population research.

The invention discloses a rolling bearing sound signal multiband fusion fault diagnosis method based on RLS and RSSD. The rolling bearing sound signal multiband fusion fault diagnosis method comprises the following steps that firstly, a bearing operation sound signal is subjected to dereverberation processing through an RLS algorithm; secondly, noise reduction processing is conducted on low-frequency signals and high-frequency signals in the reverberation-removed signals through a resonance sparse decomposition method based on the optimal quality factor and a wavelet noise reduction algorithm; the signal amplitudes of the two frequency bands are compared, and the signals are amplified and superposed to complete signal reconstruction; and finally, the bearing fault is judged through envelope spectrum analysis. According to the method, the interference of noise and reverberation on the bearing signals is reduced, the weak bearing signals are extracted through a multi-band noise reduction method, and compared with an existing acoustic diagnosis method which is based on a single band and does not consider the reverberation influence, the method has the advantages of being good in noise suppression effect, small in signal effective information loss, high in diagnosis precision and the like. The method can accurately identify bearing faults, and is suitable for acoustic diagnosis of rolling bearings.

The invention discloses a buccal mute communication method and a system. The method comprises the following steps: collecting an intraoral first signal and an intraoral second signal; determining vibration characteristic information according to the intraoral first signal, and determining form position information according to the intraoral second signal; determining voice information by using a voice prediction model according to the vibration characteristic information and the form position information; and synthesizing a voice by means of the voice information. By collecting the first signal in the mouth and the second signal in the mouth, the vibration characteristic information is determined according to the first signal in the mouth, and the form position information is determined according to the second signal in the mouth, so that the background noise interference can be reduced, the confidentiality is high, and no trauma is caused; the voice prediction model is used, the voiceinformation is determined according to the vibration characteristic information and the form position information, the voice is synthesized by using the voice information, the learning cost is low, the use is convenient and the comfort is high.

The invention discloses a target tracking method and system based on multi-feature and adaptive dictionary learning, and the method comprises the steps: obtaining a foreground template of a first frame image at an initial position of a target and a surrounding background template of the target; Constructing an initial dictionary according to the target foreground template and a target surroundingbackground template, and obtaining an initial texture feature dictionary and an initial color feature dictionary; according to the LC-KSVD algorithm, Performing learning processing on the initial texture feature dictionary and the initial color feature dictionary by using a KSVD algorithm to obtain a discriminant texture feature dictionary and a discriminant color feature dictionary; And performing target position tracking matching based on a sparse feature matching algorithm according to the discriminant texture feature dictionary and the discriminant color feature dictionary to obtain a tracking position of a next frame of the target. In the embodiment of the invention, by utilizing the discrimination dictionary, the representation capability of the target appearance can be supplemented,background noise interference is reduced, and the tracking precision is improved.

The invention discloses a centrifugal separation detection device. The centrifugal separation detection device comprises a sample feeding part, a solid phase membrane, a centrifugal device and a detector, wherein the centrifugal device comprises a centrifugal rotor and a support base; the centrifugal rotor is driven by a drive motor, and is supported by the support base; the sample feeding part isnot directly connected with the centrifugal rotor, and is arranged above, under or outside the centrifugal rotor; the sample feeding part comprises a liquid phase storage device, a sample feeding pipe and a sample feeding pump; the liquid phase storage device is communicated with the sample feeding pipe; the sample feeding pump is used for driving liquid in the liquid phase storage device to enter the sample feeding pipe; the solid phase membrane is arranged on the centrifugal rotor, and a liquid phase sample is directly or indirectly loaded onto one side, near the center, of the solid phasemembrane by the sample feeding pipe; the detector is not directly connected with the centrifugal rotor, and is arranged above, under or outside the centrifugal rotor. The centrifugal separation detection device is characterized in that the sensitivity is high, and the full-quantitative and automatic effects are realized; the detection technology with quick detection and simple used equipment is adopted, and the good application prospect is realized.

The invention provides a flexible solar blind ultraviolet detector. The flexible solar blind ultraviolet detector is characterized by comprising a transparent substrate, a graphene mesh layer and a ZnS quantum dot layer that are arranged in order from bottom to top. The graphene mesh layer is formed by graphene meshes after graphene etching. The flexible solar blind ultraviolet detector has the beneficial effects: the preparation process is simple; flexibility is high; and large-area application is realized. The prepared flexible solar blind ultraviolet detector has high response to the ultraviolet light in the solar blind zone and the low response to light beyond the solar blind zone, so that the influence of background interference is reduced. In addition, the invention also provides a preparation method of a flexible solar blind ultraviolet detector.

The invention discloses an audio adapter for conversation in a prison. The audio adapter comprises an audio input module, an audio amplifying module, an impedance matching module, and an audio output module, wherein the audio input module is used for inputting an audio signal; the audio amplifying module is used for amplifying the input audio signal, and transmitting the amplified audio signal to the impedance matching module; the impedance matching module is used for performing smooth processing on the amplified audio signal, and transmitting the smoothly processed audio signal to the audio output module; and the audio output module is used for outputting the smoothly processed audio signal. The audio adapter for the conversion in the prison disclosed by the invention can effectively adapt to a video-audio compression card in a prison helping-educating system, the noise interference is reduced, and the sound articulation is improved.