6404 results about "Layers" patented technology

A system and method for adaptive real-time multi-modal compression with dynamic resource allocation provides intelligent compression optimization based on continuously monitored device conditions. The system monitors battery level, CPU utilization, and memory availability while classifying incoming multi-modal data streams comprising image, audio, text, and sensor data to determine processing priorities. Multi-objective optimization balances compression efficiency, reconstruction quality, and energy consumption using evolutionary algorithms that generate optimal parameters for an adaptive variational autoencoder. The autoencoder features dynamically selectable processing complexity, adjustable latent space dimensionality, and modality-specific processing layers. The system automatically switches between operational modes including emergency mode triggered by resource constraints, which applies maximum compression settings and intelligent data triage. Continuous learning adapts compression parameters based on observed performance outcomes, improving future optimization decisions. The system enables homomorphic operations on compressed data and provides enhanced compression performance under varying resource constraints across diverse edge computing applications.

The invention relates to the technical field of defect detection, in particular to a special equipment defect automatic identification method and system, and the method comprises the following steps: marking a continuous path based on an image gray scale gradient and adjacent differences, identifying the pixel connection intensity to obtain a contour image layer, extracting continuous pixels, analyzing gray scale and gradient features, and expanding a texture direction to generate a defect image block. And marking and connecting the small regions to obtain a closed layer, analyzing texture and edge differences, matching classification tags, and clustering and coding to generate a defect identification tag set. According to the method, boundary structure recognition is enhanced through gray gradient and direction continuity analysis, a texture aggregation area is expanded in combination with gray consistency and edge direction stability, brightness abrupt change points are removed, contour extraction precision is improved, micro crack continuity is recovered, and pseudo defects are eliminated; and multi-dimensional image attributes are fused to identify key region feature differences, so that the classification precision and the spatial mapping consistency are improved, and efficient and accurate defect identification and stable classification are realized.

Image series transformation for optimal compressibility is performed with neural upsampling and error resilience. A novel correlation network composed of convolutional layers for feature extraction that extract multi-dimensional features from the image and a channel-wise transformer with attention to capture complex inter-channel dependencies. An angle optimizer enhances compressibility of an image and an error resilience subsystem improves robustness against transmission errors and data loss. The error resilience subsystem applies forward error correction coding, data partitioning based on importance, and embeds error concealment hints. This hybrid approach addresses both local and global features, mitigates compression artifacts, improves image quality, and enhances data integrity during transmission. The correlation network incorporates error correction and concealment techniques during decoding. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving information for accurate analysis.

Generally described, one or more aspects of the present application relate to prefetching container image layers for use in a cluster of compute instances. For example, the dependencies among the individual layers within the container images stored and / or executed on a cloud provider network may be analyzed. Then, the layers that are likely to be used by a user of the cloud provider network may be identified and prefetched into the caches of the compute instances provided by the cloud provider network, before execution of the container images including such layers is requested by the user. By doing so, the latency between the time a request to execute a set of container images is received and the time the execution of the set of container images is actually initiated can be reduced, thereby providing an improved and more efficient application execution experience to the user.

The invention relates to the field of remote sensing image change detection, and discloses a remote sensing image change detection method based on language guidance. The method comprises the following steps of: extracting a two-time-phase remote sensing image semantic feature map by adopting an Officient SAM as a visual basic model, constructing a multi-layer adapter, and extracting a two-time-phase multi-scale feature map; constructing spatial attention, and extracting visual features; the input text description is processed through a text encoder, and word embedding and overall expression embedding are obtained; a multi-head cross attention method is adopted, and a pre-fusion module is constructed and used for fusion operation of multiple layers of feature maps after word embedding and splicing; and constructing a two-channel decoder structure, performing similarity calculation on the obtained image features and semantic embedding, and outputting a final change detection mask. According to the method, a multi-layer vision-language feature cross layer is designed, so that the model fully learns related information of images and corresponding types of texts, and universal detection of multi-category remote sensing image changes can be realized by taking natural language as guidance.

In various examples, multimodal image data may be used to generate a set of top-down tile images, which are applied to a deep neural network generator architecture model to produce lane marking-specific heatmap images corresponding to the set of top-down tile images. The multimodal sensor data may include LIDAR-captured intensity channel data, LIDAR-captured feature height channel data, and optical color image channel data. The set of top-down tile images may be processed by the generator model to automatically detect lane boundaries and navigation boundaries to generate pixel-level heatmap images that may classify lane markings by marking characteristics such as line type and / or color. The generator model may comprise an encoder-decoder architecture, with multiscale feature extraction and / or context extraction functional layers intervening between the encoder model and the decoder model.

The invention relates to an optical film detection method, device and equipment based on image processing. The method comprises the following steps: collecting multiple frames of images of a multilayer optical film under different illumination conditions, and carrying out preprocessing and characteristic value calculation on the multiple frames of images to obtain a characteristic value response matrix; calculating an optimal weight coefficient of each frame of image according to the feature value response matrix, and performing multi-frame image feature fusion to obtain integrated feature representation; performing multi-scale defect feature extraction on the integrated feature representation to obtain a defect candidate region; spectral response characteristics are extracted based on the defect candidate area, matching degree calculation is carried out on the spectral response characteristics and a preset wavelength-film thickness mapping relation matrix, and a multilayer film defect distribution diagram is obtained; and performing autoregression prediction and processing control parameter optimization on the multilayer film defect distribution diagram to obtain a closed-loop control scheme. According to the invention, accurate identification and classification of different film layer defects are realized, and closed-loop control of defect detection results and manufacturing parameter optimization is further realized.

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: examining image layers of a container image and generating, in dependence on the examining, layer dependency relationship data that specifies layer dependency relationships of the container image; storing in a container repository the layer dependency relationship data that specifies layer dependency relationships of the container image; in response to receipt of a download request that specifies a targeted layer of the container image, analyzing relationship data of the layer dependency relationship data; in dependence on the analyzing, identifying a subset of image layers of the container image preceding the targeted layer; and establishing a deployment container image in dependence on the identified subset of image layers.

The invention relates to an illusion relieving method and device for a multi-modal large model, electronic equipment and a medium. The method comprises the following steps: processing input image-text data to obtain a text token and an image token, aligning the text token and the image token to obtain an input sequence of the image-text data, and constructing an image token attention vector of each position in the input sequence; based on the image token attention vector, measuring the image understanding difference between different decoding layers through Jensen-Shannon divergence, so as to determine a target layer with the maximum distance from the image token attention vector of the tail layer according to a measurement result; and converting the hidden state of the target layer into probability distribution through the linear projection layer by using a preset advance exit mechanism so as to predict the probability distribution of the next token. Therefore, the problems that an existing technology for relieving the illusion phenomenon of the multi-modal large language model is too complex and high in cost, and the model performance is affected are solved, and the reliability and accuracy of the method in practical application are improved.

Systems and methods are described for generating, using the first trained machine learning model and based on text input, a single-layer image comprising a plurality of objects; generating a plurality of masks associated with the plurality of objects; determining a plurality of attributes associated with the plurality of objects; generating, using a second trained machine learning model, a plurality of textual descriptions respectively corresponding to the plurality of objects; inputting the plurality of textual descriptions, and the plurality of attributes, to the first trained machine learning model; generating, using the first trained machine learning model, a plurality of images respectively corresponding to the plurality of textual descriptions; and generating the multi-layer image by combining the plurality of images and by using the plurality of masks, wherein the plurality of images respectively correspond to a plurality of layers of the multi-layer image.

Implementations relate to generation of segmentation masks for images in a zero-shot, unsupervised manner. Implementations also relate to generation of labels for the segmentation layers of the segmentation mask. Implementations use self-attention maps from a pass of the image through a generative image model to determine the segmentation mask and may use cross-attention maps generated when a prompt describing the image is provided with the image to the generative image model. Implementations aggregate maps from different resolutions to determine the mask and labels. The disclosed techniques enable accurate segmentation for any image without apriori training, facilitating applications in image processing, computer vision, extended reality applications, and robotics.

A method based on a multi-task learning model comprises the following steps: acquiring and processing histopathological image data of gastritis through a data preparation and preprocessing step; feature extraction is performed by using a self-supervised learning pre-trained model, and image blocks are coded into high-dimensional feature vectors; and constructing a multi-task learning model, learning feature representation through a full connection layer module and an attention layer module, and outputting a classification result of each task. And carrying out model training and optimization by using an optimizer, adding multitask loss through a loss function, and dynamically adjusting the model performance. The trained model can automatically detect and grade gastritis, atrophy, acute activity, intestinal metaplasia and other pathological indexes, outputs a standardized evaluation result, and assists in pathological diagnosis. According to the method, a multi-task deep learning framework based on self-supervised learning pre-training is constructed, a traditional single-task modeling mode is broken through, deep learning framework design is driven through pathological index association, and accuracy and clinical practicability of non-neoplastic disease assessment of the stomach are remarkably improved.

An image-guided diffusion network has two Convolution Neural Networks (CNNs). A RGB image and an IR image are concatenated with a Gaussian noise image and input to a denoising neural network that merges information from the RGB and IR images as noise is removed over many iterations. Then an enhancement neural network up-samples for Super Resolution (SR) and convolutes to generate a condition vector that controls Global Feature Modulation (GFM) at three convolution layers to generate a SRGFM enhanced fusion image. Timesteps are embedded using adaptive group normalization blocks within Adaptive Bottleneck Residual (ABR) blocks in the denoising network, which is a UNet having many levels of ABRs, and in the enhancement network before feature modulation. Global image features are detected by triple convoluting the image input to the enhancement network to generate the condition vector that controls feature modulation blocks at three layers of convolution.

The present invention relates to the technical field of deep learning and computer vision. Disclosed is an unmanned aerial vehicle image-based small object detection method for target areas. The present invention crops images of obvious small objects in certain target areas, and annotates the small objects of different categories to form a raw training and testing dataset, so as to ensure the accuracy of data required in the early stage of the algorithm and further ensure the scientificity of the algorithm; uses the computing capability of an improved YOLOv7 detection model to collect image features of different degrees in the dataset, the improved YOLOv7 detection model using YOLOv7 as a basic model and adding to a neck network an MS-CET module, which is constituted by an improved self-attention mechanism and convolution module SPPCSP, and a BHC-FB module, which is constituted by bidirectional mixed convolution modules NConv and RPConv connected in parallel; and finally fuses different feature layers as a final judgment basis of an unmanned aerial vehicle for small object detection in the target areas, to further check the accuracy of the algorithm and criteria for dataset selection, thereby improving recognition accuracy.

The invention discloses an intelligent planning method for space monitoring of an unmanned aerial vehicle. The method comprises the steps that intelligent path allocation is realized by constructing a task demand priority matrix; the method comprises the following steps: firstly, collecting geographical, climate and environmental parameters of a monitoring area, quantifying regional complexity and color features of a monitoring target by combining high-resolution image data with a neural network model, and generating a priority matrix according to task importance, change frequency and risk level; a Dijkstra algorithm is adopted to plan an initial flight path giving consideration to priority and flight limitation, a path complexity index is calculated, and the index comprehensively considers a target priority weight, a task detouring coefficient and a path relaxation degree; and finally, dividing a monitoring area into height layers according to a path complexity index threshold value, performing height layer adjustment on the initial path, and generating a dynamic flight path containing height layer switching, thereby realizing efficient resource allocation and accurate risk prevention and control in a complex monitoring scene.

The invention discloses a coal rock fracture intelligent extraction method based on improved U-Net. The method comprises the following steps: S1, constructing a coal rock fracture CT image data set; s2, constructing an improved U-Net segmentation model, specifically comprising the following steps: S2.1, taking VGG16 as a backbone network, and introducing a depth separable convolution module; s2.2, a PPA attention module is added after each layer of depth separable convolution of the decoder, the PPA attention module is introduced after each up-sampling stage of the decoder, and the output of the PPA attention module is subjected to batch normalization and Dropout layer processing; s2.3, defining a composite loss function; s3, training and optimizing a segmentation model, wherein the specific steps comprise: S3.1, setting hyper-parameters; and S3.2, training the model by using the training set, adjusting hyper-parameters by using the verification set, and evaluating the performance by using the test set, wherein the evaluation indexes comprise MIoU, MAcc and FWIoU. According to the method, the problems of difficult identification of small fractures, large model calculation amount, poor multi-scale information fusion and class imbalance in the coal rock fracture image can be solved, and the robustness, segmentation precision and practicability of the model are improved.

The invention discloses an infrared small target detection method fusing local prior and a multi-scale global background, and the method comprises the steps: firstly obtaining image data containing an infrared image and a mask label corresponding to the infrared image, and carrying out the preprocessing; secondly, a target detection model of an encoder-decoder architecture is constructed, an encoder comprises a local detail prior mining branch and a multi-scale global background perception branch which are parallel, step-by-step feature extraction is performed on the preprocessed image data, and a decoder comprises a progressive feature fusion decoding branch; and inputting the features of each level of the encoder double branches into decoder branches for decoding step by step to obtain a detection result. And finally, a weighted depth supervision mechanism is introduced in training, auxiliary prediction output is set in a plurality of decoding layers, and weighting loss is calculated. According to the method, the problems of insufficient local detail modeling, insufficient multi-scale global background perception of Mamba, difficulty in global and local feature fusion and the like in the existing method are solved, and the detection precision of the infrared small target is improved.

The invention relates to the technical field of image processing, and discloses a printed matter detection method and device. The method comprises the following steps: acquiring multispectral image data of a printed matter to be detected in different spectral bands; performing spectral feature extraction and multi-level fusion on the multispectral image data to obtain a comprehensive spectral feature map; acquiring sample spectral feature maps of a plurality of sample printed matters to perform frequent feature mode extraction, generating a spectral fingerprint database, and performing region division and matching degree search to obtain a reference spectral fingerprint map; carrying out multi-scale decomposition on the comprehensive spectrum feature map and the reference spectrum fingerprint map to obtain a plurality of scale layers, and carrying out local spectrum similarity calculation and adaptive threshold segmentation to obtain a binary mask map of a defect region; performing spectral feature clustering analysis to obtain defect categories; and performing defect root cause analysis and process adjustment on the printing process parameters to generate a process adjustment scheme, thereby improving the printing quality detection accuracy of the printed matter.

The invention relates to the technical field of image annotation, in particular to a medical image auxiliary annotation method and system based on image processing, and the method comprises the following steps: obtaining medical image data, and carrying out the edge enhancement processing of the image data; performing preliminary labeling on the central necrosis layer, the edge active layer and the peripheral normal tissue layer to generate preliminary labeling areas of different focus levels; extracting textural features, morphological features and density features of each level, and converting the textural features, morphological features and density features into feature vectors for storage; forming a multi-level lesion association model; adjusting the boundary positions of the layers, and ensuring that the relative position relation between the layers is reasonable; dynamically updating the level annotation according to the change characteristics; and outputting a labeling layer containing the multi-level focus characteristics of the central necrosis area and the edge active area. Compared with an existing single-level or coarse-grained marking method, the method has the advantages that the hierarchical expression effect of the focus area is improved, and the detail level of the focus in the complex form is clearly presented.

The invention discloses a multi-modal semi-supervised medical image segmentation method based on SAM adaptive fine tuning, and the method comprises the steps: obtaining an original multi-modal image, adjusting the original multi-modal image to a preset size, and carrying out the image preprocessing, thereby obtaining a multi-modal image pair; simultaneously inputting the multi-modal image pair into a student branch model and a teacher branch model which are completely identical in structure, wherein each of the student branch model and the teacher branch model comprises a fusion module, an SAM encoder and a layered decoder; the multi-modal image pair passes through a fusion module formed by a convolutional network to obtain fusion features, the fusion features are input to the SAM encoder, and output features of different Transform layers are obtained; and inputting the plurality of output features into a hierarchical decoder, performing similarity calculation by the hierarchical decoder according to the plurality of output features to obtain prototype classification, and obtaining a prediction mask through a linear layer. According to the method, the multi-level features can be well utilized to realize fine-grained segmentation, and a good segmentation effect is realized.

A system and method for polarization detection of a target in a strong background are provided. The system includes: an image signal acquisition module configured for image information acquisition and signal conversion of a plurality of channels; a YoLoV3 neutral network-based feature extraction module configured to increase a number of network layers, obtain a fused feature map combined with intensity information and polarization information, and extract a feature difference between an intensity modality and a polarized light modality; a Darknet53 neutral network-based feature extraction module configured to extract a feature value of a high dynamic range image; a residual network-based feature fusion module configured to learn weights of different modalities, obtain a fused feature map of intensity modality information and polarization modality information, and select and optimize the fused feature map by attention mechanism processing; and an image printing module configured to filter background information.

Methods and systems for container management include scanning layers of a first container image of a set of container images to generate scan metadata for the layers. Relationship information is generated that identifies relationships between a first set of layers of the first container image and layers of additional container images of the plurality of container images. The additional container images are scanned, omitting any layers in the additional container images that match a layer of the first set of layers based on the relationship information.

The invention provides a space-time decoupling feature fusion method based on space-time bidirectional Vision Mama, and the method comprises the steps: S1, extracting multi-scale space detail features from an input time sequence image through employing a plurality of cascaded 2D CNN blocks, and obtaining a feature graph; s2, a bidirectional space-time Mama structure is applied to the feature maps of the low and middle layers so as to compensate for loss of time information in the 2D CNN block; wherein for the feature map obtained in the step S1, time sequence features are extracted by applying time bidirectional Vision Mama, and then space features are extracted by using space bidirectional Vision Mama. The invention further provides a space-time decoupling feature fusion system based on the space-time bidirectional Vision Mama. According to the method, efficient and accurate feature extraction and information fusion are performed on a special time sequence multi-band multi-channel remote sensing image, and efficient and high-precision semantic segmentation of crops on a large-area scale remote sensing image is realized.

The invention provides a steel surface defect detection method and device, and belongs to the technical field of steel defect detection.The steel surface defect detection method comprises the steps that a defect detection network based on a YOLO architecture is constructed, and the defect detection network comprises a lightweight feature extraction network, a self-adaptive multi-scale feature fusion network and a head network; the lightweight feature extraction network comprises four layers of architectures, and each layer of architecture comprises a first convolutional layer and a space expansion feature module; the feature space expansion module comprises a second convolutional layer and an element multiplication operator module; the adaptive multi-scale feature fusion network comprises an adaptive fusion module and a feature space expansion module; training the constructed defect detection network based on the historical steel defect image, and performing channel pruning on the trained defect detection network by using LAMP (Loop-Mediated Isothermal Amplification); and acquiring a to-be-identified steel image, and inputting the to-be-identified steel image into the pruned defect detection network for defect detection. According to the method, the defect detection precision of the network can be improved while the network complexity is reduced.

The invention provides a multi-modal large model non-training reasoning acceleration method and device based on visual token pruning, relates to the technical field of artificial intelligence, and aims to accelerate the reasoning speed of a multi-modal large model. The method comprises the following steps: inputting a target image into a visual encoder for multilayer attention interaction to obtain a visual token sequence consisting of a plurality of visual tokens and attention score distribution of multilayer class tokens to the visual tokens; according to the attention score distribution of the multi-layer class tokens to the visual tokens, final attention scores of the class tokens to the visual tokens are determined, and the final attention scores represent the importance degrees of the visual tokens; according to the final attention score of the class token to each visual token, selecting a plurality of target visual tokens with high importance from the visual token sequence; and inputting the plurality of target visual tokens and the text prompts into a language model for reasoning to obtain a reasoning result.

The invention relates to a backside illuminated image sensor preparation method and a backside illuminated image sensor, and relates to the technical field of integrated circuits, the backside illuminated image sensor preparation method comprises the following steps: providing a substrate comprising a first top surface, the first top surface comprising an isolation layer and an initial semiconductor layer stacked in sequence along a first direction deviating from the first top surface; forming a plurality of isolation lamination layers which are arranged at intervals along a second direction on the top surface of the initial semiconductor layer, and sequentially forming a first semiconductor layer and a second semiconductor layer which are laminated and contain different pentavalent elements between adjacent isolation lamination layers; diffusing a first pentavalent element of the first semiconductor layer to the initial semiconductor layer to obtain a first target semiconductor layer; diffusing a second pentavalent element of the second semiconductor layer to the first semiconductor layer to obtain a second target semiconductor layer; and a dielectric layer covering the top surface of the second semiconductor layer and the exposed outer surface of the isolation lamination layer is formed, so that the electron concentration of the photosensitive area is increased, and the photosensitive performance of the BSI image sensor is improved.

The present invention sets forth techniques for performing style transfer from multiple supplied style images to a supplied content image to generate novel images that include style elements from the multiple supplied style images and content elements from the supplied content image. The techniques include guiding one or more self-attention and cross-attention layers included in a machine learning model based on the multiple supplied style images, such that content elements and style elements included in the style images are not entangled when generating the novel images. The techniques also distill a small subset of representative attention map values from multiple style images, improving performance while reducing computational costs compared to processing all attention map values from the multiple style images.

An AI-based method for visual inspection of parts manufactured on a shop floor includes acquiring a set of real images of nominal parts manufactured on the shop floor to create training datasets. A self-supervised pre-trainer module is used to pre-train a loss computation neural network in a self-supervised learning process using a first dataset on pretexts defined by real-world conditions pertaining to the shop floor. The first dataset is labeled by automatically extracting pretext-related information from image metadata. A main anomaly trainer module is used to train a main anomaly detection neural network to reconstruct a nominal part image from an input manufactured part image in an unsupervised learning process using a second dataset. The main anomaly training measures a perceptual loss between an input image and a reconstructed image by measuring a difference between feature representations thereof at one or more layers of the pre-trained loss computation neural network.

The present application provides a method for detecting a defect on the surface of a copper clad laminate on the basis of multi-scale gridding, said method comprising: S1, acquiring and capturing an image of a copper clad laminate by means of a line scan camera; S2, segmenting a copper clad region and a non-copper clad region, and rotating the copper clad region to the front; S3, dividing the copper clad region in the image according to set grid parameters, and performing a pyramid operation on a divided grid graph; S4, calculating the mean of each layer; S5, fusing the means of all of the layers by using a mean degradation coefficient, and obtaining a final background mean; and S6, by using a background-foreground difference, searching for a final defect and classifying same. According to the present application, the amount of computation is reduced, and local information of the background is retained, thus increasing detection speed, and also ensuring the stability of precision. A good detection effect can be obtained when high-speed detection must be performed on a material.

The invention belongs to the technical field of industrial detection, and discloses a defect detection method and system based on honeycomb catalyst stacking. Omnibearing image data of honeycomb catalyst stacking are obtained through a multi-angle polarization imaging technology, pixel-level polarization degree parameters are calculated to construct a global polarization feature map, and accurate distinguishing between an intrinsic porous structure and suspected defects is achieved. A blind area identification and virtual view angle reconstruction mechanism is introduced, so that the problem of a stacked edge detection blind area is solved; and a layered reflectivity compensation function is adopted, so that the optical interference of an interlayer overlapping region is eliminated. Texture features are extracted through multi-scale morphological filtering, multi-dimensional feature fusion is carried out in combination with polarization features, edge continuity indexes and correction reflection intensity, and a high-precision defect discrimination model is established. And for a low-confidence region, dynamically adjusting detection parameters and performing iterative optimization to form an adaptive detection closed loop. According to the invention, the detection precision and reliability are improved, and the defect position, type and severity can be accurately output.