7912 results about "Reference map" patented technology

The invention relates to the technical field of mode recognition, in particular to a transformer substation equipment temperature measurement method and system based on visible light guidance. Firstly, a visible light image, an infrared thermogram and vibration spectrum data are synchronously collected, a dynamic compensation coefficient matrix is constructed through illumination intensity analysis, the dynamic compensation coefficient matrix is applied to the infrared thermogram, and illumination interference compensation is achieved. And then, inputting the corrected infrared thermogram and visible light image into a pre-trained heterogeneous atlas matching model, and identifying the category and three-dimensional coordinates of the target equipment. And based on the equipment category information, calling a standard temperature field template in the digital twin model library, establishing a heat conduction path model in combination with the vibration spectrum data, and generating a temperature field prediction reference map of the equipment. And finally, through pixel-by-pixel deviation analysis, inputting the temperature deviation value, the image features and the vibration data into the probability graphic model, and outputting equipment fault information. The method can realize high-precision temperature measurement and fault diagnosis.

Wireless sensing using classifier probing and refinement is described. In one example, a described method comprises: computing output analytics by a classifier based on input data constructed based on raw measurement data; mapping each output analytics to a respective mapped outcome; identifying at least one reference input data each associated with a reference output analytics and a reference mapped outcome; each reference input data being one of the input data for the classifier for which a respective reference outcome is available and is different from the reference mapped outcome; and for each reference input data for the classifier: computing a respective plurality of perturbed output analytics by the classifier, generating selected perturbed input data based on the plurality of perturbed output analytics; and re-training the classifier based on the selected perturbed input data and the associated reference outcome.

This product relates to a graphical user interface (GUI) for displaying information, and is used, for example, to display information for the treatment of patients. The reference diagram showing the usage state shows the state in which the image transitions from left to right over time.

Systems and methods are described for video coding using generalized bi-prediction. In an exemplary embodiment, to code a current block of a video in a bitstream, a first reference block is selected from a first reference picture and a second reference block is selected from a second reference picture. Each reference block is associated with a weight, where the weight may be an arbitrary weight ranging, e.g., between 0 and 1. The current block is predicted using a weighted sum of the reference blocks. The weights may be selected from among a plurality of candidate weights. Candidate weights may be signaled in the bitstream or may be derived implicitly based on a template. Candidate weights may be pruned to avoid out-of-range or substantially duplicate candidate weights. Generalized bi-prediction may additionally be used in frame rate up conversion.

The invention relates to the field of image comparison, and discloses a multi-layer PCB alignment deviation detection system and method based on image comparison, and the method comprises the steps: obtaining high-resolution image data before and after lamination of a multi-layer PCB, carrying out the unified registration preprocessing of an original image through the combination of a multi-mode image fusion algorithm and a geometric distortion correction technology, and obtaining a multi-layer PCB alignment deviation detection result; constructing a standardized image registration input set; key alignment feature extraction is carried out on the image registration input set, and a multilayer structure graph model is constructed based on a graph neural network; in combination with the alignment reference map, dynamically adjusting an image comparison window and a search region by adopting a region attention mechanism and a local adaptive matching algorithm, and constructing an alignment deviation mapping map; constructing a deviation evolution model by using a time sequence behavior recognition network according to the constructed alignment deviation mapping graph and historical process deviation data; and performing comprehensive evaluation on the image registration input set based on the deviation evolution model and the generated early warning information. The method has the advantage of improving the accurate detection level.

The invention relates to the technical field of industrial machine vision detection and image processing, in particular to an automobile part production mold surface smoothness detection system based on image enhancement, which comprises a data acquisition module used for acquiring an original grayscale image of the surface of an automobile part mold; performing low-pass filtering processing on the original grayscale image to eliminate imaging thermal noise; the manifold reconstruction module is used for constructing a structure tensor field; reversely deducing a pseudo-curvature field of the mold surface; the adaptive enhancement module is used for generating a corrected image; constructing a texture orthotropic diffusion model; generating a texture reconstruction reference image; the surface metering module is used for calculating the difference between the corrected image and the texture reconstruction reference image and generating a defect saliency image; calculating the surface roughness value of the mold surface; according to the method, the problem that design textures and abnormal scratches are difficult to distinguish in the prior art is effectively solved, and the technical bottleneck that micro defects are easily missed in a complex geometric structure in traditional visual detection is overcome.

The invention relates to a multi-stage filtering road spilled object detection method based on dynamic difference analysis, which is suitable for automatic identification of unstructured foreign matters in video monitoring. The method comprises the following steps: firstly, extracting a reference image road mask, eliminating vehicle and pedestrian interference by using YOLOv8 detection, and extracting a motion candidate area through a frame difference method and background modeling; and then context expansion and super-resolution reconstruction are carried out on the candidate region, the candidate region is converted into an HSV space, multi-dimensional features such as color similarity, structural similarity and shadow determination are synthesized for screening, false detection is further removed in combination with inter-frame time sequence consistency, and finally a stable detection result is output. The method provided by the invention has the advantages of strong anti-interference capability, high adaptability, high detection precision and the like, and is suitable for the intelligent recognition task of the expressway thrown objects in a complex environment.

The invention discloses a building construction scheme multi-model management system and method, and belongs to the technical field of building construction management. The system is composed of four subsystems based on a building construction scheme natural language processing model: a construction industry multi-modal professional knowledge question-answering system, a construction industry professional document compiling system, a construction industry multi-modal retrieval system and a construction scheme content auditing system. The construction industry professional document compilation system adopts a multi-mode diffusion large model technology, so that the built construction image generation system can intelligently respond to a text demand input by a user, automatically generate a building construction image matched with the text demand, or perform style conversion on a building image uploaded by the user, and automatically generate a construction image matched with the text demand. According to the method, the building images meeting specific requirements are created, instant building construction reference drawings are provided for users, the workload of the users in the drawing process is greatly reduced through the one-key image generation function, and the working efficiency in the building construction scheme writing stage is remarkably improved.

Methods, apparatuses, and non-transitory computer-readable storage media are provided for video coding. In one method, a decoder derives a first and a second reference pictures for a current coding block; the decoder derives a first and a second predictor samples based on a motion vector associated with the first reference picture using a motion compensation process from the first reference picture; the decoder determines whether the first and the second predictor samples are out-of-boundary (OOB), and in response to determining the first or the second predictor sample is OOB, the decoder replaces the first or the second predictor sample that is OOB with a first or a second alternative predictor sample; and the decoder generates the final prediction sample by averaging sample values of the first predictor sample and the second predictor sample.

Aspects of the disclosure provide a method and an apparatus for video decoding. The apparatus includes processing circuitry that determines motion information of a current block. The motion information indicates one or more reference blocks of the current block. If a motion information constraint indicates that the one or more reference blocks are within picture boundaries of respective one or more reference pictures, the processing circuitry reconstructs the current block based on the one or more reference blocks. If a first motion vector (MV) points from a region in the current block to a first reference region of a first reference block that is outside a picture boundary of a first reference picture, the processing circuitry determines a first clipped MV pointing from the region to an updated first reference region by clipping the first MV where the updated first reference region is within the picture boundary.

Wireless sensing using classifier probing and refinement is described. In one example, a described method comprises: computing output analytics by a classifier based on input data constructed based on raw measurement data; mapping each output analytics to a respective mapped outcome; identifying at least one reference input data each associated with a reference output analytics and a reference mapped outcome; each reference input data being one of the input data for the classifier for which a respective reference outcome is available and is different from the reference mapped outcome; and for each reference input data for the classifier: computing a respective plurality of perturbed output analytics by the classifier, generating selected perturbed input data based on the plurality of perturbed output analytics; and re-training the classifier based on the selected perturbed input data and the associated reference outcome.

This document describes methods and systems for vehicle localization based on radar detections. Radar localization starts with building a radar reference map. The radar reference map may be generated and updated using different techniques as described herein. Once a radar reference map is available, real-time localization may be achieved with inexpensive radar sensors and navigation systems. Using the techniques described in this document, the data from the radar sensors and the navigation systems may be processed to identify stationary localization objects, or landmarks, in the vicinity of the vehicle. Comparing the landmark data originating from the onboard sensors and systems of the vehicle with landmark data detailed in the radar reference map may generate an accurate pose of the vehicle in its environment. By using inexpensive radar systems and lower quality navigation systems, a highly accurate vehicle pose may be obtained in a cost-effective manner.

An example device for decoding video data includes a memory configured to store video data; and one or more processors configured to: decode data representing an initial motion vector for a current block of the video data, the initial motion vector having integer-motion vector difference (MVD) precision; determine a search range around a reference area identified by the initial motion vector in a reference picture; perform a template matching search process in the search range to identify a best matching region; determine error values for neighboring pixels to the best matching region; use the error values for the neighboring pixels to perform a model-based fractional-pixel motion vector refinement to derive motion vector difference values; apply at least one of the motion vector difference values to the initial motion vector to determine a refined motion vector for the current block; and decode the current block using the refined motion vector.

The invention discloses a transformer substation positioning and navigation method and system integrating positioning and visual auxiliary positioning. The method comprises the following steps: establishing a background electromagnetic field distribution baseline graph associated with a three-dimensional reference map; electromagnetic field data of the transformer substation in an emergency response mode is collected through the unmanned aerial vehicle, and the abnormal field intensity of a space electromagnetic field and a fault source pointing vector pointing to a fault source are calculated; constructing a risk adaptive elliptical forbidden zone; calculating a passage cost index Cto of the unmanned aerial vehicle passing through each three-dimensional grid in the three-dimensional reference map by using the fault source pointing vector and the risk adaptive elliptical forbidden zone; and searching a path which is from the current position of the unmanned aerial vehicle to a preset target point, bypasses the risk adaptive elliptical forbidden zone, faces the fault source and has the lowest total passing cost index Cto by adopting a preset path search algorithm. According to the method, the risk self-adaptive elliptical forbidden zone is constructed and is used as the three-dimensional grid forbidden assignment processing, so that the dynamic global path avoidance of the sudden dangerous zone is realized.

The invention discloses a large-area crop rapid mapping method integrating multi-source remote sensing data, and the method comprises the steps: obtaining a multi-source remote sensing satellite image, carrying out the preprocessing, amplifying a sample based on the spectrum similarity of a field collection sample point and an amplification sample point, and screening the amplification sample point based on a dynamic time warping distance; drawing a crop distribution reference map of the research subarea in cooperation with multi-source data; and based on the crop distribution reference diagram of the research sub-region, constructing a research region sub-pixel drawing sample set and predicting a sub-pixel distribution diagram of each crop type. According to the method, existing field collection sample points are fully utilized, the drawing potential of multi-source remote sensing data and different classifiers is explored, and crop sub-pixel rapid drawing of a large-scale research area is achieved.

ObjectA video coding and decoding apparatus that can enhance coding efficiency is provided.SolutionA video decoding apparatus includes an OOB determination unit configured to determine whether a reference block is a target of OOB processing by comparing coordinates of the reference block with coordinates of a picture, and an OOB mask derivation unit configured to derive mask data indicating whether a pixel is available by comparing coordinates of the pixel included in the reference block with the coordinates of the picture. The OOB determination unit determines whether the reference block is the target of the OOB processing based on presence or absence of processing to be applied to a reference picture including the reference block.

The invention relates to the technical field of printed matter quality detection and computer vision and the technical field of artificial intelligence systems in the production field, in particular to a color box printed matter printed pattern visual detection algorithm. The invention discloses a visual detection algorithm for a printing pattern of a color box printed matter. The visual detection algorithm comprises the following steps of image acquisition, preprocessing, feature extraction, reference comparison, defect evaluation and defect classification. According to the scheme, the accuracy and the real-time performance of complex printing pattern defect detection are improved. A light-weight multi-scale attention convolutional neural network and a self-learning mechanism are combined, defects in various printing patterns such as block colors, fine characters and graph gradient are effectively detected, and human intervention and misjudgment are reduced. A defect saliency map is generated through color normalization, geometric correction preprocessing and reference map comparison, an online misjudgment cache and incremental learning strategy is introduced, self-adaptive optimization of a model along with time is kept, and real-time high-precision quality monitoring of an offset printing color box production line is achieved.

The invention provides an image generation method based on style feature injection, which can efficiently migrate the spatial layout and color texture of a style reference image on the basis of a text image. According to the method provided by the invention, on the basis of a Stable Diffusion text map, the spatial layout and the preliminary style of an image are learned by utilizing the capability of binding features of Dreambooth, and then attention injection is executed to strengthen color features and detail textures. Therefore, the method provided by the invention has high generalization in various styles, does not need tedious parameter adjustment for a single specific style, and is highly sensitive to context features such as composition, texture, color and the like. In addition, the model needs less data, only 3-5 training images are needed, only one attention reference image is needed in the reasoning process, additional training is not needed, and the robustness is very high. Therefore, the style image generation method provided by the invention can adapt to various different styles so as to have a higher degree of freedom in a personalized task.

The invention provides a BIM information integration-based mixed structure building whole-process management method, which comprises the following steps: calling a house type model in a BIM building model in response to house type selection information of a user side, and performing customization processing on the house type model according to customization information of the user side to obtain a customized model which has a plurality of virtual point locations; controlling an acquisition device to perform acquisition according to the entity position information corresponding to the virtual point location to obtain real-time data, and generating automatic adjustment information according to comparison processing of the customized reference map of the virtual point location and the real-time data; receiving completion information of the management end, calling management data of the position information of each entity based on the completion information, and cutting and splicing the management data according to a change cutting strategy to obtain initial backtracking data corresponding to each standard wall body area; and segmenting the wall body region of the real-time wall body region in the initial backtracking data to obtain element backtracking data corresponding to each standard wall body region, and generating a customized backtracking tree according to the management data and the element backtracking data.

The invention discloses a power transmission line small sample abnormal data generation method and system based on a diffusion model and feature migration, and belongs to the technical field of abnormal detection. The problem that stable and high-fidelity abnormal data can be generated only when the demand quantity of abnormal samples is much larger than that of actually obtained abnormal samples is solved. The method comprises the steps that an abnormal defect library and an equipment main body library are constructed based on defect reference images in a data set and corresponding labels, and the data set at least comprises one defect reference image of each type; training an abnormal defect identification baseline model based on the data set and verifying to obtain a low-quality image; comparing the abnormal defect library and the equipment main body library with low-quality images by using an image comparison technology to obtain an abnormal defect reference image and a base image to be generated; generating a to-be-migrated region mask based on the to-be-generated base map; and based on the to-be-generated base map and the to-be-migrated region mask, using a diffusion model to migrate the abnormal region features of the low-quality image to the to-be-generated base map for anomaly generation. The method is used for generating the small sample abnormal data of the power transmission line.

Example devices, methods, and computer-readable media are disclosed. An example device includes one or more processors configured to determine a reference picture list for a current block of a current picture of the video data. The one or more processors are configured to determine that a reference picture of a collocated block is listed in the reference picture list for the current block, the collocated block being collocated with the current block in a collocated picture. The one or more processors are configured to select, in a condition where the reference picture of the collocated block is listed in the reference picture list for the current block, a reference picture for the current block to be the reference picture of the collocated block. The one or more processors are configured to and encode or decode the current block based on the reference picture for the current block.

An example device includes one or more processors configured to determine a first search area in a first reference picture for a current block of the video data. The one or more processors are configured to determine a first initial reference block in the first search area. The one or more processors are configured to apply a local illumination compensation model to the first search area to generate a refined first search area. The one or more processors are configured to apply template matching to the refined first search area to determine a first candidate motion vector having a lowest template matching cost for the refined first search area. The one or more processors are configured to decode the current block based on the first candidate motion vector.

A novel knowledge distillation method from binocular parallax to monocular depth comprises the following steps: S1, training a parallax depth conversion module: inputting first training data into a pre-trained binocular stereo parallax teacher model to obtain a parallax map; the first training data comprises a left eye color image and a right eye color image; inputting the disparity map and the original disparity reference map into a disparity depth conversion module to obtain a pseudo label depth map; calculating a loss function according to the pseudo-label depth map, and updating parameters of a parallax depth conversion module; s2, mixing the pseudo-label depth map output by the parallax depth conversion module with the original true label depth map to obtain a mixed label depth map; s3, training a monocular depth estimation student model: training the monocular depth estimation student model through the second training data; the second training data comprises a mixed label depth map and a corresponding original reference map, and the method can achieve the training on a data set with a lower data size, and improves the global precision.

The invention relates to the technical field of image processing, and provides a personalized image generation method and device, electronic equipment and a storage medium, and the method comprises the steps: associating image data, text description and instance segmentation masks through a cross-modal automatic labeling system, and generating an image-text-instance segmentation mask associated data set; constructing a corresponding mixed training data set based on the associated data set, and performing data enhancement on the mixed training data set; performing model training on a preset diffusion model based on the mixed training data set after data enhancement; and generating a target image through the trained diffusion model by adopting a hybrid guidance strategy of time step size control. According to the method, the problems that in the prior art, the generation effect is not ideal, user operation is complex, and the generated image and the reference image are inconsistent in feature can be solved, and high-quality, flexible and accurate personalized image generation is achieved.

1. The name of the product of this design: Top of the underground solar-powered road stud (LA‑4A). 2. Purpose of the product of this design: A luminous device used in the field of traffic safety, acting as an underground solar luminous road stud. When the underground solar luminous road stud is installed on the road and used as a traffic safety product, its lower part is buried under the road surface or the ground, and its top is exposed on the road surface or the ground. The local use of this design product: serving as the top of the buried solar luminous road stud, including the protective ring cover and the transparent luminous part of the top shell. 3. The design highlights of this appearance design product lie in the product’s shape, pattern and their combination. 4. The picture or photo that best illustrates the key points of the design: Main view of Design 1. 5. Designate Design 1 as the base design. 6. Other situations that require explanation: Reference drawings: Attached are the front view reference drawings, bottom view reference drawings, and three-dimensional reference drawings of Design 1-Design 9, assuming that the top shell is opaque. 7. Other situations that require explanation: Description of the changed status: Part A in the main view reference diagram of Design 1-Design 9 is the corresponding transparent material top shell. 8. Other situations that need explanation: This design is a partial design. The part not covered by the red semi-transparent part in the view is the part requiring protection, and the part covered by the red semi-transparent part is defined as the non-protected part.

The invention provides a room decoration style migration method based on semantic and style information guidance. The method comprises the following steps: firstly, extracting semantic analysis features of an original room picture, then taking the original room picture, a reference style picture and the semantic analysis features as training samples together, and taking a room picture with a changed style as a label to construct a training set; a room picture feature and a reference picture feature are extracted by using a generator network, a normalization process is adjusted by using the reference picture feature through a double-branch normalization module to obtain space structure information and texture detail information, and a room image with a reference style is finally output through AFF feature fusion. And a discriminator network is used to discriminate the generated image by taking the label as a reference, and network training is completed. And finally, inputting the original room picture, the semantic analysis characteristics of the original room picture and the reference style picture into the trained generator network, generating a room image with a reference style, and completing decoration style migration.

The invention discloses an intelligent building decoration design method based on deep learning, and the method comprises the following steps: S1), employing a monocular camera to shoot pictures of a building at all angles, and obtaining an original picture; s2) extracting keywords, and making cue words; s3) building decoration data collection; s4) performing data screening and preprocessing; s5) customizing a loss function, and training the diffusion model to obtain a trained diffusion model; s6) inputting the original image into the trained diffusion model to generate a preliminary image; inputting the preliminary image and the cue word into a pre-trained conditional generative adversarial network to obtain a preliminary design drawing; and S7) inputting the preliminary design drawing into a pre-trained variational auto-encoder to obtain an architectural decoration design reference draw.According to the intelligent architectural decoration design method based on deep learning, through the design of the self-defined loss function and the dynamic weight, in combination with the deep learning model, the image is automatically processed, and the design reference drawing is generated, so that the working efficiency is improved.

The invention provides a method and a device for generating an inter-frame color-imitating pattern in FRC. The method comprises the following steps: determining a color depth difference value between a color depth to be displayed and a color depth of a display screen; wherein the to-be-displayed color depth is higher than the color depth; according to the color depth difference value, determining the size and the type of the color-imitated pattern, and screening out a key type from the types; according to the color depth difference value, the color-imitating pattern corresponding to each key type is divided, and a plurality of basic patterns are obtained; determining a reference pattern from the basic pattern, dividing the reference pattern to obtain a plurality of unit patterns, and transforming and splicing the unit patterns to obtain a color-imitating pattern of each frame; wherein the number of the reference patterns is the same as that of the key types. According to the scheme, the chip area occupied by the stored color-imitated patterns is reduced, meanwhile, more kinds of color-imitated patterns can be flexibly generated, and the color shaking effect is improved.

The embodiment of the invention provides an information processing method and device, a storage medium and a program product. In the embodiment of the invention, the picture generation instruction can be directly initiated for the first picture displayed on the first page of the target application, the picture backstepping model can be automatically called based on the picture generation instruction to obtain the picture generation cue word and the picture generation parameter information of the first picture in a backstepping manner, and the first page is automatically skipped to the second page; in addition, a plurality of corresponding picture generation information items on the second page can be automatically filled with the picture generation prompt word, the picture generation parameter information and the first picture serving as the reference picture, the picture generation process is simplified in the automatic process, and the picture generation efficiency is improved. Furthermore, on the basis of the information in the information item, the image generation model is called to generate at least one second image similar to the first image in style, so that the image generation efficiency and quality are further improved, and the style similarity between the second image and the first image is improved.

The embodiment of the invention provides a special effect template generation method and device, electronic equipment and a storage medium, special effect generation data is obtained by responding to a first operation, the special effect generation data comprises configuration parameters representing a special effect style of a self-defined special effect, and the configuration parameters comprise a first prompt word and / or a first reference graph; displaying an effect picture of the user-defined special effect according to the special effect generation data and the user personalized image; in response to the second operation, the effect picture and the construction data corresponding to the effect picture are packaged, a special effect template of the user-defined special effect is generated, the effect picture is used for displaying the visual effect of the user-defined special effect based on the user personalized image on the resource platform, and after the special effect template is called, a corresponding special effect image is generated through the construction data. The flexibility and convenience of creating the self-defined special effect by the user and the propagation attribute of the special effect template are improved.