57 results about "Image texture" patented technology

This invention relates to a method for loading instrument images based on Kanzi, comprising: acquiring and classifying image information to be loaded into startup loading, preloading, and reference loading; performing compatibility merging processing on startup loading images; integrating preloaded images into a single data file and storing it in the instrument program directory; placing reference loading images in a designated directory; converting the processed images into textures using the Kanzi interface tool; creating a blank image texture in Kanzi and pointing it to the directory reference image; after the instrument starts, loading the texture in the HMI resource kzb file to complete the loading of texture-related images; after the first frame of the instrument HMI is displayed, starting the data file loading to complete the loading of data file-related data; the instrument HMI updates the image texture resource path in real time via API to load the corresponding reference images; the advantages of this invention are: after image merging processing, startup loading is changed from loading multiple files to loading a single file, avoiding multiple loading caused by generating multiple cache files and improving startup efficiency.

This invention discloses a non-destructive method for sex detection of chicken embryos in the early incubation period based on RF-DS image information fusion. Machine vision and a spectrometer are used to collect information on horizontally placed embryos at day 4 of incubation. Based on image and spectral preprocessing, image texture features and spectral features are extracted. Then, basic probability assignment functions (BPAs) are constructed using the RF classification results of two single-feature types as independent evidence. Decision-level fusion is performed using D-S evidence theory, and the final identification result is given based on the classification decision threshold. Experimental results show that the highest accuracy of the image and spectral single-feature RF models reaches 78.00% and 82.67%, respectively, while the multi-feature decision fusion identification method achieves an accuracy of 88.00%, with sex identification rates of 90.00% and 86.25%, respectively. The time for identifying a single egg is 2.843 seconds. These results demonstrate that this spectral-image information fusion method can improve the accuracy of sex identification in early incubation embryos.

The application relates to the technical field of graphite preparation, in particular to a special graphite production process improvement method for improving pitch coating uniformity. The method comprises the following steps: high quinoline pitch is prepared by reforming pitch and quinoline insoluble powder melting; the high quinoline pitch is subjected to vacuum distillation, then is screened through different particle size sieves, and then is put into a mold for pressure to obtain a green body; after the green body is baked, the pitch is carbonized to obtain graphite; when the high quinoline pitch is prepared, an ultrasonic image of a melting furnace is obtained, and multi-scale texture distribution in the ultrasonic image is analyzed; and then the temperature of the melting furnace is adjusted based on comparison of image texture feature changes and threshold values in different states. The application solves the problems of pitch melting deficiency or excessive heating caused by pitch melting state being unknown, and improves the pitch coating uniformity of the special graphite.

This invention discloses a method for softening water surface edges and a water system modeling method, belonging to the field of water system modeling technology. The method includes creating an edge-softening texture, with the following steps: calculating the texture size of the water surface; creating a Canvas; drawing the basic water surface outline; and layer-by-layer outlining: S41 Outlining: outlining the water surface outline with black; S42 Color Blending: after each layer of outlining, the black outlining of that layer is blended with the current background color, and the RGBA components of the blended color are calculated; the blended color is then used as the new background color for that area; S43 Repeating steps S141 and S42 until the color blending of the edgeBlur-1 layer is completed; converting the Canvas content into an image texture to generate the edge-softening texture. The advantage of this invention is that by creating an edge gradient texture, a natural transition between the water surface and land is achieved, effectively improving the integration of the water surface with other scene elements, significantly enhancing the realism and immersion of the water surface rendering, and providing a more comfortable and professional user experience.

This invention relates to the field of video encoding and decoding technology, specifically to an adaptive bitrate control method for multi-person live streaming. It solves the technical problem that existing technologies cannot dynamically adjust bitrate allocation when total bandwidth is limited, resulting in a poor overall visual experience in multi-person live streaming. The method includes: determining the resource contention weight of each input stream based on the source-end encoding compression rate, audio energy value, and spatial proportion; correcting the image texture complexity based on the resource contention weight to determine the target encoding complexity of each input stream; determining the original texture complexity of each input stream based on the image texture complexity and spatial proportion; and determining the offset value of the quantization parameters used to adjust the encoding region of each input stream based on the difference between the target encoding complexity and the original texture complexity of each input stream. This invention is applicable to video bitrate control scenarios.

The application belongs to the technical field of medical image processing, and particularly relates to a human limb skin disease area evaluation method, device and system. The method comprises the following steps: collecting multi-view images of a target limb, adjacent view angles of the multi-view images containing overlapping areas; generating a three-dimensional point cloud of the target limb based on the multi-view images; constructing a cylindrical model with a radius changing along a limb axis based on the three-dimensional point cloud; projecting the multi-view images to the cylindrical model, and selecting pixels projected to the same position of the model based on an evaluation function, so that the model surface is attached with image texture; and unfolding the cylindrical model with the texture into a two-dimensional plane image for evaluating the skin disease area. The application realizes high-precision and high-fidelity lesion area evaluation without expensive three-dimensional scanning equipment.

This invention discloses a two-stage low-light image enhancement method and apparatus based on the HVI color space. The method includes: converting a low-light RGB image to the HVI color space to obtain a luminance feature map and a color feature map; performing global denoising on the luminance feature map and global denoising and global color correction on the color feature map through feature extraction and bidirectional interaction between features; performing local detail enhancement on the initially enhanced luminance feature map and local color correction on the initially enhanced color feature map through bidirectional interaction between features extraction and local features, obtaining fully enhanced luminance and color feature maps; and reconstructing the fully enhanced luminance and color feature maps into a low-light enhanced RGB image. This method achieves a dynamic balance between noise suppression and detail preservation, enhancing image texture, edges, and other minute structures while accurately repairing local color shifts and color overflow issues.

The application provides an infrastructure surface crack feature enhancement method, medium and system, and belongs to the technical field of crack detection.The application obtains a corrected three-dimensional depth image by starting a line structured light sensing device and an inertial navigation device to scan an infrastructure surface, synchronously triggers a high-speed camera to collect a corresponding two-dimensional gray image by using an incremental encoder, establishes a stereo calibration model, and combines a sub-pixel level phase correlation algorithm to realize pixel level accurate alignment of the two-dimensional gray image and the three-dimensional depth image, extracts crack contour features and crack center lines, superimposes and fuses the crack contour features and the crack center lines to the three-dimensional depth image to generate a crack feature enhancement image, and inputs a multi-scale crack recognition model to recognize and classify, so that the technical problem that two-dimensional image texture features and three-dimensional depth data are difficult to realize pixel level accurate fusion, resulting in poor infrastructure surface crack feature enhancement effect, is solved.

The application provides a kind of rock-soil crack intelligent identification method based on unmanned aerial vehicle multi-source remote sensing data, and relates to the technical field of geotechnical engineering safety monitoring and geological disaster identification.Through the synchronous acquisition of ground surface image and laser point cloud data by unmanned aerial vehicle, the YOLO crack detection network is used for identification.The network integrates terrain texture prior attention module, point cloud constraint fusion layer and adaptive confidence re-estimation module, realizes the deep coupling of image texture and point cloud geometric features.Further, the point cloud is subjected to density clustering segmentation to extract spatial anomaly features, and the image recognition result and point cloud features are registered and fused through the main direction and depth consistency constraint to construct a crack spatial positioning model.Finally, according to the positioning result, the unmanned aerial vehicle is guided to fly close to the ground again to obtain high-precision images of the potential rock-soil crack development area, and the crack boundary is accurately segmented and the morphological parameters are extracted.The application significantly improves the accuracy, robustness and full-process intelligent level of crack identification.

The application discloses a Cauchy noise image restoration method based on a ratio type sparse constraint, and belongs to the technical field of digital image processing. The method uses the non-local similarity of an image, takes a structure group formed by similar blocks as a training object, learns an orthogonal dictionary, performs sparse representation on the structure group, and applies a non-convex constraint on representation coefficients. Firstly, a Cauchy noise image after preprocessing is blocked, a most similar group of image block vectors is extracted in a search window with a reference block as a center after being structured, then the orthogonal dictionary is trained by using the structure group, the correlation in the structure group is enhanced by using joint coding, and a norm is used as a regularization term to perform sparse constraint on a coefficient matrix, and finally, the Cauchy noise is removed and local texture details are restored. The proposed model is solved by using an alternating direction multiplier method, most of the noise can be effectively removed and image texture information can be reserved, and therefore, the method can be used for Cauchy noise image restoration.

This invention discloses a method and system for monitoring highway pavement quality based on deep learning. The method includes raw image acquisition, data optimization processing, deep incomplete model construction, pavement monitoring model construction, and highway pavement quality monitoring. This invention obtains raw data through image acquisition; employs data optimization processing methods such as spatiotemporal alignment, region of interest extraction, sequence frame organization, data augmentation, and dataset partitioning; utilizes a method to generate dense depth maps from 2D image data and sparse depth maps for subsequent processing, acquiring high-density pavement geometric information while ensuring economy, thus providing crucial 3D morphological support for precise identification of pavement conditions; and employs a two-stream network model as the pavement monitoring model, processing image texture and geometric depth information separately and achieving dynamic fusion, while introducing uncertainty information from the depth incomplete stage, thereby improving the comprehensiveness and accuracy of the monitoring results.

The application provides a no-reference point cloud quality evaluation method based on graph convolution, and belongs to the field of three-dimensional point cloud quality evaluation. The scheme comprises data preprocessing, feature extraction, attention enhancement, construction of a single-modal graph structure, cross-modal feature fusion, and finally output of an objective score of point cloud quality. Specifically, for a given point cloud, an orthogonal projection method is used to map it to six standard orthogonal viewing angles, and three types of two-dimensional images are generated for each viewing angle: texture maps, depth maps and placeholder maps; then the three types of images are input into a residual neural network to extract features; then a double attention mechanism is introduced to adaptively weight the extracted features to highlight key features; then a dynamic graph structure is constructed by similarity, and a single-modal global fusion feature is aggregated by graph convolution; then a unified feature integrator is used for cross-modal fusion to fully integrate the mutual information of multiple modalities; and finally, a full connection layer is used to output the final quality score of the point cloud in a multi-view scene.

The invention discloses a papermaking process fiber visual language assisted quality analysis method and system. The method comprises the following steps: collecting a microscopic image of a paper pulp sample in a papermaking process; a semantic segmentation mask is generated through a semantic segmentation model, and structured parameters of fibers are calculated and converted into standardized text description; extracting texture features of the microscopic image and topological structure features of a semantic segmentation mask, converting standardized text description into a high-dimensional parameter embedding vector, and generating a multi-modal query vector through cross attention fusion and semantic alignment; by taking the multi-modal query vector as a retrieval condition, executing mixed retrieval in the papermaking fiber knowledge base, and recalling Top-K related knowledge entries to form a retrieval context; and the standardized text description, the image texture features, the topological structure features of the segmentation mask and the retrieval context are spliced according to a preset cue word template and input into a large language model decoder, and a quality analysis result is generated. According to the invention, the accuracy of fiber anomaly identification can be obviously improved.

The application discloses a shale sedimentary structure automatic division method, and comprises the following steps: S1, FMI static image is cropped and subjected to gray scale processing; S2, a gray scale coexistence matrix is used to calculate FMI gray scale image texture parameters; S3, texture parameter sedimentary structure sensitivity analysis is performed; S4, parameter optimization is performed based on a random forest classification model; and S5, shale sedimentary structure automatic division is performed based on the random forest. The FMI image is fully utilized in the aspect of sedimentary structure division, the restriction of conventional logging on shale sedimentary structure division is broken, a more convenient and effective shale sedimentary structure division method is provided, and important technical support is provided for accurate shale facies division.

This invention discloses a method and system for analyzing mulberry pests and diseases based on drone monitoring. The method includes: collecting multispectral and RGB high-definition images of multiple mulberry planting areas via drones along preset flight paths; preprocessing the image data to generate multi-dimensional spectral indices, analyzing image texture and color features to assess pests and diseases, constructing a fusion feature vector for the planting areas, calculating feature differences using Euclidean distance, and marking associated areas with feature deviations within a preset range; collecting multi-period associated area images, weighting and calculating preset indices and pest and disease indices, assessing pest and disease trends, and screening source areas; setting control priorities based on pest and disease characteristics, and planning drone-based pest and disease control schemes. This invention achieves precise monitoring, source location, and scientific control of mulberry pests and diseases, improving monitoring efficiency and control targeting, adapting to various planting scenarios, and effectively improving the level of intelligent management in mulberry planting.

The application discloses a quality-guided dual-space adaptive fuzzy C-means color image segmentation method and system. The application significantly improves the image segmentation accuracy and robustness under complex natural scenes and light change conditions. The method effectively overcomes the inherent defects of insufficient representation ability of a single color space, realizes fine capture of image texture details and strong inhibition of light interference. Through the establishment of a dynamic feedback adjustment mechanism, the algorithm can realize real-time sensing of the reliability change of different feature spaces and adaptively adjust the fusion strategy, so that the segmentation process is always guided by the actual segmentation quality, thereby obtaining consistent and accurate segmentation boundaries in texture-rich areas and shadow highlight areas. At the same time, by introducing adaptive spatial constraints based on local feature reliability, the smoothness of the uniform area is ensured, the clarity and integrity of the object edge are maximized, and the boundary blur caused by over-smoothing is avoided.

This invention discloses a method for monitoring the safety of tailings dam waterlogged areas based on deep learning, comprising: Step 1, acquiring panoramic images of the waterlogged area and close-up images of the drainage outlet, preprocessing the images, and extracting basic features; Step 2, calculating the initial image texture entropy, and calculating the actual water level change based on the basic features; Step 3, calculating the real-time turbidity based on the basic features and the initial image texture entropy; Step 4, calculating the water flow state quantification value, and calculating the siltation coefficient based on the water flow state quantification value to determine the degree of siltation; Step 5, calculating the comprehensive hazard index based on the basic features, the actual water level change, the real-time turbidity, and the siltation coefficient, determining the risk level, and identifying the hazard type. This invention solves the problems of traditional machine vision monitoring algorithms having poor adaptability to dynamic interference in waterlogged areas, water quality assessment not being correlated with particle settling characteristics, water flow analysis not being coupled with hydrostatic resistance, and hazard judgment relying on a single indicator, which is prone to misjudgment.

This invention discloses a method for decomposing blurred images and videos based on time-specific event-image alignment, comprising: 1. acquiring a motion-blurred image, a synchronized event stream, and a target time; converting the event stream into event voxels and an event time surface; and extracting event motion features and image texture features respectively; 2. constructing a relative time-encoding attention module to aggregate event information based on the relative time relationship between the target time and the event observation time, obtaining motion features corresponding to the target time; simultaneously constructing a time surface dynamic deformation module to generate a time-conditional deformation field for spatiotemporal alignment of blurred image features; 3. fusing motion features and aligned image features using an event-guided gating fusion module, and reconstructing a clear image at the target time using a reconstruction decoder to generate a high frame rate video sequence. This invention effectively alleviates the problems of motion direction ambiguity and spatial misalignment in blurred image and video decomposition, and improves the clarity and temporal consistency of the reconstructed video.

The present application belongs to the technical field of remote sensing image processing, and provides a SAR image denoising method and device based on a logarithmic domain diffusion model. The denoising method comprises: preprocessing: converting an original SAR amplitude image to a logarithmic domain to obtain a starting input image for a diffusion process; forward diffusion: constructing a forward diffusion path based on a non-central Gaussian distribution, simulating a noise injection process, and generating a noisy image sequence; neural network model noise prediction: performing feature extraction and fusion on the noisy image and physical metadata through a pre-constructed neural network model, and outputting a noise residual prediction result; backward sampling reconstruction: iteratively sampling using the noise residual prediction result to reconstruct a denoised SAR image. The denoising method solves the distribution mismatch problem of traditional diffusion models for SAR multiplicative noise, improves the denoising precision, and preserves the image texture and structure information.

A deep geometry-prior-guided Mamba light field angle super-resolution method, belonging to the field of computer vision, is proposed. It estimates a high-precision disparity map using PSV; employs a dual-branch parallel approach to extract image texture features and deep structural features separately, and calculates adaptive weights for cross-modal features using a gated attention mechanism, outputting geometrically enhanced fused features; utilizes a CNN branch to extract detailed residuals of local spatial texture, and uses a Mamba branch to perform global modeling based on the geometrically enhanced features for long-range angular dimension dependence; and dynamically adjusts the ratio of local details to global angular information according to scene content using a channel attention mechanism to achieve an adaptive balance between local spatial fidelity and global angular consistency; and employs an upsampling module to map implicit empty angle features to a dense angular domain, outputting high-quality light field angle super-resolution results. This invention effectively alleviates the blurring problem in image reconstruction and achieves adaptive feature fusion, ensuring the unity of spatial consistency and angular continuity.

The present application relates to the technical field of medical diagnosis system, specifically to a kidney stone composition intelligent identification and individualized prevention and treatment scheme generation system, which comprises a stone type identification module, a composition correlation determination module, an acid-base state division module, a metabolic behavior ordering module and a path scheme construction module.In the present application, the linkage characteristics of the local structure and energy state of the stone surface are extracted through the corresponding relationship of the image texture and the spectral peak position in space, the continuous form of the composition change on the time axis is captured through the period comparison mode of the consistent trend direction, the structural change of the metabolic state in the stage is drawn through the collaborative control of the multiple biochemical trends of lactic acid and bicarbonate in the unified time scale, the mode track of the metabolic behavior is tracked through the difference of the behavior direction change frequency in the period, the path sequence of the metabolic correlation behavior is constructed through the step-by-step promotion of the trend relationship in the period, and the dynamic linkage recognition ability between the data and the stage adaptation ability of the individual intervention path are enhanced.

This application provides a forest monitoring method and system based on multidimensional data analysis, relating to the field of data processing technology. In this application, firstly, current forest images and recent meteorological data for the target forest are acquired; secondly, texture features related to healthy growth are extracted from the current forest image to obtain forest image texture features; then, using a forest health identification model, semantic encoding is guided by the latent semantic information of the forest image texture features and the target meteorological data during the semantic encoding process of the current forest image, forming a forest health coding vector; finally, the forest health identification model is used to semantically decode the forest health coding vector to form target forest health status data. Based on the above, the relatively low reliability of forest health status in existing technologies can be improved.

This invention provides a machine learning-based method and system for TCM constitution identification and analysis, belonging to the field of data analysis technology. The method includes: acquiring health description text data input by the user through a human-computer interaction interface, and extracting semantic feature vectors from the text; collecting the user's tongue image, facial image, and whole-body optical images, extracting the tongue image texture feature set and facial image color feature set, and locating the bilateral acromion points, bilateral anterior superior iliac spine points, the spinous process point of the seventh cervical vertebra, and bilateral patellar points in the whole-body optical images to obtain an initial posture point set. This invention, by simultaneously collecting four types of data—health description text, tongue image, facial image, and whole-body posture—combining posture feature quantification extraction, multi-feature tensor fusion, and a two-stage judgment mechanism, overcomes the limitations of single-dimensional identification and improves the objectivity of TCM constitution identification.

This invention relates to the field of pipeline corrosion protection technology, specifically to a method and system for full-lifecycle rust prevention and control of ultra-high strength square tubes with rust and corrosion resistance. The method includes the following steps: extracting image anomaly markers, combining them with standard classification and adaptation, verifying indicators, generating access or blocking markers, changing status, and archiving. In this invention, defect areas are identified by acquiring images and film thickness information, and their location and classification are completed by combining structural coordinates and component codes. Based on image texture, boundary morphology, and foreign object characteristics, and combined with set standards, a regional adaptation level is established. Coverage status is determined from multiple dimensions, improving the accuracy and reliability of surface assessment. The determination results simultaneously generate access or blocking instructions. Embedded process control ensures stable switching connections, avoids protection interruptions, and status information is uniformly archived to form a structural-level traceability record, covering all stages of identification, judgment, repair, feedback, and archiving, enhancing adaptability, consistency, and full-process controllability.

The application relates to the technical field of image processing, and provides an image filling method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: encoding a text prompt word to obtain a text encoding vector, and encoding a masked background image to obtain an image encoding vector; splicing the image encoding vector, a position mask and random noise to obtain a fusion noise vector; gradually denoising the fusion noise vector, and adding the text encoding vector and a texture guide vector as guide conditions in the denoising process to generate a filling image; and the texture guide vector is obtained based on splicing, smooth transition and encoding processing of texture features of a foreground image and texture features of a background image. Through the gradual denoising process and in combination with the text encoding vector and the texture guide vector as double guide conditions, the filling image with rich details, natural texture and high fusion with the background image can be generated.

This invention discloses a high-precision emission flux quantification method for plume velocity inversion, verification, and fusion imaging. The method includes: in plume velocity inversion measurement using the improved Farneback dense optical flow method, a clustering algorithm is used to extract plume features from the image and screen the main plume components; image texture intensity is calculated based on the main plume components, and the corresponding optical flow parameters are determined; forward optical flow is calculated based on the optical flow parameters; a consistency error field based on bidirectional optical flow is introduced, and time consistency correction is performed on the forward optical flow based on the consistency error field; the fusion weight factor is determined based on the gradient of the calculated forward optical flow; and the velocity is calculated after weighted total variation denoising of the forward optical flow to obtain the plume velocity inversion result; the plume velocity inversion result is verified; and the plume velocity inversion result is combined with hyperspectral remote sensing imaging to achieve high-precision emission flux quantification, thus improving the accuracy of emission flux calculation for organized industrial emissions.

The application relates to the technical field of image enhancement, and particularly provides an underwater image enhancement method and device based on multiple attentions, which comprises the following steps: obtaining an underwater image to be enhanced; performing feature extraction and enhancement processing on the underwater image to obtain an enhanced underwater image; performing layer-by-layer down-sampling on the underwater image to extract multi-scale features; performing layer-by-layer up-sampling on the multi-scale features; performing rectangular window division on a feature map in at least one up-sampling level; performing window attention calculation of a fusion convolution operation on each rectangular window; and fusing the up-sampled features and the down-sampled features of the corresponding level; determining the parameters of the feature extraction and enhancement processing through training; the training comprises constructing a loss function based on a weighted combination of a Charbonnier loss, a gradient loss and a multi-scale structural similarity loss, and adjusting the parameters by taking the loss function as an optimization target; and the application increases the reconstruction of underwater image texture details of the model, thereby improving the quality of the image.

This invention discloses a music-assisted image generation method based on music theory element extraction. The method specifically includes: extracting six-dimensional fine-grained structured music theory semantics from audio using a multimodal large language model and performing cross-modal consistency verification; constructing a neutral scene description based on the NSA (Neutral, Concise, White Space) principle to provide a semantic whiteboard; intelligently translating music theory elements into visual modification instructions using the large language model, adaptively rewriting the neutral scene to generate fusion prompts; and using the FastVAR model for efficient image generation. Compared with existing technologies, this invention effectively solves the problems of black-box feature extraction and semantic alignment ambiguity in audio-driven generation, eliminates logical conflicts caused by cross-modal splicing, and achieves high-quality generation while ensuring high-fidelity image texture details and semantic consistency. The method is intelligent and efficient, and has good application prospects in the fields of intelligent art creation and music visualization.

This invention provides a point cloud segmentation method for tunnel lining based on a large visual model and image completion. The method involves steps such as point cloud acquisition and preprocessing, axis fitting and intensity image generation, mask generation and image texture completion, adaptive hybrid prompt information generation, zero-shot instance segmentation using a large visual model, and 3D back-projection of the segmentation results. This method solves the problems of scarce tunnel scene annotation data and interference with segmentation accuracy caused by equipment occlusion, achieving fully automatic and high-precision segment recognition, and providing technical support for intelligent tunnel operation and maintenance.

This invention discloses an intelligent recognition device for conductor skipping in power transmission line construction, belonging to the field of power transmission line construction safety monitoring technology. It includes a multimodal image acquisition module, an image restoration and processing module, a geometric constraint positioning module, an adaptive skipping judgment module, a real-time early warning transmission module, and an adaptive update module. This intelligent recognition device effectively solves many industry pain points of traditional skipping recognition technology in power transmission line construction, achieving accurate and real-time recognition and early warning of conductor skipping under extreme weather conditions. It abandons the passive mode of traditional mechanical protection and the defects of contact sensors that are prone to accidental activation. It overcomes the technical bottleneck of traditional visual recognition relying on image texture and failing in severe weather. Through multimodal image acquisition, physical restoration of extreme weather images, and geometric constraint positioning, it truly achieves all-weather, blind-spot-free monitoring. Simultaneously, relying on weather-adaptive dynamic judgment thresholds and continuous frame verification mechanisms, it significantly reduces the false alarm rate.