1328 results about "Image conversion" patented technology

The invention discloses a thermal imaging temperature rise trend early warning system based on time-space sequence prediction, and particularly relates to the technical field of thermal imaging data prediction and early warning. The thermal imaging temperature rise trend early warning system comprises an image conversion module, a fluctuation feature extraction module, an edge prediction module, an anomaly characterization module and a prediction decision module; a temperature dynamic change rate and gradient intensity are calculated, edge model prediction is carried out based on a fluctuation index combination, when the fluctuation index combination does not exceed a stable interval, a lightweight deep network model deployed at a thermal imaging acquisition end is called, and when the fluctuation index combination exceeds the stable interval, a prediction decision module determines whether to switch to a high-order multi-modal model; the space-time information extraction capability is improved by constructing the temperature evolution data body, the prediction path is dynamically controlled based on the fluctuation index combination, and the prediction stability and efficiency are improved; and the abnormal activation index and the prediction offset index are combined to realize adaptive switching of model calling, so that the accuracy and adaptability of the early warning system are enhanced.

The invention relates to the technical field of image conversion, and provides a bidirectional fusion image style migration method and system based on content and style decoupling, and the method comprises the steps: obtaining a style image set and a content image, respectively extracting a common style feature and a content feature, carrying out the bidirectional fusion of the style feature and the content feature through a cross attention mechanism, and carrying out the bidirectional fusion of the style feature and the content feature. Generating two-way fusion features after fusion; extracting a text feature based on the obtained text description, splicing the text feature with the bidirectional fusion feature to generate a condition control vector as guide information for image generation, executing a denoising inverse diffusion process guided by the condition control vector on the obtained target image, and finally decoding to obtain a stylized image; based on bidirectional feature fusion of styles and contents and a text-guided diffusion generation mechanism, an image style migration effect with delicate style expression, clear semantic structure and strong controllability is realized.

The invention discloses a universal multi-modal target tracking method based on space-time propagation and modal cooperation, and belongs to the technical field of computer vision. The method comprises the following steps: converting RGB and X modal images into a token form, and constructing initial features in combination with modal specific time tokens; the method comprises the following steps of: extracting a multi-level enhanced feature through a Transform encoder and a Mama collaborative prompt block; generating discriminative fusion features by using a gating fusion and context sensing module; a time-guided attention mechanism is adopted to strengthen search area features, and a result is output through a tracking prediction head; and transmitting the fusion time token as historical information to the next frame, and dynamically updating the template by combining a long-short time template updating strategy. According to the method, complementarity and space-time dependence between modes are effectively mined, tracking robustness and generalization ability in a complex scene are improved, and the method is suitable for various mode combination tasks such as RGB-D, RGB-T and RGB-E.

The invention provides a method for generating multi-dimensional landform vector data based on remote sensing image semantic segmentation, and belongs to the technical field of remote sensing image ground object recognition and artificial intelligence, and the method comprises the steps: training a landform recognition deep learning model based on a remote sensing image, adjusting a pre-training weight to optimize an image encoder, and generating a classification result; the landform recognition deep learning model comprises an encoder formed by a multi-layer convolutional network and a decoder of an up-sampling and feature fusion architecture; extracting a single-band label corresponding to each landform type from the classification result, and generating a binary raster image with the single-band labels; and converting the binary raster image with the single-band label into a vector diagram, and combining the vector diagram with the elevation information to generate multi-dimensional geographic data.

The invention provides an OCR (Optical Character Recognition) method and system for high-precision table data structuring. The method comprises the following steps: converting an original image into a grayscale image and preprocessing the grayscale image; extracting a table edge structure line and filling a fracture part; detecting longitudinal and transverse straight lines in the preprocessed image, calculating intersection points, and determining a table row-column structure; dividing a cell region and positioning to generate a cell coordinate matrix; pixels in the cells are divided into a frame influence area and an effective data area, and the frame influence area executes neighborhood mean filtering and weighted fusion operation; performing end-to-end detection on characters and symbols in the effective data area, and outputting an OCR recognition result with coordinates; and dynamically generating a table structure template based on the cell coordinate matrix and an OCR recognition result, speculating a strategy matching field type through a rule, processing and merging cell missing data based on adjacent cell information, and outputting structured data. The reliability and accuracy of the OCR technology are improved, and the requirement of automatic information processing for high-precision data extraction is met.

The invention discloses a deep learning-based multimodal image fusion method for soft tissue photoacoustic / ultrasound imaging. Steps: an ultrasound-photoacoustic imaging device acquires photoacoustic and ultrasound images of human soft tissue and performs size normalization processing; an input spatial transformation module converts the images to the YCbCr space; an input pre-convolution module modifies the number of data channels; an input multi-scale feature extraction module extracts salient features from the source images; an input filter prediction module derives multi-scale filters; and an input filter fusion and adaptive enhancement module combines the input source images to obtain the final fused result. The invention has superior fusion performance compared to several traditional fusion methods and deep learning-based fusion methods, and more importantly, it exhibits excellent real-time performance. Furthermore, various modes of photoacoustic / ultrasound fusion extension experiments have verified the effectiveness of the method proposed in the invention.

The invention discloses an intelligent pallet fork correction method based on visual inspection, and relates to the technical field of visual inspection, a real-time image of a pallet fork is collected through a visual inspection system, the real-time image is converted into a gray level image matrix, the gray level image matrix is compared with a pre-stored design image matrix pixel by pixel, a difference matrix is generated, and the difference matrix is used for correcting the pallet fork. According to the difference matrix, the pose offset of the pallet fork is calculated, the deformation compensation amount of the pallet fork is calculated through a compensation amount estimation model based on the pose offset in combination with the material parameters of the pallet fork, whether the deformation compensation amount exceeds a preset compensation amount threshold value or not is judged, and if yes, a control instruction of the pallet fork is generated based on the deformation compensation amount; and the adaptability of the system under different working environments and load conditions is enhanced.

The invention discloses an unmanned aerial vehicle infrared thermal imaging method and device for cold leakage detection of a low-temperature storage tank, and relates to the field of automatic inspection and detection of storage tanks, and the method comprises the steps: determining the inspection range and detection distance of an unmanned aerial vehicle based on geometric parameters, a cold leakage frequency region and environment parameters of a site; calculating the distance between the shooting points and the vertical coverage height of single-circle flight, further dividing flight elevation layering, and calculating the number of the shooting points of each circle of flight; establishing a three-dimensional model; collecting a visible light image and an infrared thermal imaging image of each shooting point; the method comprises the following steps: performing multi-dimensional correction and temperature image conversion on an acquired infrared thermal imaging image, performing image registration on a temperature image with a temperature scale and a visible light image, performing cold leakage area identification to obtain a cold leakage area, performing quantitative calculation to obtain three-dimensional positioning of a cold leakage position and a cold leakage area, and performing cold leakage area identification on the cold leakage area. And generating a visual detection result, a detection report and a maintenance suggestion. According to the invention, automatic detection and accurate analysis of the cold leakage area of the low-temperature storage tank can be realized.

The invention relates to a micro-expression recognition method based on double-flow feature fusion, and belongs to the field of computer vision. The method comprises the steps of obtaining N frames of images of a micro-expression video from a start frame to a vertex frame, and calculating an optical flow field between adjacent frames by adopting an optical flow algorithm so as to effectively extract optical flow features of micro-expressions; the method comprises the following steps: acquiring N frames of images of a micro-expression video from a start frame to a vertex frame, converting the N frames of RGB face images into a CIE Lab color space, calculating a pixel difference between two frames of converted Lab images, and extracting pixel stream features of micro-expressions; and inputting the optical flow features and the pixel flow features into a constructed double-flow three-dimensional convolutional network for feature extraction and fusion, and classifying micro expressions. According to the method, the dynamic and subtle changes of the micro-expression are effectively captured by combining the optical flow and the pixel difference characteristics. By integrating spatial and temporal information, richer feature representations are provided. The improved attention mechanism further focuses on fine facial changes, and the accuracy of micro-expression classification is improved.

The invention discloses a multi-sensor fusion processing method, perception method and equipment based on LiDAR point cloud pseudo image conversion, a multi-view projection strategy is adopted to convert a preprocessed LiDAR point cloud into an aerial view, a front view and a side view, the aerial view, the front view and the side view are subjected to feature coding and then fused through a SENet attention mechanism to generate a multi-view fusion pseudo image, and a large amount of space information is reserved. Meanwhile, in order to effectively improve the multi-sensor feature fusion efficiency, after a visual image is preprocessed, an improved CNN network is adopted to extract the features of a LiDAR pseudo image and the visual image, feature fusion is achieved through a cross-modal attention mechanism, attention weights are generated by calculating a similarity matrix, and the feature fusion efficiency is improved. And after the features are enhanced, the features are fused in a channel splicing and element-level adding mode. The method can effectively improve the precision and robustness of automatic driving environment perception, enhances the performance in a complex scene, and is suitable for tasks such as target detection and semantic segmentation in automatic driving.

The invention relates to a computer vision and digital image processing technology, in particular to an image defogging method of a multi-scale convolutional neural network based on dark channel prior. Estimating the initial transmissivity and atmospheric light of the foggy image based on a dark channel prior method; the foggy image is converted into a gray level image, a gray level threshold value is selected to be used for distinguishing a sky area and other areas, and the initial transmissivity after screening is obtained; optimizing the initial transmissivity through a multi-scale convolutional neural network by adopting a coarse optimization stage and a fine optimization stage in sequence to obtain refined transmissivity; and reconstructing a fogless image according to the refined transmissivity by adopting an atmospheric scattering model. According to the method, the advantages of a physical model and deep learning are fused, the problems of supersaturation, edge artifacts, color distortion and the like in a sky region in a traditional method are solved, the PSNR (Peak Signal to Noise Ratio) of a defogged image is remarkably improved (up to 23.30), the SSIM (Subscriber Identity Module) (up to 0.978) and the like, and a robust visual enhancement scheme is provided for scenes such as automatic driving and traffic monitoring.

The invention relates to the field of soil substance detection, and discloses a soil plastic detection method and system based on multi-modal fusion and deep learning, and the method comprises the following steps: obtaining one-dimensional hyperspectral data of a to-be-detected soil sample; converting the one-dimensional hyperspectral data based on an image conversion algorithm to obtain two-dimensional image representation; performing feature extraction on the one-dimensional hyperspectral data based on a first preset algorithm to obtain spectral features; performing feature extraction on the two-dimensional image representation based on a second preset algorithm to obtain image features; performing multi-view probability fusion on the spectral features and the image features to obtain fusion features; and inputting the fusion features into a pre-trained double-path attention residual convolutional network model for classification to obtain a detection result of the micro-plastics in the to-be-detected soil sample. According to the method, the detection accuracy is improved, the model robustness is enhanced, and low-concentration detection is realized.

A method for technical issue resolution. The method includes: receiving, from a user, a text query concerning a technical issue; obtaining query-related context relevant to the text query; and processing, through a large language model (LLM), the text query and the query-related context to produce a multimodal query response used by the user to address the technical issue. More specifically, embodiments described herein utilize text topic and zero shot classification models to translate multimodal technical documentation (e.g., including text and images) into topic relevant metadata; and process queries, pertaining to technical issues, using a multimodal LLM provided with query-related text and image context derived from said topic relevant metadata.

The invention relates to the technical field of computers, in particular to a general traffic image generation method for solving unbalanced network traffic classification, which comprises the following steps of: arranging and combining original network traffic into a session stream according to a time sequence based on a session stream mode, and converting the session stream into an image by taking a data packet as a unit. Converting the effective load of each data packet into a grayscale image; the SCGAN is used for training; eliminating noise by adopting a convolution noise reduction auto-encoder, and performing high-definition reconstruction on the generated flow sample; and combining a minority of types of traffic image samples generated through high-definition reconstruction with the original real traffic samples. According to the method, when the data packets are converted into the traffic images, the time sequence dependency relationship of the network traffic is reserved, the structural features among the data packets in image representation are also reserved, a balanced new network traffic data set is constructed, the authenticity and diversity of the data set are kept, and the generalization ability and effect of the model are improved.

The invention provides a low-cost visual field large model for visual multi-modal information processing, and the model comprises an image encoder module which is used for converting an input image into low-dimensional feature representation; the feature extraction module is used for extracting multi-scale visual features based on a hierarchical multi-task learning strategy and reducing redundant calculation through a cross-modal parameter sharing mechanism; the task specifying module is used for designing a lightweight sub-model for image classification, target detection and image generation tasks, and integrating pruning and quantification technologies to optimize calculation efficiency; the reasoning optimization module is used for reducing model reasoning complexity and energy consumption by adopting a low-rank decomposition LoRA and mixed precision calculation technology; and the multi-modal fusion module is used for integrating vision, text and sensor data through a cross-modal attention mechanism to generate cross-modal joint feature representation so as to improve task robustness in a complex scene. According to the method, through the design of model architecture, parameter quantity and calculation optimization, the requirement for hardware resources is remarkably reduced.

The embodiment of the invention provides an image processing method, a computer program product, equipment and a storage medium. The method comprises the following steps: acquiring a to-be-processed image, wherein the to-be-processed image is a blurred image with an unknown blurred domain; converting the Y-channel image of the to-be-processed image into a Y-channel image with a known fuzzy domain by using a pre-trained generator of a generative adversarial model, and performing deblurring processing on the Y-channel image with the known fuzzy domain to obtain a clear Y-channel image; and performing enhancement processing on the edge region of the clear Y channel image, and fusing the image obtained by the enhancement processing with the UV channel image of the to-be-processed image to obtain a clear image corresponding to the to-be-processed image. Through the method provided by the invention, a clear image with a clear edge and a good effect can be obtained, and the effect of the clear image obtained through deblurring processing is ensured.

The present invention discloses a mask-based wafer defect classification system and method, which relates to the field of wafer defect classification technology. The system assigns a corresponding category number to the pixels in each defective area to form a label image. A 1x1 convolutional layer is added to convert a four-channel input image into a three-channel feature map. The label image and the three-channel feature map are then input into an image semantic segmentation model for training. When a defective wafer image is input into the trained image semantic segmentation model, the model performs inference and outputs the wafer's defect location and classification results. Based on the defect location and classification results, the wafer is evaluated for defects and a defect report is generated. The classification system splices the wafer image with the defect mask in the channel direction, allowing all defective areas to be fully classified through a single segmentation inference. This not only optimizes image segmentation accuracy but also improves processing efficiency, significantly enhancing the performance and applicability of the wafer defect classification system.

The invention provides a method for quickly converting a resource image into print engine data, which comprises the following steps of: acquiring the width, the height and the number of spray heads of the resource image, and generating blank two-bit depth print engine data according to the number of spray holes of a single spray head; splitting the resource image into a plurality of sub-images according to the number of nozzles; data area addresses, widths and heights of the plurality of sub-images and mapping coordinates of the print engine data are respectively transmitted to create a mapping task; the mapping task performs first bit operation on the plurality of sub-images in a column mode to obtain a first operation result, and the first bit operation is detection; performing second bit operation on the print engine data by using the first operation result, wherein the second bit operation is writing according to lines; and completely pasting the plurality of sub-images on the print engine data through circulation. According to the method for rapidly converting the resource image into the print engine data, the image conversion efficiency can be improved, and the rapid printing requirement is met.

An image conversion apparatus according to one embodiment includes: a memory that stores an image conversion program to compress a plurality of images into a single image or decompress the compressed single image into the plurality of images; and a processor that executes the image conversion program, and the image conversion program inputs the plurality of images into an encoder model and outputs the compressed single image in which the remaining images are inserted into one of the plurality of images, and the encoder model is machine-learned to compress a plurality of initially input images into a single image by hierarchically compressing the plurality of images into one according to a tree structure, ensuring the final compressed image is identical to one of the initially input images.

Provided is an image processing device including: an image conversion unit that performs an anonymization process on a plurality of input images captured in a time series; and an image determination unit that determines whether the plurality of input images on which the anonymization process has been performed satisfy a predetermined requirement, wherein the image determination unit performs a predetermined process on the plurality of input images on which the anonymization process has been performed in a case where it is determined that the plurality of input images on which the anonymization process has been performed satisfy the predetermined requirement, the anonymization process includes a process of changing a face of a person depicted in the plurality of input images to a face of another person, and the predetermined requirement includes that faces of persons tracked as the same person in the plurality of input images are the same face in each of the plurality of input images on which the anonymization process has been performed.

The invention discloses an infrared and visible light image fusion method and system based on dual-channel frequency domain guidance, and the method comprises the following steps: firstly, extracting the shallow spatial domain features of infrared and visible light images through a convolution layer; secondly, converting the image to a frequency domain by using fast Fourier transform (FFT), respectively fusing amplitude and phase components, and recovering the image to a spatial domain through inverse FFT (IFFT); thirdly, inputting the shallow layer features into a module based on Swin Transform to extract deep global features; then, frequency domain and space domain information is integrated through a cross-domain fusion module, and intra-domain and cross-domain interaction is achieved in combination with multi-head self-attention (MSA) and cross-attention (MCA) mechanisms; and finally, reconstructing a fusion image based on a CNN-Transform hybrid architecture, and reserving the target saliency of the infrared image and the texture details of the visible light image. According to the method, through a frequency domain and space domain double-path fusion strategy, the quality of the fused image is remarkably improved, the recognition precision can be effectively improved in a target detection task, and the practical value is high.

Systems and methods for converting two-dimensional (2D) static images to three-dimensional (3D) animated images are provided. Such a method includes: receiving, by a server device, one or more 2D static images, each 2D static image of the one or more 2D static images depicting a respective environment; generating a 3D mesh based on a 2D static image of the one or more 2D static images; determining a visual perspective trajectory along the 3D mesh, the visual perspective trajectory indicative of simulated movement within a 3D animated image at least partially along an axis associated with depth in the respective environment depicted by the 2D static image; and generating the 3D animated image based on the 3D mesh and the visual perspective trajectory such that the 3D animated image replicates the simulated movement.

The embodiment of the invention provides a flexible material measuring method and device, electronic equipment and a medium, and relates to the technical field of tire manufacturing. The method comprises the steps that in the conveying process of a detected flexible material, at least two laser light strip images of the detected flexible material within a preset time interval are acquired through a camera; performing center line extraction processing on the at least two laser strip images to obtain at least two corresponding laser center lines; based on the information contained in the at least two laser center lines, image conversion is carried out, a corresponding target 3D point cloud image is obtained, and the target 3D point cloud image contains the thickness information of the detected flexible material; a calibration image corresponding to the detected flexible material is obtained, and the calibration image is an image collected under the condition that the detected flexible material is calibrated by the calibration block; and determining the width of the detected flexible material and / or the thickness of the detected flexible material based on the target 3D point cloud image and the calibration image.

The invention provides a novel rotating machine fault intelligent diagnosis method, and belongs to the technical field of fault diagnosis, and the method comprises the steps: obtaining vibration signals of a rotating machine under normal and different fault types; performing preprocessing, decomposition and noise removal on the vibration signal by adopting a variational mode decomposition method VMD, and performing reconstruction to generate a new signal; the new signal is converted into a two-dimensional time-frequency image by adopting short-time Fourier transform STFT; using an interstellar fleet optimization algorithm SFA to optimize hyper-parameters of the convolutional neural network-long and short term memory network CNN-LSTM; inputting the two-dimensional time-frequency image into the CNN-LSTM model subjected to hyper-parameter optimization for training; and after noise reduction and two-dimensional time-frequency image conversion are carried out on a to-be-diagnosed rotating machine fault diagnosis signal, the signal is input into the VMD-SFA-CNN-LSTM model to realize rotating machine fault diagnosis. The method has very important practical significance for improving the rotating machine fault diagnosis accuracy and guiding equipment maintenance and repair.

The invention discloses an electronic screen film surface dust detection method based on photometric stereo. The method comprises the following steps: image acquisition: acquiring 4-8 grayscale images in different incident directions; image preprocessing: carrying out edge-preserving noise reduction processing on the original image by adopting a bilateral filter, improving the smoothness by combining a Gaussian filter, and converting the filtered image into a floating point type; normal reconstruction: calculating a surface normal vector corresponding to each pixel point through a least square method or robust estimation according to a photometric stereo principle by utilizing a multi-light source matrix form, and generating a normal distribution diagram; curvature calculation: estimating a local curved surface of each pixel neighborhood based on the reconstructed normal graph; and dust identification: through setting a dynamic threshold and a region growing algorithm, extracting a continuous and significant normal disturbance region, and carrying out classification, marking and visual output in combination with characteristics such as area, length, boundary curvature and the like.

A processor-implemented method including converting an input image based on first sub-images of first color channels into a multispectral image based on second sub-images of second color channels, generating an illumination map representing an illumination configuration of the input image, based on the input image, generating a confidence score map of the illumination map, based on the multispectral image, and determining illuminant information of the input image by fusing the illumination map with the confidence score map, a second number of channels of the second color channels being greater than a first number of channels of the first color channels.

The invention discloses a progressive multi-modal medical image fusion method based on multiple scales. Relates to the technical field of multi-modal medical image fusion, in particular to a progressive multi-modal medical image fusion method based on multiple scales. Through the integrated design of multi-scale extraction, hierarchical coding, layer-by-layer fusion and adaptive modeling, efficient and accurate fusion of multi-modal medical images is realized, and reliable technical support is provided for clinical application. The method comprises the following steps: acquiring images of a mode A and a mode B, and preprocessing the images; performing multi-modal parallel coding on the preprocessed image, wherein the multi-modal parallel coding comprises four coding stages; the input of each coding stage passes through a self-adaptive visual RWKV module, an efficient cross-modal module and a progressive fusion module in sequence to obtain the output of multi-modal parallel coding; and carrying out image conversion to obtain an RGB fusion image.

The invention belongs to the technical field of image analysis and processing, and particularly relates to a flame image-based rotary furnace combustion state prediction method and system. The method comprises the following steps: acquiring a video image sequence of flames in the rotary furnace, and converting each frame of image into a YUV color space; calculating a combustion contribution degree based on the brightness component and the chromaticity component, and screening out a core flame pixel set; taking the combustion contribution degree as a weight, calculating a weighted covariance matrix, determining a confidence ellipse according to the eigenvalue and eigenvector of the matrix, taking the center of the confidence ellipse as a weighted centroid, determining a rotation angle by the eigenvector, and making the length of long and short semi-axes in direct proportion to the square root of the eigenvalue; extracting the area, eccentricity rate, rotation angle and center position of the confidence ellipse as combustion state feature vectors at the current moment; and inputting a time sequence formed by the combustion state feature vectors at the multiple moments into a pre-trained hidden Markov model, and outputting the combustion state of the rotary furnace. According to the invention, the accuracy and anti-interference capability of combustion state prediction are improved.

The invention discloses a high-throughput continuous switching food 3D printing method and system. The method comprises the steps that a printing target three-dimensional model is selected, layered slicing is conducted on the printing target three-dimensional model in the Z-axis direction, and multiple layers of printing images are generated; converting the multi-layer printing image generated by slicing into a material information matrix based on a gray threshold; printing parameters are set, a material switching advance distance and material switching section variable speed optimization are set according to material physical properties, and a continuous switching food 3D printing G-code control instruction is generated based on the material information matrix. According to the method, accurate segmentation and path coherence control of a multi-material area can be achieved in combination with the rheological property of the food material, so that the high-throughput printing requirement is met while the pattern fidelity is guaranteed, stable deposition and accurate pattern reproduction of the food material can be achieved in the fast switching process of the same spray head, and the printing efficiency is improved. And the comprehensive performance of food 3D printing in complex model manufacturing and high-throughput production can be improved.