2005 results about "Image map" patented technology

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enabling artificial intelligence to generate new images based on contextual data and to generate digital components based on the images. In one aspect, a method includes receiving one or more queries from a client device of a user. A digital component is selected based on the one or more queries. A customized digital component is generated by obtaining an image of an object corresponding to the selected digital component and generating, using a language model, an image editing prompt for editing the image based on digital component data related to the digital component and query data including the one or more queries and contextual data. The image and the image editing prompt are provided to an image editing model. An edited image is received and used to generate the customized digital component.

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

The invention provides a picture editing method and system based on multi-modal condition adaptation, and the method comprises the steps: obtaining a first text vector: obtaining a picture description corresponding to a picture through processing, processing the picture description through an editor, and obtaining a first text vector; obtaining a first text vector based on the picture information; a second text vector acquisition step: processing the used editing instruction to obtain a second text vector based on the editing instruction; a fusion feature acquisition step: fusing the first text vector and the second text vector through weight to obtain a fusion feature; an image potential feature code acquisition step; in the image editing step, the injected condition information is received, meanwhile, the received potential features and potential noise of the image are denoised, and the image desired by the user is gradually generated in the iterative denoising process under the guidance of the received condition information; and an image restoration step. According to the invention, the stability, controllability and accuracy of image editing can be improved.

A method for executing robotic grasps includes acquiring an image of a scene with one or more objects and processing the acquired image using a trained grasping neural network. Depth and color frames of the image are passed separately through convolutional blocks of an encoder for extracting feature maps via down sampling of the respective image frames. The feature maps extracted from the depth and color frames are fused to produce a fused feature map. The fused feature map is spatially divided into patches and fed as input to a vision transformer to encode the patches based on information from other patches in the fused feature map. The output of the vision transformer is fed to a decoder to construct a grasp map of the scene. An optimal grasping location is estimated from the grasp map.

The invention discloses a packaging box printed matter printing quality detection method, which comprises the following steps of: acquiring a high-resolution printing image through an image acquisition module, preprocessing and segmenting the printing image by an image processing module, optimizing image quality, classifying the preprocessed image by an image classification module according to characters, patterns and color blocks, and detecting the printing quality of a packaging box printed matter. The defect detection module performs multi-dimensional detection on the classified preprocessed images based on image parameter data, the quality analysis module quantitatively evaluates quality scores of characters, patterns and color blocks based on detection results, and the computer terminal generates a comprehensive score through weighting calculation and automatically generates a detection report; according to the packaging box printed matter printing quality detection method, complex defects such as font errors, stroke breakage, pattern deviation, color deviation and stains are effectively recognized through multi-dimensional defects, the manual reinspection cost is reduced through full-process automatic processing, and the quality of printed matter is visually reflected through a quantitative evaluation system.

The invention belongs to the technical field of water quality remote sensing monitoring, and particularly relates to a sky-ground remote sensing integrated lake and reservoir water quality parameter quantitative inversion method. Qualitative inversion is carried out on water quality parameters through medium-high resolution satellite remote sensing images, and ground sampling points are reasonably arranged. And carrying out ground and air collaborative operation, including on-site water body sampling and unmanned aerial vehicle flight, so as to ensure the consistency of sampled water quality parameters and unmanned aerial vehicle image spectral characteristics. The sampling point water body sample is sent to a laboratory to be tested, and measured data are obtained. An unmanned aerial vehicle image is subjected to preprocessing including splicing and radiation correction, and a reflectivity image map is obtained. Water vector data are extracted by using an unmanned aerial vehicle image, a remote sensing quantitative inversion model of water quality parameters is established, and the model is analyzed and optimized through an optimal wave band combination. And in combination with the unmanned aerial vehicle image, the inversion model and the water body vector data, obtaining a water quality parameter quantitative inversion result and spatial distribution characteristics in the lake and reservoir range. The method can improve ground sampling rationality and time coordination of lake and reservoir water quality monitoring, and supports long-term high-precision dynamic monitoring.

The invention relates to the technical field of data processing, and discloses a multi-modal relation extraction method based on large model generation and knowledge graph integration, which comprises the following steps of: firstly, generating description for an image by using a large language model, constructing an image graph, analyzing a text, constructing a text graph, linking a knowledge graph based on a tagged entity, and extracting a multi-modal relation between the tagged entity and the knowledge graph; and constructing a knowledge graph sub-graph. And then, taking the labeled entity as an anchor point, splicing the three through similarity calculation to form a unified combined graph, and extracting and fusing multi-modal features by utilizing a graph information bottleneck technology and a GCN optimization graph structure, so that the accuracy and the processing efficiency of relation extraction are improved. And through multi-modal data fusion, the accuracy and the processing speed of relation extraction are remarkably improved. A graph structure is optimized by using a graph information bottleneck technology and a graph convolutional network, and redundant information is eliminated, so that semantic features in multi-modal data are effectively extracted and fused.

A self-service POS terminal includes a tag reader, a camera, and a processor configured to: start a registration process to register items each of which has a wireless tag attached thereto, control the wireless tag reader to read tag information from wireless tags and store the tag information in memory, determine a number of the tags based on the tag information, control the camera to capture images and generate image data from each of the images, perform object recognition on the image data to determine a number of items shown in the images, compare the number of the tags with the number of the items, when the number of the tags is identical to the number of the items, perform a checkout process, and when the number of the tags is not identical to the number of the items, issue a notification signal.

The invention discloses an oral cavity panoramic image processing system, and the system comprises an image collection module which is used for collecting an initial oral cavity panoramic image containing a plurality of oral cavity diseases; the image processing module is connected with the image acquisition module and is used for performing target detection and instance segmentation labeling on the initial oral panoramic image and expanding a training data set by adopting a data enhancement technology to obtain a target oral panoramic image; a model construction module connected with the image processing module and used for training an MMC-YOLO network model through the target oral panoramic image to obtain a target MMC-YOLO network model; and the analysis and detection module is connected with the model construction module, and is used for performing synchronous detection of tooth concurrent oral diseases, comprehensive analysis of multi-dimensional pathological information and accurate recognition of multi-scale pathological changes through the target MMC-YOLO network model to obtain an analysis result. The system provided by the invention realizes synchronous detection and accurate grading of multiple types of focuses in the oral panoramic image.

Systems and methods for multi-modal image editing are provided. In one aspect, a system and method for multi-modal image editing includes identifying an image, a prompt identifying an element to be added to the image, and a mask indicating a first region of the image for depicting the element. The system then generates a partially noisy image map that includes noise in the first region and image features from the image in a second region outside the first region. A diffusion model generates a composite image map based on the partially noisy image map and the prompt. In some cases, the composite image map includes the target element in the first region that corresponds to the mask.

The invention relates to an unmanned aerial vehicle lens stain identification and cleaning method and system based on deep learning. The method comprises the following steps: generating an image acquisition instruction according to a set sampling period to obtain a to-be-detected image; the image acquisition instruction is used for instructing an unmanned aerial vehicle camera to perform image acquisition operation and feeding back in the form of a to-be-detected image; preprocessing the to-be-detected image to obtain a to-be-detected standard image; inputting a to-be-detected standard image into the stain detection model to obtain a stain identification result; the stain identification result comprises a central coordinate of the polluted area, bounding box data, a confidence coefficient score and a stain type label; generating a cleaning parameter and a cleaning instruction according to the stain identification result; the cleaning instruction is used for instructing the cleaning equipment to clean the unmanned aerial vehicle lens according to the cleaning parameters. By adopting the method, the problems of difficult stain identification and extensive cleaning decision in an existing unmanned aerial vehicle visual system can be solved, and the accuracy of stain detection and the intelligence of cleaning control are realized.

The invention discloses a meta-learning and multi-modal large model-based few-sample anomaly detection method and system, and the method comprises the steps: dividing an auxiliary data set into a task set composed of N tasks according to the type of a detected target object, and dividing each task into a training set and a test set, the method comprises the following steps: constructing a semantic-anomaly network based on a multi-modal large model, the semantic-anomaly network comprising a visual encoder, a language encoder, an image-image anomaly discriminator, an image-text anomaly detector and a fusion module; and training a semantic-exception network by using the training set and the test set of each task in the task set, and using the semantic-exception network to predict an exception score of the query sample to determine whether the query sample is exceptional. The invention aims to solve the problems that the generalization ability of cross-category anomaly detection is poor and semantic information cannot be effectively converted into anomaly information in a traditional anomaly detection method, and the accuracy and robustness of image anomaly detection and the cross-category anomaly detection ability are improved.

The invention discloses a concave-convex point detection and defect evaluation system based on multistage detection and feature change, and the system comprises an image collection unit which is used for capturing a product image in real time; the image preprocessing unit is used for carrying out noise reduction processing on the image and improving the brightness and the contrast ratio of the image; the primary product defect positioning module is used for selecting Gaussian difference extraction, dynamic threshold extraction, fixed threshold extraction, template matching and a deep learning algorithm module to extract and position suspicious defects according to the size of the product and the characteristic form of the defects; the secondary defect classification and judgment module is used for carrying out preliminary classification and type judgment on the defects in the region; the third-stage defect contour extraction unit is used for performing fine contour extraction on each detected defect area after the defect classification is clear; and the four-stage defect feature analysis and evaluation unit is used for deeply extracting key features of each defect and carrying out scientific and quantitative evaluation on the key features.

Methods and apparatus for relighting images. According to an example embodiment, inverse rendering is applied to an input image to extract a plurality of channels including an original lighting channel. A first neural network is used to determine a first latent feature corresponding to the input image based on a first set of channels including a shading channel generated using a replacement lighting channel. A second neural network is used to determine a second latent feature corresponding to the input image based on a different second set of channels including the replacement lighting channel. A relighted image is generated by propagating samples of a latent image map corresponding to the input image through a conditional diffusion model to which the first and second latent features are applied as first and second conditions.

The invention relates to an end-to-end automatic driving method based on Transform multi-modal feature fusion, and the method comprises the steps: collecting an RGB image and an original depth image, and converting the original depth image into an HHA image; inputting the RGB image and the HHA image into a sensing module for fusion to obtain a fusion feature map, and performing global average pooling and flattening operation to obtain environment features; acquiring the real-time speed of a vehicle, an advanced navigation command and a target position, connecting in series to form measurement input, and processing based on an MLP measurement encoder to obtain measurement characteristics; adding the environment features and the measurement features element by element to obtain combined features, performing downsampling step by step, and connecting a ReLU activation function behind each layer to obtain track features; and a loss estimator is constructed, training loss is dynamically predicted in real time based on the track features, and the weight of each feature parameter is dynamically adjusted according to the loss, so that the vehicle is dynamically controlled and adjusted in real time. According to the method, the multi-modal features can be well fused, so that a more accurate end-to-end automatic driving method is realized.

The invention discloses an accurate feeding system and method based on machine vision. The system comprises an image acquisition module, an image processing module, a satiation degree evaluation module, an automatic feeding machine and a control module. The image acquisition module is used for acquiring a water surface spray image of the fishpond in real time; the image processing module is in signal connection with the image acquisition module and is used for carrying out segmentation and feature extraction on the water surface spray image acquired in real time by adopting a convolutional neural network to obtain spray features of the water surface spray image, and the spray features comprise the size and the duration of the spray; the water spray features before feeding, during feeding and after feeding are stored in a feeding water spray image database; and the satiation degree evaluation module is used for evaluating the ingestion active degree and the satiation degree of the fish school according to the ingestion spray characteristics on the basis of a satiation degree evaluation model. According to the method, the feeding speed is adjusted according to the collected and analyzed water spray characteristics on the water surface, so that the feeding speed is coordinated with the feeding speed, precise feeding is achieved, and residual feed is reduced.

The invention discloses a rail transit fastener model identification system and method, and relates to the technical field of fastener overhaul, an initial image of a rail is acquired through an image acquisition module, and an image preprocessing module is used for preprocessing to obtain a reference image; the image analysis module inputs the reference image into a preset model for processing, completes segmentation of the fastener assembly and the steel rail assembly, and obtains segmented images; the positioning module is used for screening the images of part of fastener assemblies and the images of the rail bottom of the steel rail and restoring the images to the reference images; the feature acquisition module is used for acquiring a reference adjustment line based on the segmented image of the rail bottom, acquiring feature parameters of the partial components based on the segmented images of the partial components, and correcting by using the reference adjustment line to obtain reference feature parameters; and the model identification module is used for matching the reference characteristic parameters of the screening component with the data in the constructed database and outputting a corresponding fastener model. According to the invention, efficient identification of the models of the fasteners can be realized, and the identification accuracy is also guaranteed.

Systems and methods are disclosed related to synthetic bracketing for exposure correction. A deep learning based method and system produces a set of differently exposed images from a single input image. The images in the set may be combined to produce an output image with improved global and local exposure compared with the input image. An image encoder applies learned parameters to each input image to generate a set of image features including local exposure estimates for each of two or more regions of the input image and a low resolution latent representation of the input image. A decoder receives the local exposure estimates, the latent representation, and target enhancements that are processed to generate synthesized transformations. When applied to the input image, the synthesized transformations produce the set of transformed images. Each transformed image is a version of the input image synthesized to correspond to a respective target enhancement.

The invention provides a method and a system for generating deviation guide information in an approaching landing section of an aircraft and a readable storage medium, and the method comprises the steps: S1, real image collection and processing: capturing an outboard environment image through an airborne visual sensor, and extracting key feature points of a target landing airport runway; s2, virtual image generation: based on the airport three-dimensional high-precision map, generating an approach glide image under a visual angle of a virtual camera; s3, image feature registration: carrying out spatial alignment on the key feature points of the runway in the real image and the key feature points of the runway in the virtual image; the pixel deviation of the runway center point in the real image and the virtual image is calculated, glide guidance is provided for a pilot or is directly input into an automatic flight system.The method can be used for the aircraft in the approaching landing section, the enhanced outboard visual display is provided for the pilot in the cockpit based on the equivalent ILS deviation guidance method, and the visual guidance effect is improved. And providing approaching glide deviation guide information.

The invention discloses an underwater image enhancement method based on cross-domain feature representation and semantic segmentation guidance, and belongs to the field of underwater image processing, and the method comprises the steps: constructing an unpaired sample data set, and dividing the unpaired sample data set into positive and negative samples; designing and initializing an image enhancement network; respectively and randomly selecting an image IH and an image IL from the positive sample and the negative sample, inputting the image IL into an image enhancement network to obtain an enhanced image IE, inputting {IL, IH, IE} into an image feature extraction model, and calculating and comparing learning loss; pre-training the semantic segmentation model on a semantic segmentation data set, then performing fine tuning on the semantic segmentation data set of the underwater image, inputting an image IH and an image IE, generating a corresponding semantic prediction map, and calculating semantic segmentation loss; training an image enhancement network by combining and comparing learning loss and semantic segmentation loss, updating parameters of the image enhancement network through end-to-end training, and generating a high-quality enhanced underwater image; the method has the effects of image precision enhancement, detail recovery, strong generalization ability and low data acquisition cost.

The invention belongs to the technical field of refrigeration equipment, and provides refrigeration equipment and a food material recognition method.The refrigeration equipment comprises a box body, the box body is provided with a plurality of storage areas used for containing food; the image acquisition equipment is arranged in at least one storage area; the control device is connected with the image acquisition equipment and is configured to respond to triggering of an image acquisition condition, an image in the storage area is acquired based on the image acquisition equipment, and an object in the image comprises one or more food materials; determining shielded food materials in the image according to food material contours of the food materials in the image; sheltering object removal processing and missing part complementation processing are carried out on sheltered food materials in the image, and a processed image is obtained; and identifying food material information of the shielded food materials in the processed image. The problem that a traditional refrigerator is low in recognition accuracy due to food material shielding can be solved.

The invention discloses an environmental health risk assessment system, electronic equipment and a nonvolatile storage medium. The system comprises an environment image acquisition module which is used for acquiring an environment image of a target area; the image feature extraction module is used for performing feature extraction on the environment image to obtain a first feature corresponding to the streetscape image and a second feature corresponding to the remote sensing image; the environment variable prediction module is used for fusing the first feature and the second feature, and determining a parameter value of an environment variable corresponding to the target area according to a fused feature obtained after fusion; and the comprehensive index determination module is used for determining a comprehensive environment index corresponding to the target crowd object in the environment of the target area according to the parameter value of the environment variable. According to the method and the device, the technical problem that the environmental health risk cannot be effectively assessed due to the fact that a method for measuring and analyzing the environmental variables mainly depends on field monitoring, the efficiency is low and the data coverage is narrow in the prior art is solved.

The invention discloses a wide-angle video monitoring system, method and equipment based on multiple cameras and a medium, and relates to the technical field of video monitoring, the wide-angle video monitoring system comprises a multi-camera acquisition module, a variable-focus high-definition camera multi-angle acquisition module, a high-quality image obtained through distortion correction and an image splicing processing module, an improved algorithm is used for accurately matching feature points and fusing the images, and the high-quality image is obtained. The intelligent analysis module detects and tracks a target and analyzes behaviors in real time by means of an improved model, the storage and transmission module performs cluster storage, advanced coding cost reduction and high-speed link transmission, and the control module performs intelligent regulation and control according to multiple information and can also perform remote management. The system has the advantages of multi-angle acquisition without dead angles, good image splicing, accurate intelligent analysis, efficient storage and transmission, adaptability to severe environments, flexible power supply, guarantee of data safety, improvement of monitoring quality and efficiency, meeting of complex scene requirements, and enhancement of practicability, reliability and safety.

A computer system and a computer-implement method include obtaining a source image and a modification input that indicates a target edit to the source image and generating a modification encoding representing the target edit. An image generation model generates an output image that depicts the source image with the target edit based on the source image and the modification encoding. The image generation model is trained to perform a pose modification task and a part replacement task.

Provided are an image encoding / decoding method and apparatus. An image decoding method may comprise deriving chroma reference samples located around a chroma block and luma reference samples corresponding to the chroma reference samples based on an intra prediction mode of the chroma block being a cross-component linear model (CCLM) mode, deriving CCLM parameters based on the chroma reference samples and the luma reference samples, and generating a prediction sample of the chroma block based on the CCLM parameters. The chroma reference samples may be obtained from two or more chroma reference lines adjacent to the chroma block.

The embodiment of the invention discloses a Himalayan marmot hole intelligent identification model construction method fusing habitat information. The method comprises the steps of obtaining multiple unmanned aerial vehicle image maps of a Himalayan marmot hole; the habitat features of marmot holes and the surroundings of the marmot holes in the unmanned aerial vehicle images are marked, and the habitat features comprise hole earth mounds, vegetation, stones and animal traces; and training a target detection model by using each marked unmanned aerial vehicle image map, and using the trained model to improve the situation of marmot hole missed identification. The embodiment of the invention can overcome the missing detection condition of marmot holes.

The invention discloses an electronic component surface quality detection method and system based on machine vision. The method comprises the steps of original image acquisition, image basic processing, image illumination reflection decoupling, quality detection model construction and component surface quality detection. The invention relates to the technical field of electronic component image processing, in particular to an electronic component surface quality detection method and system based on machine vision, and the method comprises the steps: collecting an original image to obtain an original component detection image; an image basic processing method of image cleaning, image enhancement and image standardization is adopted; an image illumination reflection decoupling method is adopted, so that illumination non-uniformity and reflection interference are eliminated, and the contrast ratio and detectability of a defect area are improved; the fusion feature defect detection model is adopted for element surface quality detection, multi-scale defects can be effectively processed, and the detection precision and the anti-interference capability are remarkably improved.

The invention discloses an Alzheimer disease risk prediction method based on feature fusion, a medium and equipment. The method comprises the following steps: firstly, acquiring an sMRI image, an FDG-PET image, a biomarker and intelligence score data of a target subject; then, sMRI and FDG-PET image data are respectively input into a three-dimensional convolutional neural network module, and a corresponding first image feature map and a corresponding second image feature map are extracted; secondly, inputting the two feature maps into a cross attention fusion module to obtain image fusion features; and inputting a U-shaped up-sampling network to segment a hippocampus region to obtain hippocampus features. And then, merging the image fusion features, the hippocampus features, the biomarker data and the intelligence score data, and inputting the merged data into an extreme learning machine for calculation, thereby obtaining an onset risk prediction result of the Alzheimer's disease. According to the method, by means of cross-modal data fusion, multi-modal data complementary information is extracted, and the accuracy of onset risk prediction can be effectively improved.

Disclosed herein are system, apparatus, device, method and / or computer program product embodiments for determining, in a remote deposit system, whether a deposit attempt is illegitimate (e.g. fraudulent). Whether the deposit attempt is illegitimate may be assessed based on one or more of the following processes: comparing location data to a location parameter determined from past deposits, comparing an image capture location with a deposit location, and analyzing image-of-image characteristics obtained through image processing to identify whether an image associated with the deposit attempt is an image of an image. In some embodiments, a remote deposit status related to acceptance of the deposit attempt may be provided in real-time

The invention discloses a visual control method for rapidly sorting magnets. The visual control method comprises the following steps that a flexible vibration disc stops vibrating; acquiring an image in the flexible vibration disc; the image identification sequentially comprises the following steps of: converting the image into a gray level image, and identifying a magnet in the image by adopting gray level identification; carrying out binarization and edge pixel extraction on the grayscale image in sequence, and screening out a pixel contour conforming to the contour shape of the magnet; through an image recognition algorithm based on deep learning, carrying out image recognition on the positions of the screened pixel contours so as to recognize good magnets in a preset posture; the position of the good magnet in the preset posture in the manipulator coordinate is determined; the manipulator sequentially arrives at the positions of the good magnets in the preset postures to grab the good magnets; and after the flexible vibration disc starts to vibrate for a period of time, returning to circulate. According to the invention, the working efficiency of identifying and sorting the magnets in the flexible vibration disc by the manipulator is improved.