1576 results about "Image processing" patented technology

The invention provides a tunnel crack identification method and system based on multi-source image processing, and relates to the technical field of tunnel engineering, and the method comprises the steps: obtaining multi-source data of a horizontal rock stratum tunnel; performing spatial registration on the multi-source data to generate a multi-modal image under the same reference system; extracting multi-modal features according to the multi-modal image, and constructing a multi-source feature map under the same space grid; performing crack initial detection on the multi-source feature map in combination with multi-scale filtering and structure tensor analysis to obtain a crack candidate region mask; accurate crack identification is carried out through the crack candidate area mask, a crack identification result is obtained by combining bedding direction constraint and a microconditional random field, and the crack identification result comprises a crack segmentation map and a crack category. The method solves the problem that existing crack identification does not consider the bedding characteristics of the horizontal rock stratum tunnel.

The invention relates to an infrared and visible light image fusion method based on a cross-domain Transform, and belongs to the field of computer image processing. The method comprises the following steps: respectively carrying out preprocessing operation on an infrared image and a visible light image to obtain a training data set; an end-to-end image generator network is designed, an encoder module is used for extracting deep semantic features of an infrared image and a visible light image, a fusion module introduces an axial attention mechanism to enhance the global modeling capability of the features, and feature fusion is carried out in combination with information of a spatial domain and a frequency domain; the fused features are gradually recovered to an image space through a decoder module, and a fused image is generated; constructing a fusion loss function module, and guiding the network to focus a significant feature difference between the source image and the fusion image based on a comparative learning idea; and finally, inputting the infrared and visible light image Y channel into the network model, generating a fusion image, completing a training process, and realizing unified optimization of fusion performance and visual quality.

The invention discloses a virtual fitting method and device, a storage medium and electronic equipment, and is applied to the technical field of computer image processing, and the method comprises the steps: processing a target video, and obtaining the human body posture data of each video frame in the target video; constructing a 3D human body model of each video frame by using the human body posture data of each video frame; for the 3D human body model of each video frame, acquiring clothing rendering information of the 3D human body model, and rendering virtual clothing on the 3D human body model based on a dynamic fitting algorithm and the clothing rendering information to obtain a virtual rendering video frame of the video frame; and generating an AR fitting video based on each virtual rendering video frame, and displaying the AR fitting video to the user. Therefore, the selected costume can be tried on in the AR form, the fitting effect of the costume can be displayed for the user, the problem that the size is improper due to the fact that the costume purchased online cannot be tried on is solved, the probability of refunding and changing goods is reduced, and good shopping experience is provided for the user.

An image processing apparatus is disclosed. The image processing apparatus of the present invention comprises: an image receiving unit for receiving a first image and a second image of the same object taken at different times; a processor for obtaining transformation information by registering the first image on the basis of the second image, obtaining a first segment image corresponding to an area of the object from the first image, and generating a second segment image corresponding to an area of the object of the second image by transforming the obtained first segment image according to the transformation information; and an output unit for outputting the second segment image.

The invention discloses a diabetic foot assessment method based on wound image recognition. The method comprises the following steps: processing a foot infrared thermal imaging image to generate a temperature anomaly graph; fusing the foot wound image and the temperature anomaly graph to generate a fused image; constructing a foot blood flow analysis model, extracting a blood flow influence factor, and correcting the fused image through the blood flow influence factor; and constructing a joint assessment model, taking the corrected fusion image and historical data of the diabetic foot patient as input of the joint assessment model, predicting a risk assessment level of the diabetic foot, and outputting a disease assessment result of the diabetic foot patient according to the risk assessment level. According to the method, multi-modal medical image fusion analysis is realized, the accuracy of wound area positioning and pathological state expression is improved, the accuracy of lesion area recognition is improved, the illness worsening risk can be predicted in advance, clinical decision can be assisted, the risk of serious complications such as amputation of a patient is reduced, and the prognosis and life quality of the patient are improved.

The invention discloses a hydraulic engineering dam body crack detection method and system based on machine vision, and relates to the technical field of computer vision. A high-definition camera is used for shooting a dam body image, obtaining a sample data set, extracting feature parameters of different noise types, and constructing a feature database; filtering the current dam body image to obtain a first dam body image, enhancing the crack gray scale difference of the first dam body image, obtaining a second dam body image, segmenting the second dam body image, screening candidate cracks in the crack image, and identifying real cracks according to the edge features of the candidate cracks. According to the method, a feature database is constructed, a targeted dam body image processing flow is combined, a high-definition camera collection and automatic processing flow is used, filtering parameters are dynamically adjusted by constructing the feature database, gray level enhancement and precise segmentation are combined, real cracks are precisely recognized through edge feature analysis and comparison, and quantitative parameters are output; and a reliable basis is provided for dam body safety assessment.

The invention discloses a self-adaption eye fundus image processing method and device based on a passive field. The method comprises the following steps: acquiring an eye fundus image with a label in a source domain and an eye fundus image without a label in a target domain, and preprocessing the eye fundus image; training a teacher model and optimizing model parameters; using teacher model parameters to initialize two student models with the same structure; inputting the target domain unmarked fundus image into the teacher model and the student model for pixel-level learning; constructing category prototypes of optic cups and optic disks based on high-confidence features extracted by the teacher model, and guiding student model features to be aligned with the category prototypes; calculating the prediction difference of the teacher model and the student model in the boundary region, and correcting the segmentation result of the fuzzy boundary; constructing a total loss function, and iteratively updating teacher model parameters to obtain a fundus image segmentation model; and performing optic cup and optic disk segmentation on the target domain eye fundus image by using the eye fundus image segmentation model, and performing quantitative analysis. According to the method, the generalization and segmentation performance of the model on the target domain is remarkably improved.

The invention provides a robot electrical equipment defect detection system based on multi-modal image processing. The system improves the accuracy and reliability of electrical equipment defect identification. Infrared and visible light images are jointly collected, and through a registration algorithm of multi-source features and equipment structure priori, space-time alignment of multi-modal images is achieved. Then, a dynamic weighted fusion strategy is utilized to generate fusion features with higher discriminative ability, and abnormal features are extracted through a double-branch mechanism to be verified with thermophysical consistency; and finally, constructing a neural network model fused with physical prior, and performing defect classification and positioning output on the verified feature data. According to the method, the structure and thermal information are fused, a physical constraint mechanism and a joint training strategy are introduced, the robustness and engineering interpretability of the system under complex working conditions are remarkably improved, and the method has a wide application prospect.

The invention discloses a heterogeneous double-flow fusion method and system for diabetic retinopathy grading. The method comprises the following steps: obtaining an output result of diabetic retinopathy grading by utilizing a heterogeneous double-flow architecture; processing an input fundus image into images with different resolutions; extracting global context features from the low-resolution image by using a lightweight visual Transform model distilled by composite knowledge, and extracting local focus features from the high-resolution image by using a convolutional neural network model; performing interactive fusion on the global context features and the local focus features of the double-branch architecture through a symmetric bidirectional cross attention fusion module to obtain enhanced fusion feature representation; and finally, inputting the fusion features into a classifier, and outputting a severity grading result of the lesion. The method aims at improving the accuracy and robustness of hierarchical diagnosis through deep analysis of global information and local details, and can be applied to the medical fields of clinical computer-aided diagnosis, eye image analysis and the like.

The invention discloses an industrial surface defect image classification method based on hybrid query strategy active learning, and belongs to the technical field of computer image processing and machine learning. The invention aims to solve the technical problems of high cost, long period and low rare defect recognition rate caused by category imbalance due to dependence on large-scale manual labeling. The core of the method is to execute a hybrid query strategy in an iterative loop: firstly, screening out a candidate sample set of model cognitive ambiguity through uncertainty measurement of prediction entropy; secondly, in the candidate set, a core set and hierarchical thought diversity sampling method is adopted to select a final to-be-labeled sample with both characteristic representativeness and category balance. And the query batch is manually annotated and then is used for carrying out iterative updating and optimization on the model. According to the method, the recognition precision and generalization ability of the classification model on various defects can be remarkably improved with extremely low manual labeling cost, and the model development period is greatly shortened.

The invention discloses a laser welding seam online quality detection system and method based on multi-mode visual fusion, and particularly relates to the technical field of laser welding seam quality detection. Comprising a data acquisition and synchronous control unit, a 2D image processing and defect detection unit, a 3D point cloud processing and size measurement unit, a multi-modal information fusion and collaborative analysis unit and a comprehensive quality judgment and output unit. According to the laser welding seam online quality detection system and method based on multi-modal visual fusion, the 2D and 3D multi-modal visual fusion technology is adopted, an improved defect detection algorithm and an accurate size measurement method are combined, welding seam surface defects are accurately recognized through 2D images, key size data are obtained by means of 3D point cloud, and the detection accuracy is improved. And the limitation of'heavy defects and light sizes' or'heavy sizes and light defects' in single-modal detection is avoided, and comprehensive and accurate evaluation of the welding seam quality is realized.

The invention discloses a hot-dip galvanized steel pipe ground cage verticality measuring system based on machine vision, and relates to the technical field of physical measurement, and the system comprises a projection unit which is used for projecting polarization gray scale stripes with polarization codes to a to-be-measured hot-dip galvanized steel pipe ground cage; the imaging unit comprises at least two cameras which form a triangulation base line with the projection unit so as to synchronously acquire multi-view images from different views; and the processing unit is configured to perform polarization difference fusion on the multi-view images to suppress mirror reflection, generate corresponding polarization difference fusion images, reconstruct pipe body three-dimensional point clouds of all the hot-dip galvanized steel pipes in the corresponding hot-dip galvanized steel pipe ground cages, generate pipe body axial vectors by adopting robust cylinder axis fitting, and obtain the pipe body three-dimensional point clouds of all the hot-dip galvanized steel pipes in the corresponding hot-dip galvanized steel pipe ground cages. And calculating the perpendicularity deviation angle of the pipe body according to the axial vector of the pipe body and the gravity direction. Therefore, on the premise that the measurement precision is guaranteed, the spatial postures of the multiple steel pipes are synchronously collected and recognized at a time, multi-point repeated scanning is not needed, and the detection efficiency is remarkably improved.

The invention relates to the technical field of robot control, and discloses a robot scanning path adjusting method, device, equipment and medium, and the method comprises the steps: controlling a robot equipped with a sensor to move along a preliminary path, collecting a preliminary two-dimensional image of a target object, processing the image, extracting the feature points of the target object, and combining the spatial information of the sensor when the image is collected; the method comprises the steps of generating a primary three-dimensional point cloud, determining a plurality of ideal sensor postures based on the primary three-dimensional point cloud, determining a new sensor position of each posture on a contactable surface to generate a re-planned scanning path, controlling a robot to move along the re-planned scanning path, adjusting the sensor postures, and collecting a final two-dimensional image of a target object. According to the method, the scanning path is optimized in combination with the initial three-dimensional point cloud local surface normal direction, so that the attitude of the sensor is matched with the geometrical characteristics of the target surface, the problem of three-dimensional reconstruction surface breakage caused by inter-frame pose mismatching under free breathing is solved, and the accuracy of autonomous ultrasonic scanning of the robot is improved.

The invention relates to the technical field of image segmentation, in particular to an intensive care unit video image processing method based on image semantic segmentation, which comprises the following steps of: acquiring a video image through monitoring camera shooting, dividing a semantic region, calculating a pixel displacement direction of each part, identifying an abnormal track, erasing interference, recombining a boundary contour, and comparing shape change. And constructing a trend and re-drawing a structure, evaluating stability in combination with directions, speeds and amplitudes, screening and correcting inconsistent labels, and outputting an index result. According to the method, track features are constructed by introducing pixel direction coding, a deviation region is identified and interference is eliminated in combination with a direction change trend, an edge structure is reconstructed by using a boundary connection sequence and curve fitting, contour division is optimized through deformation direction consistency, and labels are corrected by synthesizing direction change and boundary speed. Dynamic tracking and accurate labeling of the patient state are achieved, the abnormal action recognition efficiency and the label updating accuracy are improved, and the time sequence integrity and the space expression ability of image data are enhanced.

The invention relates to the technical field of intelligent medical treatment, and discloses a portable blood vessel puncture device and method based on an AI identification B-ultrasonic image, and the method comprises the steps: determining a puncture body position and a to-be-scanned surface; constructing a coordinate system; based on the two-dimensional grid layout, driving the B-ultrasonic puncture integrated equipment to perform matrix scanning in the to-be-scanned surface to obtain and visualize a plurality of static blood vessel sub-images arranged in a matrix and corresponding coordinates of the static blood vessel sub-images; performing image processing by using the plurality of static blood vessel sub-images and the corresponding coordinates thereof to obtain and visualize continuous blood vessel structure image data; an AI recognition model is constructed, the blood vessel structure image data, the multiple static blood vessel sub-images, the corresponding coordinates and preset puncture data serve as input, a puncture strategy is output and visualized, and the puncture strategy comprises target puncture data and a puncture path which are determined based on a coordinate system; and driving the B-ultrasonic puncture integrated equipment to puncture along the puncture path. According to the invention, full automation of blood vessel puncture to establish deep and shallow artery and vein channels is realized, and the puncture success rate and safety are improved.

The invention discloses an infrared and visible light image fusion method based on text supervised contrast learning. Comprising the steps that an infrared image, a visible light image and text description of the infrared image and the visible light image of the same scene are acquired, and multi-modal image features are extracted through linear embedding and cross attention Mama modules by adopting a preprocessing and image block division strategy; a pre-training text encoder is used for obtaining text semantic features, dimension alignment and weighted fusion of images and text features are achieved through an image-text feature alignment fusion module, and a fused image is generated. End-to-end training is carried out through image-text contrast learning loss in combination with pixel reconstruction and infrared intensity retention loss, and the semantic consistency and the thermal target retention capability of the fused image are effectively improved. The fusion process further comprises image-text matching weight calculation, feature weighting adjustment and fusion convolution operation. The method has the advantages of being high in semantic guiding capacity, excellent in fusion effect, accurate in hot target expression and the like, and is suitable for a multi-modal image processing task.

The invention relates to the technical field of data processing, in particular to an auxiliary driving device and system based on video image processing, and the device comprises a frame buffer queue with a multi-channel video collection module aligned with timestamps; a hierarchical calculation task decoupling module identifies task types in the frame buffer queue and marks priority labels, including a first priority label of a radar data analysis and distance superposition task, a second priority label of a vehicle profile generation task and a third priority label of a video fusion task, and outputs a data stream with priority labels; the calculation module generates a task processing result; the genetic algorithm optimization scheduling module generates a resource allocation strategy and controls the calculation module to execute task processing; and the output synchronous control module synthesizes a high-priority task result and performs frame rate synchronous output on a low-priority task. According to the method, the problem of real-time degradation caused by multi-path high-definition video stream processing is solved through task grading and dynamic resource scheduling, and the image output delay of the auxiliary driving scene is reduced.

The invention discloses a video transmission image stitching data enhancement method based on deep learning, and relates to the field of video image processing. The method comprises the following steps: S1, acquiring and screening images; s2, continuously screening structures and selecting key frames; s3, correcting image distortion; s4, splicing and fusing the images; s5, performing image enhancement output; firstly, a sliding time window mechanism is adopted, multi-dimensional image quality screening is combined, fuzzy, underexposure or severely-shielded inferior frames are accurately removed, and high quality of input key frames is ensured; through intelligent splicing and enhancement of a dynamic adaptive threshold strategy and semantic guidance, the image splicing precision and efficiency of the unmanned aerial vehicle and the multi-view camera in a complex environment are remarkably improved; besides, semantic segmentation guided feature extraction is combined with a multi-band fusion technology, seamless splicing is realized, the quality of an output image is improved, and the reliability of automatic analysis and decision making is remarkably improved.

The invention provides an efficient image super-resolution method and device based on dual guidance semantic enhancement, and relates to the technical field of image super-resolution, visual content generation and the like in computer image process.The method comprises the steps that an image super-resolution model containing a pre-training diffusion model backbone structure is constructed, and a pre-training diffusion model is constructed; a trainable LoRA module is inserted into a U-Net structure and a VAE encoder of the image super-resolution model; calculating the perception image loss of the generated image and the real image by adopting a dual-guidance quality enhancement training strategy; based on a semantic alignment method of score matching, performing semantic feature constraint on the generated image through a condition vector of a pre-training diffusion model to form semantic consistency loss aligned with real image distribution; and carrying out end-to-end training on the image super-resolution model under joint optimization of perceptual image loss and semantic consistency loss, and after the training is finished, realizing high-resolution generation of a low-resolution image only through one-time U-Net reasoning.

A method includes obtaining a document structure from a data repository. The document structure includes multiple structured sections. A table is detected in a first structured section. A table representation of the table is processed by a general large language model (LLM) to generate a natural language description of the table. An image is detected in the first structured section. The image is processed by an image-processing LLM to generate a natural language description of the image. A form is detected in the first structured section. The form is processed by the general LLM to generate a natural language description of the form. The natural language descriptions of the table, image and form are inserted into the first structured section to obtain a modified first structured section. A modified document structure including the modified first structured section is outputted.

An apparatus includes an input unit, a processing unit, and an output unit. The input unit is configured to provide the processing unit with at least one diffusion magnetic resonance imaging dMRI image of a patient's brain. The processing unit is configured to: 1) determine an estimate of an orientation of neurons at each voxel in the dMRI image; 2) determine a plurality of fiber tracts in the at least one dMRI image; 3) select a plurality of voxels along at least one fiber tract of the plurality of fiber tracts; and 4) determine a neurological disease classification.

Disclosed is method of image processing for three-dimensional reconstruction in an extended reality environment. The method includes defining a set of visual-attributes derived from reference images; identifying presence of at least one visual-attribute in a displayable content of target images to be used for the three-dimensional reconstruction; and modifying the displayable content of the target images, by concealing or displaying the identified at least one visual-attribute, for the three-dimensional reconstruction in the extended reality environment.

The invention discloses a unified multi-mode infrared and visible light image fusion and conversion method in the technical field of computer vision and multi-mode image processing. The unified multi-modal infrared and visible light image fusion and conversion method comprises the following steps: constructing a unified encoder based on a UniIVFT architecture, sharing parameters to process IVF and I2V tasks, and introducing comparison loss to align visible light and infrared image embedding in a multi-modal embedding alignment module; and in the multi-modal feature fusion and decoding module, optimization is carried out through reconstruction loss, and the multi-modal features are fused and decoded into an output image. According to the unified multi-modal infrared and visible light image fusion and conversion method, multi-modal features are aligned by sharing an encoder architecture and comparing loss, efficient infrared-visible light image fusion and conversion are achieved, model redundancy is reduced, and cross-task performance is improved.

The invention relates to the technical field of video image processing, and discloses a video image super-resolution enhancement method based on a generative adversarial network. The method comprises the following steps: segmenting a low-resolution video sequence, and analyzing frame timestamp information to generate a dynamic time axis containing key frame nodes so as to reflect video time change characteristics; then, in combination with the time axis and an image feature extraction system, feature mapping is carried out on the low-resolution frames, and a preliminary high-resolution image sequence with feature information is obtained; enhancing the preliminary sequence by using a generative adversarial network containing a generator and a discriminator in combination with a context-aware optimization technology to generate an enhanced sequence; and a machine learning algorithm is introduced to identify and classify different image quality region characteristic modes, and an intelligent identification rule base is established, so that an enhanced sequence is optimized. And finally, in response to user interaction, adjusting display parameters to realize personalized display, integrating a multi-dimensional analysis tool, calculating details of a specific region, and presenting a result in a visual interface, so that the video image quality can be improved.

The invention relates to the technical field of computer image processing, in particular to a farmland forest network extraction method and system based on a SegFormer model, and the method comprises the steps: obtaining a remote sensing image of a farmland forest network; the remote sensing image is preprocessed; performing image annotation on the preprocessed remote sensing image to obtain a training data set; a farmland forest network extraction model based on a Segform model is constructed; adopting the training data set to train the farmland forest network extraction model; and inputting a remote sensing image of a to-be-detected area into the trained farmland forest network extraction model to obtain a high-precision farmland forest network target area. According to the embodiment of the invention, the SegFormer model is optimized, the jump connection module is added, and the CBAM module is introduced, so that the perception capability of the model for space and channel information is enhanced, the segmentation precision is further improved through the jump connection and the up-sampling module, and the farmland forest network can be accurately extracted.

The invention discloses a paint surface visual inspection and grinding and polishing method. The method comprises the following steps: after carrying out structured light stripe projection on a vehicle body paint surface according to preset robot track information, collecting an original color stripe image through a camera; performing image processing on the original color stripe image to obtain a feature enhanced image; performing defect detection on the feature enhancement image through a pre-constructed defect identification model to obtain defect information; according to the defect information, grinding and polishing motion tracks and corresponding technological parameters of all the robots are determined; and each robot is controlled to work according to a preset grinding and polishing control algorithm, the grinding and polishing motion track and the process parameters. The method can solve the problems that the labor efficiency is low, the quality is difficult to unify, and the high-quality and standardized production requirements cannot be met.

The invention provides a textile fabric drapability measuring method and system capable of showing warp and weft anisotropy. The method comprises the following steps: aligning the centers of square textile fabric samples and covering the square textile fabric samples on a square supporting platform in parallel; collecting a stable top view image of the sample drooping due to self weight; processing the image to obtain overhanging contour information; respectively determining the overhang spacing along the warp direction and the weft direction of the sample as characteristic values based on the contour; and independently evaluating the longitude and latitude drapability according to the characteristic values. According to the invention, the to-be-tested textile fabric can form a stable draping form with clear direction characteristics, independent draping quantitative indexes in warp and weft directions can be respectively obtained through single test, the fabric warp and weft anisotropy can be directly represented, the test repeatability is good, the operation is simple and convenient, and a reliable basis is provided for clothing fabric parameter calibration.

Embodiments of the disclosure provide a method, apparatus, electronic device and storage medium for processing image, and the method includes: obtaining an image to be processed; determining an object structural feature within the image to be processed corresponding to a target object and determining a style texture feature corresponding to a reference style image to be applied; and determining a target style image corresponding to the image to be processed based on the object structural feature and the style texture feature.

A mark that identifies a lesion site is displayed on a tomographic image. A two-dimensional map and a graph are displayed regardless of whether or not the mark is displayed. The two-dimensional map represents lesion site probability distribution. The graph represents temporal change of lesion site probabilities.

The method for estimating the area of an irregular-shaped fire scene using an optoelectronic pod in the present invention belongs to the technical fields of navigation control algorithms and infrared image processing, and includes: S101: Preprocessing and background suppression are performed on the infrared thermal image, and the fire scene area in the image is identified according to the gray value of the image and the set temperature threshold; S102: Determine the slant range information of the fire scene area aligned with the optical axis of the pod; S103: Place the infrared thermal image in a rectangular coordinate system with the alignment point of the pod optical axis as the origin, and the fire scene area forms an irregular area in the rectangular coordinate system; S104: Calculate the area projected onto the actual ground for each pixel in the fire scene area according to the optical axis attitude, geographical location information, and slant range information, and add up the projected areas of each pixel to obtain the fire scene area on the actual ground. It can greatly improve the efficiency of forest fire prevention emergency rescue and the accuracy and real-time nature of fire situation reports, thereby achieving rapid analysis of forest fire situations and providing strong information support for forest fire fighting and emergency command.