1785 results about "Background noise" patented technology

The invention provides a thin film surface defect detection method and system, and relates to the technical field of defect detection.According to the thin film surface defect detection method and system, an intelligent secondary verification link is constructed by introducing a defect confidence evaluation mechanism based on form and energy distribution, so that the detection performance is fundamentally improved; according to the mechanism, real physical defects with regular forms and concentrated energy and pseudo defects caused by electromagnetic interference, instantaneous film wrinkles and the like can be accurately distinguished, and the problem of high false alarm rate caused by dependence on single signal strength in the prior art is effectively solved while the high detection rate of low-contrast defects is reserved; besides, the judgment model based on physical characteristics has natural robustness for background noise generated in high-speed motion, and an adjustable confidence threshold value endows the system with extremely high practical flexibility, so that the system can adapt to complex and changeable industrial environments and different quality control standards, and the method is suitable for large-scale popularization and application. And the accuracy, the reliability and the intelligent level of the whole detection system are obviously enhanced.

The invention discloses a real-time single-stage remote sensing image correction target detection method based on YOLOV8, and relates to the technical field of remote sensing image processing. According to the method, a deformable convolution dynamic prediction local geometric distortion parameter is embedded based on a YOLOv8 backbone network, an adaptive deformation field is generated, pixel-level real-time correction is realized, shallow details and high-level semantic features are fused through a bidirectional path aggregation network, and channel attention and a space gating mechanism are combined, so that the real-time correction of the image is realized. The small target detection capability is enhanced, background noise is suppressed, angle prediction is divided into discrete classification and continuous residual error regression tasks through a decoupling type rotation detection head, angle periodic errors are eliminated in combination with a direction sensitive loss function, and the rotation frame positioning precision is improved. And constructing a dynamic multi-task collaborative loss function, introducing gradient distribution consistency constraint to jointly optimize correction and detection tasks, and realizing feature semantic alignment and model self-enhancement through end-to-end closed-loop training. And the rotating target detection precision and the complex scene robustness are obviously improved.

The invention provides a microcrack precise segmentation method integrating feature fusion and convolution attention, and belongs to the field of image processing. According to the method, a crack segmentation network based on an encoder-decoder architecture is constructed, a convolution block attention module is introduced at an encoder end, background noise is adaptively suppressed and obvious characteristics of cracks are enhanced through a channel and space dual attention mechanism, and the method is suitable for the adaptive segmentation of the cracks on the premise of almost not increasing the calculation overhead. The sensitivity of the model to microcracks is improved; a feature fusion module is introduced at a decoder end, and cooperation of low-layer details and high-layer semantics is realized through cross-layer fusion, so that a semantic gap is effectively bridged, detail loss caused by traditional convolution stacking is avoided, and continuity and a complete topological structure of a long and narrow crack are ensured. According to the method, through collaborative optimization of multi-scale feature extraction and an attention mechanism, accurate capture of the saliency features of the crack and effective suppression of complex background interference are realized, and the detection sensitivity and overall segmentation consistency of the micro-crack are remarkably improved.

The invention relates to the technical field of AI toys, and provides an AI toy voiceprint recognition interaction method, device and equipment, and the method comprises the steps: obtaining a to-be-recognized target voice signal, extracting an original audio data set to generate a sound field estimation parameter and a background noise feature, carrying out the voiceprint feature extraction of the target voice signal, obtaining a voiceprint feature vector, and obtaining the voiceprint feature vector; and performing feature clustering on the voiceprint feature vector and a preset child voiceprint vector set to obtain user identity information, a behavior tag and an emotion tag so as to generate a corresponding multi-modal response instruction, and inputting the multi-modal response instruction into a control module of the AI toy. Robustness of a target voice signal in a complex environment is improved by combining sound field estimation parameters and background noise features, and through voiceprint feature vector extraction and clustering and similarity calculation, the target voice signal is improved under the condition that environmental noise interference is remarkable or semantic emotion interaction is complex. The problems of low identification accuracy and low user discrimination degree exist in the prior art.

The invention discloses a crack segmentation method and system based on a dynamic receptive field and multi-scale semantic aggregation, and relates to the technical field of computer vision. The method comprises the following steps: inputting a crack image, and simultaneously capturing local details and global structural features of a crack through a dynamic snakelike Mama module: dynamically adjusting the shape of a convolution kernel to adapt to the geometric change of the crack, inputting the obtained features into a spatial pyramid pooling layer to extract multi-scale context information, and outputting feature representation fused with a long-range dependency relationship; based on the feature representation fused with the long-range dependency relationship, an interaction relationship between local details and global semantics is established through a multi-scale semantic aggregation module, background noise interference is suppressed through a parallel supervision attention mechanism, and a pixel-level crack segmentation result is generated through a lightweight segmentation head. According to the method, fine cracks can be segmented more accurately in a complex background environment, and meanwhile, the conditions of wrong segmentation and missing segmentation are effectively relieved.

The invention belongs to the technical field of leakage detection, and particularly relates to a leakage detection method based on multi-sensor time shift correction and deep learning. A plurality of sensors sensitive to leakage sound waves or vibration are arranged at different positions of a monitored pipeline or container and used for collecting leakage related signals; time alignment is carried out on the time sequence signals collected by the multiple sensors according to the position difference of the time sequence signals in the space; comparing and differentiating the plurality of sensor signals subjected to time alignment; modeling and updating environmental noise in real time, dynamically adjusting detection parameters according to noise level, continuously monitoring statistical characteristics of background signals, and establishing a noise model; a pre-trained deep learning model is used to carry out mode identification and classification determination on the signal after noise reduction processing; and the alarm and display module is used for triggering alarm and recording leakage information when suspected leakage is detected. According to the invention, weak leakage signals can be reliably detected under the condition of strong background noise.

The invention discloses an intelligent cleaning and feature extraction system and method for multi-modal industrial data, and relates to the technical field of equipment state monitoring. The method is used for solving the problems that multi-source heterogeneous signal time alignment is not accurate, fault features are easily covered by background noise, a causal chain is not clear under working condition changes, and feature stability is poor. Firstly, a matching window is dynamically adjusted based on the main vibration frequency of rotating equipment, temperature signal delay is calculated in combination with a material thermal expansion coefficient, and modal alignment is achieved; then, a fault sensitive frequency band is solved through a bearing pedestal kinetic equation, a frequency band protection window is constructed, frequency domain filtering and gradient truncation operation are executed, and microcrack high-frequency features are extracted; secondly, recognizing a fault propagation path by combining image definition and envelope spectrum kurtosis, and dynamically shrinking a frequency domain window bandwidth according to a real-time load; finally, the feature vector is reconstructed to a phase space, when the curvature change rate or the temperature drift exceeds the limit, parameter updating and frequency band readjustment feedback are triggered, and the stability and adaptability of the system are improved.

The invention discloses a concrete crack detection method based on a hybrid Mama attention segmentation model, and the method comprises the steps: 1), obtaining an original image, carrying out the preprocessing of the image, and dividing a data set; 2) constructing an MA-UNet model, adopting an encoder-decoder symmetric structure, extracting features by an encoder through convolution and pooling, recovering resolution by the decoder through up-sampling of transposed convolution, and fusing high-resolution detail features of the encoder with deep semantic features of the decoder through jump connection; (3) a visual state space module VSS is adopted to suppress background noise and reinforce crack features through a dynamic focusing mechanism; 4) performing grouping channel attention weighting on the feature map through a multi-head depth separable channel attention module MDCA; according to the method, the calculation complexity and the parameter quantity are reduced through the lightweight module design, the continuous segmentation capability of the model on the micro cracks is enhanced, and the anti-interference performance under the complex background is improved.

The invention discloses a remote sensing image-oriented multi-scale adaptive small target detection system and method. The system comprises a backbone network backbone, a feature aggregation network Neck and a detection head Head, the backbone network backbone is used for extracting multi-scale effective features, the feature aggregation network Neck is used for fusing and enhancing the multi-scale effective features, and the detection head Head is used for making a decision for target detection. The method comprises the following steps: constructing a target detection data set by using remote sensing images, preprocessing the images, and dividing the images into training, testing and verification sets; a backbone network backbone is adopted to extract multi-scale effective features, and a neck network Neck is adopted to refine the extracted features; carrying out mixed loss training by adopting NWD loss; and the detection head Head outputs the category and location of the target according to the results of the classification branch and the regression branch. According to the method, the loss of information in the transmission process is reduced, the background noise is inhibited, and the accuracy of small target detection of the remote sensing image is improved.

The invention discloses a small sample target detection method based on target feature enhancement and semantic fusion perception, and relates to a computer vision technology. A data set is divided into a query set and a support set, after features are extracted through a backbone network, background noise in the support features is inhibited through a dynamic hypergraph construction module, and high-order semantic association of a target area is enhanced; fusing the category name text semantics and the image specific prototype by using a semantic fusion perception module to generate a high-discrimination category prototype; modeling semantic distribution by means of a variational auto-encoder, and extracting variational features; and fusing the region-of-interest features and the variation features through a channel attention mechanism to realize classification and regression. According to the method, the prototype characterization capability is effectively improved, and experiments show that the method remarkably improves the detection precision and is suitable for labeling sample scarce scenes. More accurate small sample target detection is realized by enhancing the feature expression of the support feature map and the semantic meaning of the category prototype, and higher robustness and recognition performance are shown in a complex scene.

The invention relates to the technical field of ground resistance detection, in particular to a single-core cable ground resistance detection method capable of resisting strong power frequency interference. High-frequency signals are injected in a non-contact mode through a coupling type capacitor clamp, background voltage and current signals are collected firstly, and injection frequency far away from power frequency and harmonic waves is selected through Fourier analysis; cancelling background noise by adopting a normalized least mean square adaptive filter to generate an enhanced signal; the signal is down-converted to a base band through digital quadrature demodulation, a Kalman filter estimates the amplitude and the phase in real time, and the state and noise parameters are periodically calibrated through a compressed sensing algorithm; and finally, loop impedance is calculated according to the voltage and current amplitudes and the phase difference to obtain grounding resistance. The method has the advantages of being non-contact, high in safety, strong in anti-interference capability, high in measurement precision and the like, and is suitable for monitoring the grounding state of the cable in a complex electromagnetic environment.

The invention provides a target tracking method, electronic equipment and a readable storage medium. According to the target tracking method provided by the invention, by combining generation and updating of the static template and the dynamic template, the problems of time-varying characteristics and background noise in infrared small target tracking can be effectively solved. Firstly, a generated static target image template is cut by multiple scales, so that the adaptability to different scales of a target is improved; and the generation of the dynamic target image template is combined with the dynamic template of the previous frame and the temporary template of the current frame, and updating is carried out through a fusion strategy, so that the morphological change and the thermal radiation fluctuation of the target can be reflected in time, and the problem of response lag caused by the time-varying characteristic of the target is solved. And finally, inputting the static and dynamic templates into a pre-trained target tracking model for processing, thereby effectively suppressing interference of complex background noise, and accurately positioning the target.

The invention discloses a defect identification system of an ultrasonic flaw detector, and relates to the technical field of nondestructive testing, the system comprises a signal acquisition and preprocessing module, a defect feature identification module, a physical modeling analysis module, a life prediction and evaluation module and an intelligent decision visualization module; the signal acquisition and preprocessing module adopts a multi-frequency-point phased array transducer array, obtains an original signal through low-noise amplification, band-pass filtering and analog-to-digital conversion, and outputs a time domain signal matrix through adaptive noise reduction and gain compensation processing; the multi-frequency-point phased array transducer array and the advanced signal processing technology are integrated, the defect recognition precision and efficiency are remarkably improved, the system obtains high-quality original signals through low-noise amplification, band-pass filtering and analog-to-digital conversion technologies at first, then the high-quality original signals are subjected to self-adaptive noise reduction and gain compensation processing, and the defect recognition accuracy is improved. The background noise interference is effectively eliminated, and the purity of the signal is ensured.

The invention relates to the technical field of bill intelligent verification, and discloses a financial bill intelligent identification and verification method based on machine learning. The method comprises the following steps: acquiring an original image data stream of financial bills in real time, monitoring the total quantity of input bills and judging whether the total quantity exceeds a system processing safety threshold; during overrun, processing bill image feature elements by using a machine learning algorithm to generate a feature interaction graph so as to evaluate a potential error risk level, analyzing a background noise distribution mode by using a signal decomposition technology, reconstructing a noise dynamic characteristic model, and calculating an interference degree index of the noise dynamic characteristic model to a key region; deciding whether to start an overall verification optimization process or not according to the grades and the indexes; when the system is started, all bill image recognition path attribute data are analyzed to generate recognition complex factors, verification priority values are calculated according to the recognition complex factors, and a verification sequence is sequenced and output. According to the method, the accuracy and efficiency of financial bill identification and verification can be improved, and the processing flow is optimized.

The invention relates to the field of visual processing, and provides a visual classification processing method and device based on large model and multi-modal data fusion. The method comprises the following steps: inputting a to-be-classified input image and a corresponding category text description into a text encoder for multi-level feature extraction to obtain global text features and local text features; performing fine-grained cross-modal alignment on the local visual features and the local text features, calculating association weights between the image regions and the text phrases through a bidirectional cross attention mechanism, and generating aligned intermediate features; splicing and fusing the aligned middle features and the global visual features, and inhibiting background noise in a fusion result and reinforcing discriminative features in the fusion result through a feature mask algorithm in combination with the global text features to obtain multi-modal fusion features; and synchronously inputting the multi-modal fusion features into a multi-space classifier to generate respective classification results, and adaptively outputting an image classification result according to a confidence threshold in combination with a dynamic routing mechanism.

In a traffic scene, a traditional target detection algorithm always faces the problems of strong background interference, difficulty in small target detection and the like, and detection precision and robustness are affected. Therefore, the invention provides an improved YOLOv12n vehicle detection method in which an EMA (Empirical Multi-scale Attention) attention mechanism and an SFA (Space Feature Aggregation) attention mechanism are fused. The invention further provides a method for detecting the YOLOv12n vehicle based on the improved YOLOv12n vehicle based on the attention mechanism of the EMA (Empirical Multi-scale Attention) and the attention mechanism of the SFA (Space Feature Aggregation). The SFA module is deployed in a shallow network, key target area expression is enhanced by aggregating spatial features, and background noise interference is suppressed; the EMA module is embedded into a neck network, and the global information capture and multi-scale sensing capabilities are improved by adopting multi-scale convolution, cross-space modeling and feature grouping mechanisms. According to the method, the real-time performance is kept, meanwhile, the detection precision in a complex scene is remarkably improved, and particularly, higher robustness is shown in the aspects of small target recognition and shielding processing.

The invention relates to the technical field of spectral analysis, and discloses a method and a system for detecting the concentration of trace metal ions. The method comprises the following steps: acquiring original spectral response data of an electronic smoke sample; carrying out signal separation by utilizing a frequency domain feature extraction technology to obtain an initial spectrum data set; performing background noise filtering and baseline drift correction on the initial data to obtain a refined spectrum data set; constructing a concentration-wavelength mapping relation through absorption peak positioning and characteristic wave band screening on the basis of the refined spectrum data set; carrying out continuous time sequence sampling on the samples based on the mapping relation to generate a concentration dynamic change data set; analyzing a concentration fluctuation rule and an abnormal point in the dynamic data, and generating concentration risk assessment data; and finally outputting a time sequence detection file. According to the method, high-precision dynamic monitoring and intelligent risk assessment of trace metal ion concentration are realized, interference is effectively inhibited, and sensitivity and early warning capability are improved.

The invention discloses a low signal-to-noise ratio direct spread signal detection method based on noise cancellation, and belongs to the field of communication spectrum sensing. The self-adaptive noise cancellation method based on the minimum mean square error is adopted, non-stationary noise interference can be tracked and eliminated in real time, filtering parameters are automatically optimized in an unknown channel environment, and a signal detection system can adapt to different background noise conditions. And stable signal detection is realized in a low signal-to-noise ratio environment by utilizing a cyclic spectrum analysis method and extracting the cyclic stability characteristic of the direct spread signal. The existence of the signal is judged through the characteristic spectrum peak on the non-zero cyclic frequency, and the carrier frequency and the pseudo code rate are further estimated, so that more accurate signal identification and parameter extraction are realized, the influence of noise uncertainty on the detection performance is avoided, and the detection robustness and reliability are improved. Welch smoothing processing and short-time Fourier transform are combined, the variance of spectrum estimation is reduced when the cyclic spectrum is calculated, and the detection robustness is improved.

The invention relates to a dynamic return-to-zero and suppression method and device for electromagnetic background noise, equipment and a medium. The method comprises the following steps: initializing electromagnetic background noise, and initializing two modes for each frequency point; each mode comprises a mean value, a variance and heat; electromagnetic background noise is collected according to a preset period, and after an electromagnetic background amplitude value is obtained, the final attribution probability of the mode of each frequency point is determined according to the amplitude value of each frequency point and the mean value and the variance of the corresponding mode; according to the final attribution probability of the mode of the current frequency point, the modes are switched in real time through mode judgment, instant interference can be effectively suppressed while timeliness is guaranteed, and permanent electromagnetic background noise is dynamically zeroed. According to the method, the noise model can be adaptively and dynamically adjusted, noise separation is realized, real-time performance and precision are considered, and the application bottleneck of the prior art is broken through.

The invention discloses a mine small target detection method based on deformable convolution and a residual structure, belongs to the technical field of underground small target detection, and further improves the detection precision and robustness of a small target by introducing multi-scale feature fusion and an attention mechanism. The method comprises the following steps: a backbone network reinforces cooperative perception of channel, space and position information in a feature extraction stage by fusing an MLCA attention mechanism, and effectively inhibits background noise interference; on the basis of a DPC-Block multi-scale feature fusion network, the relevance between low-order detail information and high-order semantic features is reserved through cross-layer feature interaction; the detection layer adopts a ShapeIoU loss function to optimize bounding box regression precision and accelerate model convergence; according to the invention, high target detection precision can be realized, and the problem of missing detection of small targets is effectively improved; and an effective solution is provided for small target detection in a complex scene in collaborative optimization of an attention mechanism and feature fusion and a geometric perception loss function.

The invention provides an anti-interference sound and vibration detection method and device, and relates to the field of sound and vibration detection. The method comprises the following steps: acquiring target special equipment and an equipment type corresponding to the target special equipment; according to the equipment type, acquiring a multi-channel high-sensitivity sensing array combination corresponding to the equipment type from a preset inspection method database; acquiring sound vibration signal data corresponding to the target special equipment based on the multi-channel high-sensitivity sensing array combination; performing modal decomposition on the sound vibration signal data by applying an improved empirical mode decomposition algorithm, eliminating pseudo-modal components and reconstructing effective modal signal data; and inputting the reconstructed effective modal signal data into a sound-vibration collaborative recognition model, and outputting a structural state recognition result of the target special equipment through the sound-vibration collaborative recognition model. According to the method and the device, the problem of low sound vibration detection accuracy of a traditional sound vibration detection technology when mechanical impact, fluid disturbance, electromagnetic interference or multi-source background noise is accompanied in the environment where the detected equipment is located is solved.

The invention relates to a robust unmanned aerial vehicle detection method based on dynamic feature fusion and context attention, and belongs to the technical field of image processing. Aiming at the problems of small target feature loss, semantic gap, background noise interference and the like caused by a fixed convolution kernel scale, one-way feature fusion and a static attention mechanism in an existing unmanned aerial vehicle aerial image target detection method, the method comprises the following steps: constructing a detection model comprising a backbone network, a neck network and a detection head network; a feature rearrangement and extraction module is designed in the backbone network to enhance feature learning, an enhanced double-flow feature fusion pyramid is designed in the neck network to optimize multi-scale feature fusion, and a dynamic multi-scale context attention mechanism is designed in the detection head network to suppress irrelevant background noise. The method effectively improves the accuracy and robustness of small target detection, and achieves a clearer and more stable detection effect in a complex environment.

The invention relates to the technical field of direct-current power supply fault diagnosis, in particular to a fault self-diagnosis modular direct-current power supply system, which is characterized in that a failure mechanism dynamic modeling unit constructs a multi-stress coupling degradation mapping library, adopts a degradation mechanism decoupling algorithm to separate and superpose failure effects and generates a dynamic degradation model; the early degradation capture unit deploys a high-frequency wide-domain sampling circuit and a noise suppression signal chain, combines time-frequency domain joint feature extraction and separates degradation feature signals from background noise, and the self-adaptive life prediction unit adopts a long short-term memory network and random forest fusion algorithm to dynamically correct parameters and output residual life probability distribution. The intelligent fault judgment unit realizes progressive diagnosis through a hierarchical threshold decision mechanism, and the health management cooperative execution unit triggers a pre-maintenance strategy, executes power flexible derating, redundancy switching or directional fusing isolation, and improves the reliability of the system.

The invention discloses a sea water area karst cave group transient electromagnetic collaborative investigation data processing method and system, and the method comprises the steps: transmitting a wide frequency spectrum excitation signal to the seabed through a shipborne transient electromagnetic transmitting system, and synchronously collecting a secondary field attenuation signal responded by a seabed medium through a pull-type receiving array, meanwhile, a distributed sensor network is arranged at a preset seabed node to collect background noise base data; performing motion attitude compensation on the secondary field attenuation signal to generate transient electromagnetic response data; constructing an adaptive filter based on the background noise base data, performing noise suppression processing on the transient electromagnetic response data, and outputting noise suppression data; and performing space-time alignment on the noise suppression data of the towed array and the seabed node data to form a three-dimensional space sampling data set. According to the method, high-precision fusion of deep and shallow detection data and quantitative evaluation of the stability of the karst cave are realized, and the detection reliability and the engineering risk early warning capability of the complex ocean karst area are remarkably improved.

The invention provides a multi-step automatic testing method based on machine vision, and the method comprises the steps: capturing an original image sequence of a test scene through a camera, extracting the contour features of a test object in an image through an edge detection algorithm, and obtaining a preliminary positioning coordinate; if the dynamic position change trend exceeds a preset threshold value, adjusting an image enhancement parameter to suppress background noise, and obtaining an enhanced target image; feature matching is carried out through the enhanced target image, a robust identifier such as a texture mode is extracted, and an accurate three-dimensional position coordinate is obtained; according to the accurate three-dimensional position coordinates, calculating an execution deviation value of the current step, and judging whether the deviation value is within an allowable range or not; if the deviation value is within the allowable range, a control instruction sequence is generated and transmitted to the mechanical arm, and a step execution confirmation signal is obtained; comparing a confirmation signal with a next image sequence through the steps, updating positioning model parameters, and determining a continuous adjustment scheme of the whole test process.

The invention provides a method for extracting electrical characteristic signals of electrical equipment in a complex working condition environment, and belongs to the technical field of electrical equipment detection.The method comprises the steps that a multi-channel ultrasonic sensor array is arranged to collect partial discharge signals, background noise is eliminated through adaptive noise cancellation processing, and an ultra-sparse frequency band energy distribution vector is constructed; the method comprises the following steps: calling a self-adaptive time-frequency analysis model to extract instantaneous frequency, amplitude and phase parameters to form a micro-hour-frequency characteristic matrix, separating independent source signals through independent component analysis, calculating a kurtosis value and a skewness value, fusing multi-domain characteristics to construct a transient stationary comprehensive characteristic vector, matching with a standard discharge characteristic vector library to identify the discharge type and intensity, and calculating the discharge intensity. A corresponding prediction algorithm is selected according to the discharge mode, multi-parameter coupling optimization adjustment is started under a certain condition, an electrical characteristic signal description vector is finally constructed, and the technical problem that the partial discharge signal of the power equipment is difficult to accurately extract under a complex working condition environment is solved.

The invention discloses a one-way valve air tightness detection method and system, and relates to the technical field of air tightness detection.According to the one-way valve air tightness detection method and system, through dynamic interaction of AI virtual sensor prediction and physical detection values and combination of time-frequency domain signal fusion, the extraction capacity of micro-leakage signals is remarkably enhanced, and misjudgment caused by background noise or residual gas in a traditional method is avoided; a multi-mode interference source correlation analysis and dynamic weight distribution mechanism is utilized to actively identify and compensate composite interference such as temperature drift and electromagnetic pulse, so that the reliability of a detection result in severe scenes such as workshop vibration and airflow disturbance is improved; and meanwhile, a model adaptation module based on transfer learning and non-contact vibration spectrum monitoring are adopted, manual parameter adjustment dependence is reduced, valve bodies of different specifications are rapidly adapted, early damage of the diaphragm is warned in advance, and the equipment maintenance period is prolonged.

The invention is applicable to the technical field of geophysical detection, and provides an underwater target detection method and device based on acoustoelectric joint and width learning, and the method comprises the steps: carrying out the signal collection through an acoustoelectric joint detection network which is disposed in an underwater monitoring region in advance, the method comprises the following steps: acquiring an acoustic signal and an electromagnetic signal synchronously acquired by each detection node in an acoustic-electric joint detection network, performing feature extraction on the acoustic signal and the electromagnetic signal based on a data sliding window mechanism to obtain an acoustic-electric fusion feature matrix, and calculating the acoustic-electric fusion feature matrix according to the acoustic-electric fusion feature matrix. Whether a target object capable of autonomously radiating an acoustic signal and an electromagnetic signal underwater exists in an underwater monitoring area or not is determined through a pre-trained width learning network, so that false alarm interference caused by background noise in an underwater environment is effectively reduced, and the underwater target recognition capability under a weak signal condition is remarkably improved; and the accuracy of underwater target detection is improved.

The invention discloses a dense target detection optimization method based on mask generation type distillation and cross-task consistency, and the method comprises the steps: obtaining a student model mask graph based on a task perception mask generation algorithm, training a student model through the student model mask graph and a teacher model feature graph, and obtaining a student model with the enhanced feature representation capability. Training student models based on the regression task loss, the classification task loss and the feature map alignment loss to obtain a calibrated student model; the calibrated student model is used to detect the dense target to obtain a target detection result. The problem that the student model is difficult to fully learn task-related knowledge of the teacher model due to the fact that a traditional knowledge distillation method cannot effectively process feature demand differences of classification and regression tasks in dense target detection is solved. And an existing method is easily interfered by background noise and target overlapping in a dense scene, so that the effect of characteristic distillation is influenced.

The invention discloses an airborne laser radar sounding data processing method and system, and relates to the technical field of marine surveying and mapping and earth observation, and the method comprises the following steps: collecting original full-waveform data of an airborne laser radar sounding system, the original full-waveform data comprising infrared laser channel data and blue-green laser multichannel data; joint denoising processing is carried out on the original full-waveform data to obtain denoised waveform data, and the joint denoising processing comprises background noise modeling and removing based on machine learning and random noise filtering based on frequency domain low-pass filtering; a collaborative joint denoising strategy is formed by fusing background noise modeling based on machine learning and frequency domain low-pass filtering based on signal-to-noise ratio optimization. According to the method, complex background noise can be accurately estimated and removed, random noise can be adaptively filtered out, weak underwater echo signals are reserved to the maximum extent, and the problem of water depth information loss caused by excessive smoothness is effectively avoided.