174 results about "Adaptive denoising" patented technology

The invention relates to the technical field of building information modeling, in particular to a building drawing geometric feature extraction and visual modeling method and system, and the method comprises the steps: carrying out the self-adaptive noise reduction, contrast enhancement and line refinement processing of an original building drawing image, and carrying out the automatic layer separation based on colors and line types; linear geometric features and specific symbol geometric features in the drawing image are extracted, and a geometric feature set is constructed; component instantiation, attribute assignment and topological relation reasoning are carried out by using a predefined building component semantic rule base, and a building component semantic network is generated; and mapping the semantic network to a parameterized three-dimensional modeling engine, calling an IFC standard three-dimensional template, performing parameter driving and automatic assembly, generating a three-dimensional building model with semantic information and a spatial structure, and performing visual output. According to the method, efficient and standardized conversion from a two-dimensional building drawing to a three-dimensional building model can be realized, and the method has the remarkable advantages of processing complex drawings and high-precision modeling.

The invention provides an intelligent event identification method and system based on a high-speed camera, and the method comprises the steps: setting the collection parameters of the high-speed camera, and triggering the camera to collect a target scene video stream. And hardware acceleration decoding processing is carried out on the collected original video data stream, real-time environment illumination information of the environment illumination sensor is obtained, and dynamic brightness equalization processing is executed. And performing motion adaptive denoising processing on the video sequence. Geometric distortion correction is carried out on the image sequence through camera calibration parameters, sub-pixel-level displacement vectors and dense optical flow field data of a moving object are extracted, and multi-scale morphological features are extracted. And the features are fused to generate motion feature data, the data are processed through a spatio-temporal joint event classification model, an event identification result is output, the result is bound with a high-precision timestamp, and event identification information is output to an industrial control system display device in real time. According to the invention, the accuracy and real-time performance of event identification can be improved.

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based electric energy quality disturbance identification and positioning method, which comprises the steps of constructing an electric energy quality disturbance signal data set, performing segmented preprocessing on electric energy quality disturbance voltage data, enhancing time-frequency joint features and encoding disturbance sensitive areas. And constructing a deep learning model for power quality disturbance identification and positioning, and identifying and positioning the power quality disturbance. According to the invention, through adaptive denoising processing, boundary detection and multi-resolution time-frequency feature extraction, the identification precision and positioning precision of power quality disturbance are significantly improved; self-adaptive wavelet denoising and dynamic segmentation are combined, noise interference is effectively suppressed, and the edge characteristics of voltage sudden change points are kept; according to the dual-task sharing network, disturbance identification and positioning tasks are cooperatively optimized, so that the network can consider disturbance classification and time positioning at the same time; and through Bayesian reasoning, the system can output confidence estimation, provides credibility quantification of identification and positioning results, and effectively improves the reliability of the system.

The invention relates to an image processing method for an underwater robot heterogeneous imager array, and the method comprises the steps: S1, collecting an original underwater image, and carrying out the brightness adjustment, and obtaining a first image with balanced brightness; s2, analyzing pixel distribution of the first image, and judging and executing de-scattering processing to obtain a second image; s3, performing multi-scale detail enhancement on the second image to obtain a third image with richer details; s4, evaluating color distribution of the third image, and performing color correction to obtain a fourth image; s5, performing adaptive denoising processing on the noise features of the fourth image to obtain a fifth image; s6, according to the contrast characteristic of the fifth image, contrast adjustment is carried out to ensure that a preset threshold value is met, and a sixth image is obtained; s7, edge enhancement processing is carried out on the sixth image, and a seventh image with the clear edge is obtained.By means of illumination compensation, scattering removal and multi-scale detail enhancement, the influence of complex optical conditions of the underwater environment on the image quality is effectively overcome.

The invention discloses a ring piece ultrasonic detection noise reduction and identification method and system and a computer storage medium. The method comprises the steps that a matched ultrasonic phased array probe is selected according to the shape and size of the cross section of a workpiece, and technological parameters are set and comprise at least one of the probe frequency, the number of array elements, the water layer height and the focusing depth; according to the selected ultrasonic phased array probe and process parameters, ring piece water immersion ultrasonic phased array detection is carried out, full-coverage scanning is carried out in a weld joint area, and the scanning position of the probe is recorded in real time through an encoder; in the scanning process, an ultrasonic image scanned by the phased array probe is collected in real time, and the ultrasonic image is transmitted to a pre-trained adaptive noise reduction YOLOv5 target detection model for defect recognition; and the rotating angle position of the ring piece is recorded in real time through an encoder, and when the target detection model finds defects, the defect position is recorded, and alarm information is generated. The method is suitable for ring piece ultrasonic detection noise reduction and recognition, the defect recognition accuracy can be improved, and the manual labor intensity is reduced.

The invention provides a high-noise-resistance bearing fault diagnosis method for complex working conditions, relates to the technical field of bearing fault detection, and constructs a progressive technical system of'dynamic noise reduction-multi-modal fusion-cross-domain association '. According to the method, firstly, working condition self-adaptive noise reduction is achieved through sliding window dynamic principal component analysis, and redundant noise caused by rotating speed fluctuation is stripped while periodic impact characteristics are reserved; meanwhile, on this basis, a time domain-frequency domain multi-mode complementary feature system is constructed, and the denoised signals are respectively input into a bidirectional gating circulation unit and an improved residual network added with FFT transform to extract bidirectional time sequence dependence and frequency domain texture features. And finally, performing feature enhancement on a time sequence signal and a time-frequency image extracted by the multi-modal feature network by adopting eight self-attention, constructing a dynamic interaction channel by taking a time sequence feature as Query and an image feature as Key-Value, and adaptively screening a cross-modal association feature most related to the context of the current rotating speed.

The invention provides a liver echinococcosis ultrasonic image intelligent processing method based on deep learning, electronic equipment and a storage medium. The method comprises the following steps: data collection: collecting liver ultrasonic image data; carrying out image preprocessing on the collected liver ultrasonic image data by using an adaptive denoising and enhancement model, carrying out classification labeling on the data after image preprocessing, establishing a classification data set, and labeling the images as cystic echinococcosis, alveolar echinococcosis and other liver lesions; and based on the classification data set, training an optimized VIT classification model DFEV-VIT. The beneficial effects of the invention are that the method carries out the image preprocessing of the collected data through employing the optimized CLAHE algorithm ADEN, and carries out the training of the classification model DFEV-VIT based on the classification data set after the image preprocessing, can greatly improve the diagnosis efficiency and accuracy, and reduces the missed diagnosis and misdiagnosis of the echinococcosis.

The invention discloses a music data identification method and device based on multiple sound parts, equipment and a storage medium. The method comprises the steps that music data is collected and then preprocessed, noise interference is removed, the music data is converted into a spectrogram through multiple kinds of time-frequency analysis, features are extracted through a deep learning algorithm fusing CNN, RNN and an attention mechanism, then sound parts are classified and labeled, adaptive noise elimination and a filter are adopted in preprocessing, and volume normalization is carried out. The device comprises a data acquisition module, a preprocessing module, a time-frequency analysis module, a feature extraction module and a classification labeling module, and the equipment comprises a processor and a memory to execute the method. The method is also realized when the program stored in the storage medium is executed; through adaptive denoising, a multi-analysis method, a composite deep learning model and a classification labeling technology, noise is effectively removed, sound features are clearly displayed, features are accurately extracted, sound functions are determined, processing efficiency is improved, large-scale real-time processing requirements are met, and digital development of the music industry is assisted.

A virtual reality technology-based printed circuit board defect detection system relates to the technical field of printed circuit board detection, and comprises the following steps: shooting a printed circuit board according to initial shooting parameters, obtaining visual image data of the printed circuit board, and obtaining other modal data of the printed circuit board; performing feature analysis on the visual image data, and performing adaptive adjustment on shooting parameters of the printed circuit board according to a feature analysis result; performing adaptive denoising preprocessing on each pixel point in the grayscale image to obtain a denoised grayscale image; performing feature extraction and detection on the grayscale image to obtain abnormal key features in the grayscale image; outputting types and severity coefficients of the abnormal key features; and visually displaying the type, the severity coefficient and the coverage area of the abnormal key features of the printed circuit board. According to the invention, the efficiency and accuracy of printed circuit board defect detection are obviously improved.

The invention discloses a laser radar echo signal distance inversion method based on a deep learning combination model, and belongs to the technical field of laser radar signal processing. According to the method, firstly, a CNN, ResNet or DCNN architecture is adopted to construct a spatial feature extraction module, and local and global spatial features of echo signals are extracted through multi-scale convolution, residual connection and an adaptive denoising mechanism; then, a time sequence dependency relationship of the signals is captured by utilizing BiGRU bidirectional time sequence modeling and a multi-head self-attention mechanism of Transform; and integrating the spatio-temporal features through the feature fusion layer, and then outputting a distance inversion value through the full connection layer. A parallel multi-scale CNN, a shrinkage enhanced residual network and a lightweight DCNN structure are innovatively designed, and the problems of insufficient spatial-temporal feature fusion of a single model and precision degradation under low signal-to-noise ratio interference are solved in combination with dynamic gating adjustment of a bidirectional gating circulation unit and dynamic position coding of Transform. According to the method, the precision and robustness of distance inversion in a complex environment are remarkably improved, and the method can be applied to the fields of automatic driving, environment monitoring and the like.

The invention relates to the technical field of radar electronic countermeasures, and particularly discloses a radar radiation source open set identification method (ARPLAD) based on countermeasure reciprocity point learning. The method comprises the steps that adaptive noise reduction and feature extraction are conducted on radar signals through a feature extraction network fusing a DRSN module and an ECA module, channel-level adaptive noise reduction is achieved through the DRSN by means of a soft threshold function, and key features are strengthened through dynamic weight distribution by means of the ECA; an adversarial reciprocity point learning framework is adopted, reciprocity points are set for each known class to serve as out-of-class space representation, and known and unknown class feature spaces are separated by maximizing the distance between known class samples and the corresponding reciprocity points; introducing a central loss function to compress intra-class feature distribution, and constructing a weighted total loss function optimization network in combination with an open space limitation function; and calculating a class self-adaptive threshold value based on the training sample, and comparing the maximum distance from the sample to each reciprocity point with the threshold value during testing to judge known and unknown classes.

The invention discloses a vocal cord problem recognition and feedback system for the ophthalmology and otorhinolaryngology department. The vocal cord problem recognition and feedback system comprises a sound collection module, an image collection module, a biological feedback module, a data processing module, an AI diagnosis module and a rehabilitation guidance module. The sound acquisition module comprises a microphone array and a self-adaptive noise reduction unit; the image acquisition module is provided with an endoscope camera and an image enhancement processor; the biological feedback module integrates a laryngeal myoelectricity sensor and a three-dimensional motion simulator; the data processing module executes multi-modal feature extraction and fusion; through mutual cooperation of the sound acquisition module, the image acquisition module, the biological feedback module and the data processing module, data can be accurately acquired, the early canceration detection rate is improved and the misdiagnosis rate is reduced through multi-modal fusion, the data acquired by the multi-modal structure is analyzed through the data processing module, the model is combined with a weekly updated disease map, and the early canceration detection rate is improved. And the recurrence prediction accuracy is improved.

The invention discloses a medical image semantic segmentation method based on attention mechanism optimization, and relates to the technical field of medical image processing, and the segmentation method comprises the specific steps: S100, data collection and label preprocessing: collecting medical image data from different medical institutions and a plurality of imaging devices, according to the method, the attention mechanism is introduced to carry out deep preprocessing on the medical image data, the precision and efficiency of semantic segmentation of the medical image are remarkably improved, the attention mechanism is utilized, key areas, such as diseased regions or tissue boundaries, in the image can be recognized and enhanced, meanwhile, noise and irrelevant information are effectively removed, and the accuracy of semantic segmentation of the medical image is improved. The refined preprocessing mode not only improves the quality of the image, but also provides a more accurate data basis for subsequent image detection and segmentation, and the method is also combined with a self-adaptive denoising algorithm, dynamic adjustment of contrast, brightness and color and a geometric transformation advanced preprocessing technology, so that the availability and diagnostic value of the image are enhanced.

The invention provides an optical cable fault positioning method based on OTDR signal characteristic adaptive denoising and event identification, and the method comprises the steps: classifying modal components after OTDR signal adaptive noise decomposition based on a preset entropy threshold value, and obtaining a noise dominant component, a mixed component and a signal dominant component; singular value difference spectrum abrupt change point detection is carried out on the noise dominant component, and residual useful signals are extracted; verifying the entropy value of the mixed component, and reconstructing the component meeting the entropy threshold value, the signal dominant component and the residual useful signal into a de-noised signal; synchronously optimizing hyper-parameters and feature selection subsets of the support vector machine by adopting a swarm intelligence algorithm, wherein search parameters of the algorithm are dynamically updated according to an exponential decay mechanism; and outputting fault point space position information based on the optimized support vector machine model.

The invention discloses a multi-modal data adaptive denoising and missing reconstruction method and system, and relates to the technical field of point data denoising and reconstruction, and the method comprises the steps: obtaining to-be-processed multi-modal original data and a modal missing mask; performing unsupervised denoising on image data in the multi-modal original data to obtain a denoised image, and further obtaining multi-modal data; inputting the multi-modal data into a double-flow encoder for processing to obtain a multi-modal embedded vector of cross-modal alignment; the method comprises the following steps of: performing mapping and adding position embedding on a modal embedding vector to obtain each modal coding feature, determining a missing modal based on a modal missing mask, inputting an available modal coding feature into a retrieval enhanced expert model based on prototype memory to perform missing reconstruction to obtain a multi-modal joint representation, and mapping the multi-modal joint representation to a task output space through a full connection layer. Through introduction of unsupervised denoising, double-flow coding alignment and modal knowledge expert hybrid reconstruction, robust representation learning and information complementation under the condition that noise and modal missing exist in multi-modal data are realized.

The invention discloses a food waste detection method and system based on image processing, belongs to the field of image recognition, and aims to realize efficient and automatic recognition and quantification of kitchen waste. According to the method, residual food images are collected at multiple periods and multiple angles in a kitchen garbage can or a dinner plate recovery area through high-resolution and multi-spectral imaging equipment, preprocessing is carried out in combination with an improved Retinex algorithm and a space self-adaptive denoising technology, and the image quality is improved. Afterwards, fine segmentation of a food area is achieved through a multi-scale super-pixel segmentation and graph segmentation algorithm, and multi-category intelligent recognition is conducted on remaining food through a recognition network fused with multi-modal features. The system further combines stereoscopic vision and Monte Carlo sampling to dynamically and accurately count the volume or weight of various residual foods. The method has the advantages of high adaptability and accurate statistical result, and can provide data support for catering management, resource recovery, nutrition evaluation and the like.

The invention relates to the technical field of image stitching, and discloses a video transmission high-definition image intelligent stitching method and system. The system comprises an image preprocessing module, a feature point matching and screening module, an image optimal splicing seam generation module and a video output module. The method comprises the following steps: firstly, acquiring a video, carrying out dynamic range equalization, carrying out filtering processing by using an adaptive noise reduction method, and carrying out image correction; secondly, extracting feature points by using a self-adaptive corner detection algorithm, matching the feature points based on a multi-dimensional spatial data index to obtain feature point matching pairs, and screening the feature points; searching an overlapping region, and introducing a dynamic search algorithm to generate an optimal image splicing path to obtain an optimal image splicing seam; and finally, dividing the image according to the dynamic grid, and realizing video output by using priority ranking. According to the method, the video images are processed and spliced, the purpose of intelligent image splicing is achieved, and the method is accurate and objective.

The invention belongs to the technical field of image processing, and particularly discloses a vehicle-mounted camera image denoising and enhancing method and system, an image is decomposed into sub-band images with different frequencies through multi-scale decomposition, so that noise and details are processed on different scales, aiming at the characteristics of different sub-bands, a self-adaptive algorithm is adopted to estimate noise intensity, and the noise intensity is improved. According to the method, a high-frequency sub-band image is estimated, adaptive denoising processing is carried out according to the estimated noise intensity, the denoising effect is ensured, meanwhile, blurring of edges and textures is reduced, the processing quality is improved, detail enhancement operation is carried out on the denoised high-frequency sub-band image, a deep learning model structure and parameters are optimized in the training process, and the robustness of the high-frequency sub-band image is improved. The method can effectively improve the image quality under limited computing resources, the design of the deep learning model reduces the calculation amount, the powerful feature learning capability of the deep learning model can capture the image features which are difficult to process by a traditional method, and the denoising and enhancement effects are further improved.

The invention discloses a cutting fluid solid particle concentration measurement method and system, and relates to the technical field of particle concentration measurement, a time sliding window mode is used for carrying out fusion processing on an image sequence, synchronous acquisition of temperature and illumination intensity is combined, a dynamic temperature illumination normalized background image is constructed, and the concentration of solid particles in a cutting fluid is measured. The problems of brightness drift, image flicker and the like caused by environmental fluctuation are effectively eliminated, and the stability and adaptability of background modeling are remarkably improved. Through a disturbance identification and characteristic parameter extraction module, multi-dimensional characteristic extraction is carried out on non-particle disturbance such as bubbles, oil films and light reflection possibly occurring in the image, a disturbance characteristic set Rdr is formed, and the system can accurately identify and distinguish non-real particle signals. And through a dynamic difference denoising analysis module, a disturbance feature set Rdr is combined to carry out adaptive denoising on a difference image, a real particle structure is reserved, a non-particle interference region is eliminated, and a purified image with an enhanced edge is output, so that cleaner and more accurate basic data is provided for subsequent particle identification.

The invention relates to the technical field of carbon emission source inversion calculation, in particular to a construction site carbon emission source inversion calculation method based on an atmospheric diffusion model. According to the technical scheme, the method comprises the following steps that a spatial diffusion model is constructed, meteorological parameters of a construction site are obtained through meteorological monitoring equipment, pollutant concentration distribution is calculated based on an atmospheric diffusion model, and the model corrects vertical diffusion by introducing a mirror image source item; performing dynamic noise reduction on the data: performing filtering processing on the original monitoring data, and balancing noise suppression and real fluctuation retention through a dynamic adjustment algorithm; performing iterative inversion calculation; and comprehensive verification: combining theoretical simulation with actual detection. Through the dynamic coupling meteorological-emission model, the adaptive noise reduction algorithm and the multi-source verification mechanism, accurate, efficient and low-cost inversion of the carbon emission source of the construction site is realized, and reliable technical support is provided for real-time carbon management, carbon transaction and green construction.

The invention provides a weld defect detection method and system fusing TOFD image waveform characteristics. The method comprises the following steps: carrying out adaptive noise reduction processing on TOFD image data and TOFD waveform data; performing feature extraction on the TOFD image data and the TOFD waveform data after adaptive noise reduction processing through a dual-network view angle to obtain image multi-scale features and waveform time sequence features; fusing the image multi-scale features and the waveform time sequence features by adopting a self-adaptive attention weighting mode to obtain fused features; and performing defect detection based on the fusion features. According to the method, film evaluation knowledge of'simultaneous analysis of wave maps' in the field of nondestructive TOFD detection is fused, TOFD image weld defect detection and identification are realized, and the accuracy and reliability of a defect detection result are improved.

The invention relates to the technical field of artificial intelligence image processing and biological detection crossing, and discloses a perception enhancement and feature distillation-oriented high-density microalgae detection method, which comprises the following steps: acquiring a high-density microalgae image containing cell overlapping, boundary blur and cross-scale distribution, and inputting the image into a backbone network to extract a multi-scale feature map; optimizing the bounding box through potential consistency mapping processing; generating a microalgae density map through density sensing auxiliary processing, and calculating density loss; self-adaptive denoising is carried out based on image complexity; a student model is optimized by using a dual-feature distillation framework, and the small-scale microalgae detection capability is enhanced; and finally, fusing the results of the modules, and outputting the position, category and quantity of the microalgae. According to the method, the overall average accuracy of high-density microalgae detection can be improved, bounding box jitter and small-scale microalgae omission ratio are reduced, the average reasoning time is shortened, the real-time detection requirement is met, and reliable data support is provided for microalgae culture process control and optimization.

The invention discloses a student psychological risk perception method based on multiple modes, and relates to the technical field of emotion calculation and intelligent education. The method comprises the following steps: firstly, extracting a facial expression feature vector and a voice intonation feature vector respectively by using a convolutional neural network and Fourier transform through a collected video stream and an audio stream; then adaptive denoising processing is carried out on environmental interference, timestamp alignment and dynamic time warping are carried out on the denoised multi-modal data, time sequence synchronization is ensured, and corrected multi-modal sequence data are formed; then, dynamic emotion track features are extracted from the sequence data, a preliminary emotion state label is generated by comparing the dynamic emotion track features with a baseline threshold value, and the threshold value is adaptively updated in combination with historical data so as to improve the judgment accuracy; and finally, aggregating the emotional state labels of a plurality of students to generate a visual group emotional thermodynamic diagram so as to realize macroscopic perception of group psychological risks. The accuracy, robustness and visualization degree of student psychological state analysis are effectively improved, and an efficient technical means is provided for campus psychological early warning.

The invention relates to an adaptive weighted bilateral filtering deconvolution OCT image processing method and system, and the method comprises the steps: carrying out the preprocessing of an original OCT signal, including background noise removal, wave number calibration, spectrum shaping and dispersion compensation, so as to obtain an OCT reconstructed image; enhancing the contrast ratio through histogram stretching, adjusting the space weight and the intensity weight of the OCT stretching image, and performing adaptive denoising on the image; and further optimizing the image by using a blind deconvolution algorithm, and iteratively updating the estimated image and a point spread function (PSF) to obtain a high-definition OCT reconstructed image. According to the method, efficient denoising and detail reservation of the OCT image are realized through adaptive weighted bilateral filtering and blind deconvolution technologies, so that a high-definition reconstructed image is obtained.

The invention discloses a law enforcement behavior intelligent supervision system and method based on edge computing, and relates to the technical field of edge computing. Multi-modal data of each law enforcement communication terminal is collected, and adaptive denoising is performed on video data of the law enforcement communication terminals; incremental updating is carried out on the general noise level of the video data of the law enforcement communication terminal, and scene reclassification is carried out according to an incremental updating result; the method comprises the following steps: performing human body feature recognition on a first frame image of video data, performing human body feature matching and shielding frame and visible frame marking on a subsequent frame image of the video data, constructing a dynamic graph convolutional network according to a marking result, marking tracking targets, modeling each tracking target as graph nodes, constructing dynamic edge weights among the nodes, and performing image segmentation on the dynamic edge weights; outputting spatial features of the tracking target in each shielding frame; and the danger early warning level of each tracking target is output, and data grading uploading is performed according to the danger early warning levels, so that the data identification accuracy and the data management security are significantly improved.

The invention discloses an infrared visible light image fusion system based on semantic-driven space-frequency routing, and aims to solve the problems of multi-mode redundancy, weather degradation and insufficient space-frequency modulation. The core of the method comprises the following steps: a CMBA module realizes cross-modal bottom layer interaction and redundancy elimination; the FASRP module is integrated with 2D-SSM to perform long-range modeling, and high and low frequency feature decoupling is realized by using a routing mask; the DSPE module extracts environment degradation semantic priori by relying on a visual language large model; the DFMB module decouples the features into amplitude and phase, and realizes adaptive denoising according to prior dynamic gating. And the system reconstructs the image through fidelity fusion and progressive decoding. According to the method, the generalization ability in a complex scene is improved, and the fused image has precise infrared target positioning and visible light texture details.

The invention relates to the technical field of infrared imaging, in particular to an infrared image self-adaptive denoising algorithm and system based on an FPGA (Field Programmable Gate Array), and is characterized in that an adaptive blind pixel searching algorithm module captures data of a certain frame number at an FPGA end, performs multi-directional gradient detection on each pixel point, sets conditions to judge to obtain a blind pixel position, and marks the blind pixel position; the convolution kernel self-adaptive blind pixel replacement module performs self-adaptive blind pixel replacement multi-time module multiplexing at the PL end of the FPGA through a convolution kernel sliding block and gradient comparison to ensure complete coverage of a large blind pixel group, and the self-adaptive median filtering module intelligently selects and replaces pixels meeting requirements through automatic sorting of center pixels and surrounding pixels; according to the method, surface fuzzy filtering is carried out through a surface-blue algorithm module, so that a smooth area in an image is effectively smoothed, details of an edge area are reserved, blind pixels in a video stream can be effectively detected and compensated, and meanwhile traditional noise is suppressed and image details are reserved through multi-stage filtering.

The invention relates to a point cloud denoising method of a photon counting laser radar and an intelligent denoising system, and belongs to the technical field of photon laser radar data processing. The technical problems that the performance of a fixed parameter denoising method is seriously unbalanced under different ground feature and complexity scenes, and high denoising rate and high signal fidelity cannot be considered at the same time are solved. Synchronously acquiring an optical image and an original photon point cloud of the target area; identifying the dominant ground feature type of the laser spot area through real-time semantic segmentation; calculating scene complexity based on the point cloud data and determining the grade of the scene complexity; querying a preset two-dimensional parameter mapping table according to the combination of the surface feature type and the scene complexity level, and dynamically obtaining an optimal denoising parameter set; and finally, the parameter set is utilized to drive adaptive denoising processing, and signal points and noise points are distinguished by calculating the local density and direction consistency of the points and constructing a two-dimensional discrimination space. The method is mainly used for real-time processing platforms such as unmanned aerial vehicles, and the point cloud denoising precision, the signal retention rate and the topographic feature fidelity are remarkably improved.

The invention discloses a power transmission line unmanned aerial vehicle inspection depth visual intelligent identification method and system, and relates to the field of power transmission line inspection, and the method comprises the steps: dynamically adjusting imaging parameters based on the voltage grade and environment complexity of a power transmission line, collecting the multispectral visual data of a line body, a metal fitting for line connection and fixation, and a gallery environment, according to the invention, the method can dynamically adapt to the voltage grade of the power transmission line and the environmental complexity, optimizes the imaging effect, accurately collects the multi-dimensional visual data, and associates the key environmental parameters. The data standardization level is improved through adaptive noise reduction, accurate splicing and distortion correction, defect features and environment association attributes are efficiently mined through an attention guidance mechanism and a dynamic convolutional network, and accurate judgment of defect types and levels and future evolution trend prediction are performed in combination with historical data.

The invention relates to the technical field of graph contrast learning, in particular to a graph contrast learning recommendation method based on adaptive denoising enhancement and difficult negative sample generation. According to the method, a dynamic denoising mechanism is introduced to automatically and accurately recognize and filter noise edges, meanwhile, key information interaction in an original image is effectively reserved, linear mixing is carried out on embedding of an original view and a denoised view, then a loss function is optimized through two-stage joint, and the image quality is improved. The whole model is uniformly trained in combination with double-view representation and high-quality negative samples while noise is removed, and finally, the model can sensitively capture subtle differences between positive and negative samples through high-quality difficult negative samples generated adaptively, so that the discrimination ability of comparative learning is remarkably improved, and the accuracy of comparative learning is improved. The method not only strengthens the recognition capability of the model for the negative sample, but also optimizes the contrast learning target, effectively improves the overall learning effect and generalization capability, and provides a powerful guarantee for the accuracy of a personalized recommendation algorithm.