39 results about "Feature compensation" patented technology

The invention belongs to the technical field of building construction safety control, and particularly discloses a building construction site dangerous behavior recognition method and system based on machine learning, and the method comprises the steps: obtaining a single-view continuous video stream of a construction site, segmenting the single-view continuous video stream into a time sequence video frame sequence, and extracting an initial spatial feature sequence through a spatial feature encoder; a pre-trained virtual visual angle projection and feature compensation module encodes the visual angle implicit vector and maps the visual angle implicit vector to a visual angle invariant feature space, and a sequential context is combined to compensate occlusion missing features to generate an enhanced feature sequence; a time sequence memory alignment module captures long-term and short-term time sequence dependence and outputs time sequence consistency characteristics; and finally, outputting a current dangerous behavior classification result through the classification prediction head, and outputting a future dangerous intention probability curve through the time sequence prediction head. The method does not need an additional camera, can accurately cope with a shielding scene, predicts the danger in advance, and improves the construction safety monitoring efficiency and reliability.

The invention discloses a three-dimensional occupancy perception method and system suitable for multiple tasks, and belongs to the field of robot perception, and the method comprises the steps: carrying out the manual labeling of point cloud data and image data, obtaining a point-by-point label and a pixel-by-pixel label, carrying out the data verification, converting the point cloud data with the labels into a 3D semantic occupancy label of a scene through 3D semantic reconstruction, and carrying out the recognition of the 3D semantic occupancy label. Forming sample data; training a three-dimensional occupancy perception model by using the sample data and performing three-dimensional occupancy perception prediction; sequentially performing feature enhancement extraction, feature dimension conversion, feature time sequence fusion and feature compensation correction on the image data based on a feature extraction module to obtain multi-scale voxel features; the feature information of the multi-scale voxel features is independently adjusted through a semantic segmentation head and a target detection head, then a 3D semantic occupancy result and an instance detection result are output, the two detection results are converted into an instance segmentation result and a target tracking result through a post-processing module, and low-cost and high-efficiency multi-task three-dimensional occupancy perception is achieved.

The application discloses a gas extraction water ring vacuum pump fouling degree online detection system and method, relates to the technical field of vacuum pump fouling degree detection, and comprises a sound signal acquisition module, an excitation control module, a parameter sensing module, a signal processing module, a feature compensation module, a fouling inversion module and a model calibration module; the sound signal acquisition module is arranged on the outer wall of the pump body and is used for acquiring structural vibration signals generated in the operation process and outputting original vibration data; the excitation control module is connected with a piezoelectric excitation device and receives the operation state feedback of the sound signal acquisition module, is used for triggering the piezoelectric excitation device to apply high-frequency pulse signals to the pump shell when the suction negative pressure fluctuation is stable and continuously meets the steady-state condition, and synchronously starts the sound signal acquisition module to collect response signals; and the parameter sensing module is used for monitoring the cooling water inlet / outlet temperature and motor current waveform and outputting environmental and operation parameters.

The invention relates to the technical field of electromagnetic valve manufacturing and quality detection, and discloses an online detection system for the pressing force of a valve element of an electromagnetic valve, and the system comprises a composite magnetic field excitation module, a multi-physical field signal acquisition module, a multi-dimensional feature resolving module and a force value estimation output module. A composite magnetic field is applied to a valve element, and an induced voltage signal, a Hall signal and a temperature signal are synchronously collected; then, three characteristic quantities of harmonic amplitude, instantaneous magnetic field intensity and instantaneous temperature are calculated; and finally, inputting the three characteristic quantities into a preset multi-dimensional mapping model, and calculating to obtain a pressing force estimated value. The invention aims to solve the problem of low measurement accuracy caused by the fact that the existing single electromagnetic parameter detection is easily interfered by temperature and excitation field fluctuation. And through multi-physical field signal fusion and multi-dimensional feature compensation, the influence of disturbance factors is effectively eliminated, and the accuracy, stability and anti-interference capability of online detection are remarkably improved.

This invention provides a multimodal fusion-based method for correlation analysis of deep-sea environmental data outside the Yangtze River Estuary, belonging to the field of deep-sea environmental analysis technology. This invention achieves accurate data registration by establishing a spatiotemporal standardization model for multi-source data and employing an adaptive spatiotemporal kriging interpolation algorithm. It utilizes a sparse coding marine signal separation algorithm to construct an overcomplete dictionary to separate mixed signals and extract pure features. Based on an attention mechanism, a feature extraction network is constructed to automatically learn deep feature representations of physical, chemical, and biological parameters. A matrix rank deficiency detection algorithm is used to automatically supplement feature compensation vectors to ensure feature integrity. A cross-scale attention mechanism based on wavelet transform is constructed to fuse multi-scale features. A Shapley value interpretability evaluation system is established to quantify the importance of correlated features. This invention solves the technical problem of inaccurate correlated feature extraction during the fusion of multi-source heterogeneous marine environmental data.

The application discloses a hydrological remote sensing image target recognition method based on a deep semantic model, relates to the technical field of remote sensing image processing, and comprises the following steps: obtaining a primary semantic code of a hydrological remote sensing image through a deep semantic network, calculating a semantic attribution probability distribution according to the primary semantic code, generating an initial attention guide signal, dynamically adjusting the weight of a specific perception path in the network, realizing first feature re-extraction to obtain refined features, calculating a feature compensation vector based on the confidence deviation generated by matching the features with a standard feature library, correcting the refined features to obtain enhanced features, and inputting the enhanced features into the network again for analysis to obtain a final recognition result. Through the attention adjustment of the semantic guide and the feature compensation based on the confidence feedback, the method effectively improves the recognition accuracy of complex hydrological ground object targets and the model robustness.

The application discloses an end-to-end pest detection method with feature compensation and local information enhancement, and belongs to the field of deep learning. First, a Transform network framework based on feature representation compensation and cross-shaped window attention mechanism is established to extract multi-scale features of an image. Second, regional grid self-attention is used to replace even-numbered multi-head self-attention modules in a Transform model encoder to obtain feature information of the image. Finally, the first K encoder features in the last layer are selected to initialize the position query of a Transform decoder with contrastive denoising, and the content query remains a learnable parameter. Compared with a convolution-based method, the technical scheme of the application can achieve a higher average precision mean in a pest detection task.

The application discloses a kind of vehicle axle intelligent identification optimization method and system based on neural network, belong to neural network technical field;Image acquisition is carried out in ETC lane, vehicle passing image sample set is constructed, and scene identification parameter is established, vehicle image is divided into regions, and the weight of correction of obstruction is calculated;Based on convolutional neural network, multi-level features are extracted, features are compensated in the obstruction area by neighborhood feature compensation module, and complete axle candidate feature map is formed;Then the candidate feature map is input into the lightweight neural network model, the multiscale fusion of shallow and deep features is combined, and the feature layer weight is dynamically adjusted according to the obstruction correction weight, and the axle recognition result is output;Finally, according to the preset axle configuration rule base, the vehicle model identification is matched, and the sample-parameter-classification mapping dataset is established.The axle feature can be still stably identified under complex illumination and obstruction conditions, and the accuracy and robustness of ETC lane vehicle identification are improved.

This invention discloses a network security traffic feature compensation and identification method based on graph neural networks. The method includes: acquiring network traffic data to be tested and extracting key attributes; constructing a dynamic heterogeneous graph based on the key attributes; performing feature compensation processing on the dynamic heterogeneous graph, mapping nodes to a three-dimensional coordinate space and compensating for missing feature dimensions; inputting the compensated dynamic heterogeneous graph into a graph neural network model to generate node state information; comparing the node state information with a sparse baseline to output an anomaly score; and generating a virtual network function management strategy based on the anomaly score and deploying it to the target node. This invention achieves traffic feature compensation through three-dimensional coordinate mapping and neighbor feature aggregation, combines graph neural networks and a sparse baseline for anomaly detection, and forms a closed-loop response through inference acceleration and automatic VNF deployment, thereby improving the accuracy and real-time performance of network security detection.

The embodiment of the invention provides an audio processing method and system, computing equipment and a storage medium. The audio processing method comprises the following steps: acquiring various types of initial audio and reference audio features; based on the initial audio feature of the initial audio, determining an audio feature relationship between the initial audios of various types; constructing a feature compensation model based on a reference audio feature and an audio feature relationship by taking an auditory frequency response relationship as a constraint; obtaining a feature compensation value of the initial audio based on a feature compensation model; and adjusting the initial audio features based on the feature compensation value to obtain multiple types of target audios. According to the technical scheme of the invention, the loudness standards of various types of audios can meet the requirements, the spatial sense and the layering sense of sound are prevented from being damaged, and the unreasonable covering phenomenon of various types of audios in a sound mixing scene is avoided, so that the overall hearing sense and the spatial layering sense of various types of audios after being integrated into a final product are improved, and the sound quality is improved. The method can be widely applied to the fields of digital culture product manufacturing software and the like.

The application is suitable for the technical field of target detection, and provides a dead chicken detection method based on multi-scale reconstruction layer aggregation and feature compensation progressive fusion, including: acquiring a target detection image, the target detection image including dead chickens and live chickens, inputting the target detection image into a preset YOLO model, outputting a dead chicken detection result, the preset YOLO model including a backbone feature extraction network, a feature fusion module and a detection output head, the backbone feature extraction network being a preset multi-scale reconstruction efficient layer aggregation MSR-ELAN network, and the feature fusion module being a preset feature compensation progressive fusion pyramid FCPFN network. Thus, by segmenting and recombining the extracted features, using a multi-stage feature interaction and integration strategy, the overall perception ability of the target is optimized, thereby effectively improving the detection performance of the dead chicken target.

The present invention relates to the technical field of person re-identification. Disclosed are a cross-modal person re-identification method and system based on wavelet transform. The method comprises: constructing a two-stream ResNet-50 backbone network; by means of an ICB module, fusing shallow features of the two-stream ResNet-50 backbone network, so as to obtain fused features; by means of a WEB branch module, performing feature extraction on the fused features, so as to obtain modality-shared features of high-frequency and low-frequency portions; and by means of a dual-branch center-guided loss, optimizing the modality-shared features output by the WEB branch module and the fused features output by the ICB module, so as to obtain a final identification result. In the present invention, an information compensation module is combined with wavelet transform to aggregate shallow network features in different phases, and thus valuable information lost in network feature extraction is compensated for, thereby improving the quality of a final feature vector; and a wavelet enhancement module is provided, and a dual-branch center-guided loss is used to guide a network to mine modality-invariant information in wavelet subgraphs, thereby improving the model performance.

The invention relates to the technical field of digital image processing, and discloses a multi-modal image fusion method for spatial perception multi-scale feature learning, which comprises the following steps of: processing a registered multi-modal image pair by adopting a hierarchical expansion convolution structure so as to obtain multi-scale features with different receptive field ranges in parallel; processing the multi-scale features by using a two-layer four-way recurrent neural network, and introducing an attention mechanism to integrate local and global feature information of the image to obtain spatial direction sensing features; by introducing an attention coordination mechanism and jump connection, shallow details and deep semantic features are fused, and a fused image is reconstructed and generated through convolution operation. According to the method, through parallel multi-scale feature extraction, global spatial information perception and cross-level feature compensation, the performance of the fusion image in the aspects of information fidelity, structural integrity and detail definition is effectively improved, and a fusion result with a prominent target and rich textures can be generated.

The invention provides a construction road crack detection method and system, a readable storage medium and a computer. The method comprises the following steps: constructing a training data set according to each construction road image; constructing a feature extraction model, and introducing a wavelet convolution algorithm into the feature extraction model to generate a feature extraction optimization model; replacing a sampling module of the feature extraction optimization model with a dynamic sampling algorithm, and performing weighted fusion on the feature compensation algorithm and the backbone network features of the feature extraction optimization model to obtain a feature processing model; and constructing a weighted loss function, performing model optimization on the feature processing model by using the weighted loss function and the training data set to generate a crack detection model, and completing crack detection on the to-be-processed construction road image according to the crack detection model. According to the method, the weighted loss function fusing supervised learning and unsupervised learning is constructed, the potential of label-free data is fully mined, and the dependence on labeled data is greatly reduced while the precision is ensured.

This invention belongs to the field of network security technology and discloses a method for predicting industrial control system (ICS) time series based on multi-scale time-frequency joint sensing. It proposes an end-to-end learnable adaptive time-frequency feature extractor to replace the low-pass filtering method relying on fixed parameters in existing technologies. A data-driven dynamic multi-scale partitioning mechanism is proposed, which adaptively adjusts the scale partitioning method according to the actual distribution characteristics and fluctuation patterns of ICS time series data. A scale-adaptive residual projector is designed, and through multi-dimensional spatial projection and residual feature compensation, the problem of multi-scale feature dimension mismatch is solved, establishing a feature cascade enhancement relationship between coarse and fine scales, thus strengthening the effective fusion of multi-scale features and the ability to model long-term time series dependencies. A time-frequency cross-modal collaborative calibration mechanism is proposed, breaking through the limitation of traditional channel attention mechanisms that rely only on a single time dimension. It achieves joint learning of dual-domain information by fusing time-domain statistics and frequency-domain context.

The invention relates to the technical field of advertisement analysis, in particular to a game advertisement putting effect evaluation system and method combined with a knowledge graph, and the method comprises the following steps: S1, capturing a non-task exploration behavior sequence of an open world game, and extracting an exploration behavior feature set comprising a scene retention hotspot, environment interaction frequency and path deviation degree; s2, injecting the exploration behavior feature set into a pre-constructed advertisement knowledge point graph to generate an enhanced knowledge graph carrying an exploration weight; and S3, generating an exploration feature compensation strategy based on the enhanced knowledge graph, and outputting an effect evaluation report fused with the implicit interest mark. According to the method, the reaching rate, the conversion rate and the rejection probability of the advertisement content to players of different exploration behavior types are quantified, the behavior interpretation of an evaluation result and the adjustability of an advertisement strategy are improved, and a behavior-putting-feedback three-dimensional integrated evaluation system is helped to be realized.

The invention discloses an image defogging method based on feature aggregation and prior feature compensation and a related device, and the method comprises the steps: collecting real scene foggy image data, constructing pseudo clear image data, and constructing non-paired real scene foggy image data through employing a data augmentation method based on a diffusion model; the method comprises the following steps: extracting features of foggy image data of a real scene by adopting a convolutional neural network (CNN), and carrying out preliminary defogging processing on the extracted features by adopting a physical-driven feature aggregation method; multiple groups of image features are obtained by using multiple image prior processing modes, and feature compensation is performed on the preliminary defogged image data; and carrying out image defogging model training by using a fusion splicing semi-supervised learning method by using the defogging image data after feature compensation, the pseudo clear image data and the non-paired real scene foggy image data, and obtaining a defogging image through the trained image defogging model. According to the invention, the defogging processing effect and interpretability of a complex real scene foggy image can be improved.

This application provides an image detection method, a training method for a detection model, and an apparatus that can be applied to the field of image processing technology. The method includes: performing multi-scale feature extraction on a first image and a second image respectively to obtain multiple first initial features of the first image and multiple second initial features of the second image, wherein the first image and the second image are obtained by acquiring images of a target region at different times using a remote sensing device; for any two adjacent scales, fusing the loss information between the first initial features and the loss information between the second initial features at each scale to obtain loss fusion features; based on the loss fusion features, using an attention mechanism to perform feature compensation on the difference information between the first initial features and the second initial features to obtain target compensation features; and detecting the target compensation features to obtain a detection result.

This application discloses a neural signal decoding method and system based on bias prediction and feature compensation. The method includes: acquiring a visual image and a neural signal; extracting reference visual features of the visual image based on a visual encoder, and extracting initial neural signal features of the neural signal based on a neural signal encoder to be trained; generating bias information based on the initial neural signal features using a bias prediction module, wherein the bias information is used to characterize the difference between the initial neural signal features and an ideal feature that can be aligned with the reference visual features; compensating the initial neural signal features using the bias information to generate compensated neural signal features; optimizing the neural signal encoder and the bias prediction module; acquiring a target neural signal, and decoding the target neural signal based on the optimized neural signal encoder and the bias prediction module. This application can achieve a high degree of alignment between the decoded neural signal and the visual signal.

This invention discloses a convolutional neural network pruning method and apparatus based on feature similarity and feature compensation. The method includes: adjusting the size of the input images in the dataset to a fixed size, standardizing the pixel values ​​of the images, and increasing the training data using image enhancement techniques; initializing the network structure and setting model parameters, and training the model using the training data; for the trained model, obtaining the similarity between convolutional kernels, performing cluster analysis based on the similarity, grouping each layer of convolutional kernels into similar groups, selecting the convolutional kernels to be retained in each similar group, and generating a new network structure; copying the parameters of the retained convolutional kernels into the new network structure, and compensating the weight parameters of the pruned convolutional kernels in each similar group into the retained convolutional kernels through parameter superposition; performing model accuracy recovery training using the original dataset, and saving the model parameters and network structure. This pruning method can maintain model accuracy.

The invention discloses a semi-supervised video frame segmentation method and device, a medium and a product, and relates to the technical field of image processing, and the semi-supervised video frame segmentation method comprises the steps: obtaining a video of a current time period; performing pixel-level labeling on the video frame at the first moment in the video of the current time period to obtain a real pixel mask of the video frame at the first moment; using a pixel mask prediction model, based on the real pixel mask of the video frame at the first moment and the video frame at the first moment, starting from the second moment of the current time period, determining predicted pixel masks of the video frames at all moments of the current time period in sequence, and completing segmentation of the video frames at all moments of the current time period; the pixel mask prediction model is obtained by training a video object segmentation network, and the video object segmentation network comprises a visual backbone network, a fine-grained memory reading module, a global feature compensation module and a linear fusion module. According to the invention, the segmentation efficiency and precision of the video frame are improved.

The invention belongs to the technical field of medical image sequence registration, and provides a self-adaptive medical image sequence registration method and system based on space-time collaborative coding, and the method comprises the steps: obtaining 4D image sequence data, defining each element in the 4D image sequence data as a 3D image corresponding to a corresponding moment, registering the 4D image sequence data by using a pre-trained deep neural network model to obtain a registration result; the deep neural network model comprises a feed-forward encoder and a reconstruction decoder which both adopt a multi-stage hierarchical design, and the feed-forward encoder fuses time sequence dependence and space context information in an image sequence; the reconstruction decoder performs step-by-step up-sampling and accurate reconstruction on the features output by the encoder, and constructs a feature compensation path through jump connection between layers so as to fuse shallow spatial information and deep semantic features. According to the invention, the accuracy of registration is improved.

The application discloses a kind of multi-channel new media data fusion method and system, it is related to data processing technical field, obtains the multi-channel new media data to be fused, carries out feature compensation and uniform subspace projection alignment to multi-channel new media data, exports standardization feature representation and the compensation confidence bound with standardization feature representation, carries out feature inhibition and screening to standardization feature representation, instantiates core feature node, constructs the cross-channel relationship edge connecting each core feature node, generates multi-element complex relationship graph, converts natural language query instruction into retrieval intent vector and comprehensive modal tendency degree, generates target graph node feature response value, retrieves target feature node with target graph node feature response value and retrieval intent vector, and combines dynamic fusion weight to calculate matching degree, recall target feature node, supplement the cross-channel context node of recall existing dependency relationship, carry out event aggregation to target feature node and cross-channel context node, output fusion retrieval result cluster.

The invention provides a differential interference signal generation method and system based on target identification, relates to the technical field of signal processing, and aims to provide an efficient and accurate differential interference signal for a target identification scene. Firstly, a reference signal set in a non-interference state of a target recognition scene and a target feature set for recognition of a target object are obtained, and a time sequence corresponding relation is established; performing a differential dimension sensitivity test based on the target feature set, and determining a differential dimension set and an interference adjustment rule; distributing basic parameter weights according to rules to generate an initial differential interference signal set; interference parameters are optimized through a multi-round iteration adjustment mechanism; and finally, performing interference signal feature compensation processing, generating a final differential interference signal set and outputting the final differential interference signal set to the target interference equipment, thereby effectively improving the interference effect and adaptability in the target identification scene.

This invention discloses a method for registering optical and SAR images based on high-level ground feature compensation, comprising: Step 1, acquiring SAR image data and extracting potential dual-echo information from the SAR image to calculate the high-level ground feature compensation factor; Step 2, acquiring optical image data, resampling the optical image data, and calculating the high-level ground feature compensation factor using the morphological building index; Step 3, processing the SAR image data using the high-level ground feature compensation factor obtained in Step 1, and processing the optical image data using the high-level ground feature compensation factor obtained in Step 2, and extracting a threshold-adaptive feature point set; Step 4, performing feature point matching operation on the threshold-adaptive feature point set. This invention can effectively reduce the registration error caused by high-level ground features in local areas, optimize the registration effect of optical image data and SAR image data, and improve the accuracy of remote sensing images.

The invention provides an ultra-high-definition film defect detection method based on improved YOLOv8, and relates to the technical field of detection, and the method comprises the steps: obtaining an ultra-high-definition image of a to-be-detected film, adaptively adjusting the partitioning size and the overlapping rate based on a defect size distribution statistical result, and decomposing the ultra-high-definition image into a plurality of sub-image blocks with spatial redundancy; performing feature extraction on each sub-image block by using a feature extraction network; according to the boundary feature vectors of the adjacent sub-image blocks in the overlapping area, weighted interpolation is executed based on the spatial gradient and the semantic similarity, and feature maps of all the sub-image blocks subjected to feature compensation are generated; inputting the feature map into a defect detection network, wherein the network comprises an anchor frame configuration module designed for an extreme length-width ratio target, a shallow feature enhancement path and a cross-scale feature compensation fusion module; and determining the position and category of the defect in the ultra-high-definition image. The method can effectively improve the accuracy and efficiency of ultra-high-definition film defect detection, and is particularly suitable for detecting extreme length-width ratio and small-size defects.

Target audio data and frequency spectrum information of the target audio data is acquired. The target audio data includes an audio missing segment and context audio segments of the audio missing segment. The frequency spectrum information includes frequency spectrum features of the context audio segments. Feature compensation is performed on the frequency spectrum information of the target audio data based on the frequency spectrum features of the context audio segments to obtain compensated frequency spectrum information corresponding to the target audio data. The compensated frequency spectrum information indicates upsampled frequency spectrum information of the target audio data. Audio prediction is performed based on the compensated frequency spectrum information to obtain predicted audio data. The audio missing segment in the target audio data is compensated by replacing the audio missing segment with a predicted segment in the predicted audio data to obtain compensated audio data of the target audio data.

This invention provides a feature compensation and passive positioning method and system. The method includes: performing signal feature processing operations; extracting WiFi signal features by analyzing channel state information to obtain a PLCR matrix; processing DFS data based on the reflection path change rate (PLCR); deriving an observation-based matrix P1 and a reliability-based matrix R from the PLCR matrix; assigning weights to each type of prediction for combined prediction operations; calculating each type of prediction; combining the weights to obtain the final PLCR prediction; processing to obtain applicable PLCR prediction values ​​and user trajectories; determining the user's speed; and predicting the wireless signal features at the next moment to obtain the complete trajectory. This invention solves the technical problem of low accuracy in WiFi passive positioning operations under non-continuous communication scenarios due to insufficient utilization of the correlation between WiFi links and the loss of wireless signal features in real-world application scenarios.

The invention discloses an angle gather expansion method and device based on AVO feature compensation, electronic equipment and a medium. The method comprises the following steps: acquiring seismic data and speed data, determining incident angles of rays, and further acquiring partial stacks of different incident angles; calculating the reflection coefficient of the middle and long gathers; extracting seismic wavelets of each incident angle; and fitting the reflection coefficients of the seismic wavelets to the mid-long gathers to obtain mid-long gather information so as to realize gather expansion. According to the method, small-angle gather information can be expanded, the signal-to-noise ratio of seismic data is improved, and the pre-stack inversion precision is higher.

This invention relates to the field of digital identification technology for power equipment, and discloses a noise-resistant temperature-measuring laser micro-dot code decoding method and system for curved copper and aluminum fittings. The method includes: constructing an observation coordinate system and performing polarization analysis to obtain a set of polarization features; using a wave-particle duality adjustment factor to perform energy decoupling to obtain a wave-like energy distribution field; applying a phase angle distribution set to perform directional spatial filtering to generate a texture feature map and extracting quality assessment parameters; using an AI image-locking model to lock the geometric feature set based on the quality assessment parameters, and using an AI polymer image-locking model to refine the segmentation to obtain a set of candidate code points; reconstructing a micro-dot logic array based on the local radius of curvature; constructing a topological error-correction map and performing feature compensation to obtain a full-dimensional array, and outputting a logic verification pass identifier. This invention solves the problems of high reflectivity semantic aliasing and manifold distortion, and achieves reliable reading and closed-loop identity verification of micro-dot codes in harsh industrial environments.