554 results about "Image object" patented technology

The invention discloses a multi-modal entity and relation extraction method and system based on cross-modal alignment and fusion, and the method comprises the steps: carrying out the processing and coding of an input text and an image, and obtaining a plurality of types of image and text features; performing feature alignment on the fine-grained and coarse-grained text features and the pixel-level image representation by taking the semantic representation of the image as an anchor point, and mapping the image and the text features to the same semantic space; performing multi-granularity feature fusion through text-guided dynamic gating aggregation, visual prefix cross-modal fusion and cross-modal image-text matching, modeling association between noun phrases and image objects in a text while increasing feature complementarity, and obtaining multi-granularity multi-modal feature representation; fusing multi-granularity multi-modal features through entity guidance attention gating, and gathering visual information related to a text entity to obtain final multi-modal fusion representation; according to the multi-modal fusion representation, task prediction of multi-modal named entity recognition and multi-modal relation extraction is carried out.

The invention discloses a target detection method based on Mama feature fusion, and relates to the technical field of image target detection. According to the method, the innovative implementation of the VSSA module is utilized, a selective scanning mechanism of the state space model is applied to 2D visual data processing, the long-distance dependency relationship in the image is effectively captured through state space modeling in four directions, the limitation of a traditional state space model in the two-dimensional visual data processing process is solved through the multi-direction processing strategy, and the processing precision of the 2D visual data is improved. The model can comprehensively perceive spatial dependency relationships in different directions in an image, the VSSA adopts learnable state space parameters to dynamically model a feature sequence, the ability of the network to understand a complex space structure is enhanced, the method is particularly suitable for processing scenes needing long-distance context information, and in addition, the method is combined with MTMHSA, so that the complexity of the network is reduced. And the fusion capability of different levels of features in target detection is further enhanced. Through the innovation, the model can better understand the target in the image, and the positioning and classification precision of the target is improved.

The invention relates to a remote sensing image ground feature recognition method based on deep learning, and the method comprises the steps: carrying out the data collection and preprocessing of a ground surface target region, eliminating the position deviation through geometric correction, processing the illumination difference through combination with radiation equalization, and generating a ground feature registration image; performing multi-dimensional feature fusion processing on the image, performing tensor fusion on vegetation spectral features, earth surface texture features, point cloud data features and linear ground feature features, and constructing a ground feature fusion matrix; a bilateral convolutional neural network is adopted to extract spectral response characteristics and spatial correlation characteristics, and characteristic interaction is realized through an attention mechanism to generate a ground feature probability distribution diagram; and finally, carrying out noise filtering, boundary refining and vectorization conversion processing on a classification result, and outputting a ground feature classification vector diagram. According to the method, three technical bottlenecks of insufficient cooperative utilization of multi-source heterogeneous data, insufficient spectrum-space feature fusion and poor GIS compatibility are solved, and the operation efficiency of territorial investigation, disaster monitoring and other scenes can be remarkably improved.

Disclosed is a nighttime unmanned aerial vehicle (UAV) object tracking method fusing a hybrid attention mechanism. According to the method, a night vision image enhancement model is employed to enhance various nighttime image frames in a night vision video sequence of UAV before performing image object tracking and recognition, to improve the accuracy of object tracking for nighttime images. With the aid of a spatial channel hybrid attention mechanism, the night vision image enhancement model can adaptively learn spatial channel features, enhancing generalization ability, and enabling the network model to focus on more effective features. Additionally, a denoising processing module is introduced to remove noise hidden in the nighttime images, improving the object positioning accuracy and tracking performance of UAV in nighttime scenarios, and reducing the failure probability of object tracking by UAV in nighttime scenarios.

A method is provided for generating a dynamic image object (DIO), comprising: generating a synthetic image from a first image and a second image; storing the synthetic image within a DIO; and generating a display image based on the DIO and a viewing parameter.

The invention discloses a defoaming agent foam distribution analysis method based on image feature recognition, and particularly relates to the field of industrial foam behavior perception and analysis for recognizing an image object with a random mode as a feature, and the method comprises the following steps: obtaining a foam image sequence in a target area, and collecting the foam image sequence through imaging equipment, the image frames of the foam image sequence have time continuity; and performing disturbance feature extraction operation on the foam image sequence to obtain local disturbance speed information, membrane surface tension change trend information and form boundary fluctuation information of the foam edge within a preset time. According to the method, foam structure disturbance characteristics are extracted from an image time sequence, a structure evolution graph memory bank is constructed, and irregular sudden change image behaviors are identified in combination with a trend matching mechanism, so that dynamic perception and abnormal response of a sudden foam state without prior support are realized, and the problem that a random mode foam state cannot be identified is solved.

The embodiment of the invention discloses an adaptive alignment cross-modal vision-language ship intelligent man-machine interaction method. The method comprises the following steps: extracting target image objects semantic representation and position information corresponding to each object from a visual image acquired by a ship-borne visual sensor; extracting a text token semantic representation from a corresponding language instruction of the visual image, and calculating a text summary representation; performing in-mold alignment operation on the extracted text token semantic representation; carrying out intra-mode and inter-mode interactive alignment on the extracted image token semantic representation; performing compression and integration on the text token semantic representation information of the fine granularity, and fusing the text semantic representation and the cross-modal image objects semantic representation; and projecting the fusion features, constructing a loss function, and obtaining a target related to a language instruction and a position thereof, so that a sailor can conveniently perform real-time man-machine interaction with an intelligent identification scene in a cruising process, the intelligence and operation efficiency of a ship are improved, and the next intelligent decision can be better performed.

A method for automated, artificial-intelligence-based COC retrieval includes using an artificial intelligence / machine learning system (AI / ML system) to optically scan a follicular fluid sample to produce an image object using an imaging system that includes a microscopy system, a camera system, and a lighting system. The method includes comparing the image object to a predetermined threshold using an AI / ML system, wherein the predetermined threshold is at least in part an optical pattern with a probability of corresponding to a cumulus-oocyte-complex (COC). The method includes identifying a COC within the follicular fluid sample based at least in part on the image object satisfying the predetermined threshold. The method includes determining a COC location within the follicular fluid sample based at least in part on identifying a region of the image object corresponding to an optical pattern within the image object that satisfies the predetermined threshold.

A trained model is retrained for video quality assessment and used to identify sets of adaptive compression parameters for transcoding user generated video content. Using transfer learning, the model, which is initially trained for image object detection, is retrained for technical content assessment and then again retrained for video quality assessment. The model is then deployed into a transcoding pipeline and used for transcoding an input video stream of user generated content. The transcoding pipeline may be structured in one of several ways. In one example, a secondary pathway for video content analysis using the model is introduced into the pipeline, which does not interfere with the ultimate output of the transcoding should there be a network or other issue. In another example, the model is introduced as a library within the existing pipeline, which would maintain a single pathway, but ultimately is not expected to introduce significant latency.

The invention discloses a cross-domain remote sensing image target detection method based on multi-scale decoupling representation and reinforcement learning. The method comprises the following steps: step 1, acquiring a cross-domain remote sensing image target detection data set; 2, building a DINO remote sensing image cross-domain target detection model, obtaining an initial multi-scale feature map through a backbone network, obtaining multi-scale domain invariant semantic features by using a multi-scale decoupling representation module, and reducing domain deviation between a source domain and a target domain; 3, performing multiple rounds of training on the model built in the step 2; 4, multiple rounds of retraining are conducted on the trained model, on the basis that the training logic in the step 3 is kept, a category self-adaptive pseudo-label screening mechanism based on reinforcement learning is introduced, the model obtains high-quality pseudo-labels of a target domain, model training is guided, effective target domain information is learned, and adaptability to the target domain is improved; and 5, performing detection on the model obtained in the step 4 by using a target domain test set to improve the cross-domain target detection performance.

The invention provides a satellite-borne edge calculation-oriented target detection model lightweight method. The method comprises the following steps of S1, training an image target detection model capable of identifying a feature missing target by collecting a training data set, performing self-supervised contrast training and constructing a channel attention mechanism; s2, abstracting a neural network model by using a graph structure for the target detection model, and identifying and trimming redundant channels so as to compress the neural network model to obtain a compressed model; and S3, performing model performance optimization on the compression model by using a comparative generative adversarial network and a knowledge distillation method to obtain a lightweight target detection model. According to the method, under the condition that the compression model realizes lightweight deployment of the satellite-borne edge computing environment, the detection speed and precision are ensured, and the recognition capability of a feature missing target is enhanced.

The invention relates to the field of computer vision target detection, in particular to a weak illumination target detection method based on improved YOLOv8, which comprises the following steps: acquiring a weak illumination image data set, converting the weak illumination image data set into a data set suitable for a YOLO format, and dividing the data set into a training set, a verification set and a test set; an improved YOLOv8 weak illumination image target detection model is constructed; wherein a space and channel recombination convolution and weighted bidirectional feature pyramid network module is introduced into the neck network; an efficient channel attention module is introduced into the backbone network and the neck network; and finally, introducing a loss function based on an auxiliary frame to optimize an original loss function. Training the improved YOLOv8 target detection model by using the training set to obtain a model pre-training weight; inputting a to-be-detected image into the optimal weight model for detection; according to the method, the target detection task in a weak light environment is better aimed at, the detection accuracy is improved, the model is lighter, and deployment on mobile equipment is facilitated.

The utility model discloses a monocular telescopic laser range finder with a novel focusing function, which comprises a telescopic optical system, and the telescopic optical system comprises an objective lens group, an inner focusing lens, a beam splitter prism group, an LCD (Liquid Crystal Display) and an eyepiece group which are sequentially arranged along an optical axis L from a scene side to an eye side, the objective lens group, the inner focusing lens, the beam splitter prism group, the LCD and the eyepiece group are installed in a shell, the eyepiece group can move left and right along an optical axis L so as to adjust the distance between the eyepiece group and the LCD, people with different eyesight can clearly watch images displayed on the LCD, the inner focusing lens is additionally arranged between the objective lens group and the beam splitter prism group, and the lens group can be used for adjusting the distance between the eyepiece group and the LCD. The inner focusing lens can move left and right along the optical axis L so that sceneries at different distances can be imaged on the LCD, the inner focusing lens is driven by the driving mechanism, two functions of adjusting the distance between the eyepiece group and the LCD and focusing and imaging the sceneries at different distances on the LCD are realized by adopting two sets of independent mechanisms, the two functions do not interfere with each other, and the implementation is easy.

Embodiments of the present description provide an image object detection method. The method comprises: on the basis of an image to be retrieved, an object description text, and an object retrieval condition, determining, by means of an object detection model, a target position of an object to be retrieved in said image, wherein the object description text is used for describing said object, and the object retrieval condition comprises at least one of a mask image, a pose, and a texture corresponding to said object.

The invention discloses a big data hypergraph network modeling method and device, computer equipment and a product, aims to solve the problem that efficiency and accuracy are difficult to consider when large-scale data of intellectual property is processed in the prior art, and aims at the characteristics of high increment, high timeliness and multiple modes of the intellectual property data. The method comprises the following steps: analyzing and concluding passed intellectual property files, classifying according to corresponding professions, and establishing a corresponding intellectual property text library; constructing a text corpus based on intellectual property by using a BERT algorithm model, performing capsule graph neural network processing on the image information of the corresponding category, obtaining a correlation between image objects and text attributes thereof, and constructing an image database; capturing complex correlation characteristics in the text by utilizing the characteristics of the graph convolutional neural network; and constructing a hypergraph neural network model. The invention provides a big data hypergraph network modeling method capable of processing high-increment, high-timeliness and multi-modal data.

Methods and systems for performing image object removal, including: obtaining an input image comprising an object; obtaining a mask corresponding the object in the input image; generating a masked image based on the input image and the mask, wherein the masked image comprises a missing area corresponding to the object; providing the masked image to a Fourier-based encoder; and generating a composed image by providing an output of the encoder to a Fourier-based cascaded decoder comprising a Fourier-based global modulation decoder cascaded with a Fourier-based spatial modulation decoder, wherein the object is not included in the composed image

The invention belongs to the field of target detection application of image target detection, underwater target detection and the like, and discloses a target detection method based on a spiking neural network and a Transform, which comprises the design of a feature extraction network based on the spiking neural network and the Transform, the design of a novel spiking neuron, the design of a Transform module based on the spiking neuron, and the design of a target detection module based on the novel spiking neuron. The problem that an existing target detection network based on a spiking neural network is too low in performance is mainly solved. According to the rapid and effective target detection method provided by the invention, the spiking neurons are introduced, so that the target detection network achieves high performance, and meanwhile, the network operation power consumption, the parameter quantity and the calculation quantity are reduced; the network can be effectively trained in various target detection scenes, the network weight is deployed to edge small computing power equipment and brain-like chip equipment, and large-scale application of a target detection algorithm is realized.

The invention provides a remote sensing image ground object segmentation method and system based on YOLOv8-seg-GCHA, and electronic equipment. The method comprises the following steps: acquiring a remote sensing image, performing ground feature labeling on the acquired image, and generating a ground feature segmentation data set; the method comprises the following steps: constructing a YOLOv8-seg-GCHA network structure; according to the YOLOv8-seg-GCHA network structure, a GCHA module and a normalized depth separable convolution DSCBS module are introduced into YOLOv8-seg, and the GCHA module and the normalized depth separable convolution DSCBS module are introduced into the YOLOv8-seg. Wherein the GCHA module is used for identifying global information and local details of an image; using the surface feature segmentation data set to train the YOLOv8-seg-GCHA network structure, and obtaining a surface feature segmentation model; and inputting a remote sensing image of a target area into the ground object segmentation model to obtain a ground object segmentation result of the target area. By applying the technical scheme provided by the invention, the features can be decoded and classified more accurately, the capability of analyzing the boundary and internal details of an actual ground object by a network is improved, the segmentation precision is improved, and meanwhile, the loss of computing resources is reduced.

The invention provides an improved YOLOv8 underwater image target detection method, device, medium and program, a fine-grained feature extraction module is arranged to replace a C2f module on the basis of YOLOv8, the fine-grained feature extraction module comprises a visual state space model and a local feature extraction module which are arranged in parallel, feature distribution is adjusted through linear transformation in the visual state space model, and the local feature extraction module is used for extracting local features in the visual state space model. A multi-scale space context is extracted in combination with depth separable convolution and a SiLU activation function; in the local feature extraction module, detail information of a target is focused through a convolution kernel channel attention mechanism, and noise interference is suppressed; the two outputs are subjected to element-by-element addition fusion and then enter a multi-scale cross attention fusion module, local and global features of different scales are fused in the multi-scale cross attention fusion module through dynamic weighting, and fine-grained features are output. The improved YOLOv8 is used for underwater target detection, and the identification capability of a fuzzy target and a complex background in underwater image target detection can be remarkably improved.

The present invention discloses a method and system for detecting lightweight unmanned aerial vehicle images based on wavelet convolution. The method comprises: step 1, constructing an experimental data set, and dividing the data set into a training set, a validation set and a test set after preprocessing. Step 2, training the model constructed by the method for constructing an image target detection model using a training connection to obtain a trained image target detection model; wherein the method for constructing the image target detection model comprises: constructing a backbone network, the backbone network comprises the 0th to 9th layers connected in sequence; constructing a neck network, the neck network comprises the 10th to 21st layers; constructing a detection head, the detection head comprises the 22nd to 24th layers. Step 3, preprocessing the test set and inputting it into the trained image target detection model, and outputting the target detection result. The method and system of the present invention provide a more efficient, robust and easy-to-integrate target detection solution.

A system for generating non-fungible token-based test suites from design diagrams comprises a processor associated with a server. The processor is configured to obtain image objects representing a workflow associated with a design diagram and a user profile of a user. The processor is configured to generate a design non-fungible token (NFT) associated with the design diagram to verify a design diagram ownership. The processor is configured to convert the image objects of the design diagram into corresponding text objects and to process the corresponding text objects of the design diagram to generate a plurality of text datasets corresponding to the workflow of the design diagram, analyze the plurality of the text datasets and generate a test suite which comprises a set of test scripts corresponding to the design diagram, and generate a test case NFT associated with the test suite to verify a test suite ownership.

A computer implemented method, system, and non-transitory computer-readable device that may be used in a remote deposit environment. Upon receiving a user request, based on interactions with the UI, the method implements an electronic deposit of a financial instrument by activating a camera on the client device to generate a live video stream of image data of a field of view of at least one camera, wherein the live video stream includes imagery of at least a portion of each side of the financial instrument. The method continues by extracting data fields based on the formation of image objects on one or more sides of the financial instrument from the live video stream of image data. An EFT conversion of extracted data fields may be processed during or subsequent to the extraction process. A message is sent from a payee to a payor requesting the EFT. Upon acceptance, an EFT to the payee occurs. Upon denial, the remote deposit process is completed.

The invention relates to a training method of an image generation model, an image generation method and related equipment. The method comprises the following steps: acquiring noise image sample tokens of a plurality of noise sample images and condition sample feature information of corresponding condition sample information; the plurality of noise sample images are sample images with a plurality of different image object categories and / or different noise intensities; obtaining a sample token pool corresponding to each noise image sample token in the same training batch; calling an image generation model realized based on a diffusion model, and carrying out denoising processing on the sample token pool and the condition sample feature information to obtain predicted image information; in the de-noising processing process, based on a preset expert capacity, determining target sample tokens which need to be processed by each expert sub-network in the hybrid expert network in the image generation model from a sample token pool; and performing model training based on the difference between the predicted image information and the target image information. The performance of the trained model can be improved.

The invention discloses an unmanned aerial vehicle hyperspectral image object-level target detection method based on spatial-spectral decoupling and double-flow interactive fusion, belongs to the technical field of remote sensing image processing and computer vision, and particularly relates to an object-level target detection method of a hyperspectral image. The objective of the invention is to solve the problems of low detection precision and robustness and the like caused by pixel-by-pixel detection, insufficient spatial spectrum information fusion and insufficient complex scene adaptability in an existing unmanned aerial vehicle hyperspectral target detection method. The method comprises the following steps: step 1, acquiring a hyperspectral image of an unmanned aerial vehicle; step 2, inputting the hyperspectral image into a hyperspectral decoupler, and outputting spatial features and spectral features by the hyperspectral decoupler; 3, inputting the spatial features and the spectral features output by the hyperspectral decoupler into a spatial-spectral feature extraction and fusion module, and outputting the features by the spatial-spectral feature extraction and fusion module; and 4, inputting the features into a detection head, and outputting a detection result by the detection head.

The invention discloses a style migration method for separating content image objects, which comprises the following steps of: extracting a style image and a content image of a target image, processing the style image by using a salient target detection module, and distinguishing a style main object from a background object; constructing a depth estimation mechanism, processing the content image through a depth estimation module, and obtaining depth information of the content image; on the basis of the style separation attribute of the convolutional feature channel, extracting the features of the style subject object, and designing an opacity sensitive loss function to obtain a stylized subject object migration result; in combination with the characteristic that the content background contains a complex object, based on defocusing and instance normalization, the definition and style information of the content background are adjusted to obtain a stylized background migration result; and finally, combining object migration results. When facing a content image with a disordered content main body, the method guides the style migration module to realize style migration through a depth estimation mechanism, and effectively solves the problem of disordered style migration results of a complex scene.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a modified digital image with a modified rendering order of objects within a digital image. For instance, the disclosed systems generate, in response to an input indicating a selected region of a digital image, an object mask for a first object located at least partially within the selected region of the digital image and further generate a vectorized object mask including a boundary of the first object from the object mask. The disclosed systems determine an overlapping region of the vectorized object mask with the selected region and an additional vectorized object mask. The disclosed systems generate a modified digital image by modifying a rendering order of a portion of the first object corresponding to the selected region and a portion of a second object overlapping the portion of the first object within the selected region.

A method is provided for generating a dynamic image object (DIO), comprising: generating a synthetic image from a first image and a second image; storing the synthetic image within a DIO; and generating a display image based on the DIO and a viewing parameter.

A method for training a neural network for controlling a robot. The method includes ascertaining a camera pose in a robot cell and an uncertainty area around the ascertained camera pose, ascertaining an object area in the robot cell, generating training-camera-images, for each training-camera-image a training-camera-image camera pose being randomly established in the uncertainty area around the ascertained camera pose, a training-camera-image object pose being randomly established in the object area and the training-camera-image being generated, so that it shows the object with the training-camera-image object pose from the perspective of a camera with the training-camera-image camera pose, generating training data from the training-camera-images, each training-camera-image being assigned one or multiple training-robot control parameters for handling the object in the training-camera-image object pose of the training-camera-image, and training the neural network using the training data.

Systems, methods, and data storage devices for improved classifier training using a video object tracker to determine video data samples are described. A group classifier may be trained using machine learning to classify image objects, based on a set of machine learning parameters, and assign them a group identifier. A retraining data set may be determined based on video data that was assigned that group identifier based on an object tracker. The group classifier may be retrained using the retraining data set to determine an updated set of machine learning parameters and the group classifier may be updated with those parameters.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a modified digital image with a modified rendering order of objects within a digital image. For instance, the disclosed systems generate, in response to an input indicating a selected region of a digital image, an object mask for a first object located at least partially within the selected region of the digital image and further generate a vectorized object mask including a boundary of the first object from the object mask. The disclosed systems determine an overlapping region of the vectorized object mask with the selected region and an additional vectorized object mask. The disclosed systems generate a modified digital image by modifying a rendering order of a portion of the first object corresponding to the selected region and a portion of a second object overlapping the portion of the first object within the selected region.