Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2176results about How to "Improve visual effects" patented technology

Automatic driving vehicle trajectory planning method

The invention relates to an automatic driving vehicle trajectory planning method, which comprises the following steps of: extracting comprehensive spatio-temporal information representation of a driving scene from automatic driving multi-modal data by adopting an end-to-end branch, and predicting and generating a trajectory sequence predicted by a vehicle in a future set time period; a visual language model branch is adopted to embed visual features related to the text instruction into a large language model, and a plurality of different track sequences in a future set time period are obtained through prediction; and fusing the trajectory sequences output by the two branches according to the loss value and the danger situation of the current driving scene to obtain a final planning trajectory. Compared with the prior art, the method has the advantages of high safety and reliability.
Owner:TONGJI UNIV

CAD and BIM coordinate automatic conversion method and system based on coordinate mapping

The invention relates to the technical field of coordinate conversion, in particular to a CAD and BIM model coordinate automatic conversion method and system based on coordinate mapping, and the method comprises the following steps: extracting CAD building two-dimensional coordinates input by reference to a building drawing, constructing an initial two-dimensional triangular mesh, extracting key geometric feature points of a building, and combining the floor height parameter and corner information of the building to obtain a CAD and BIM model coordinate automatic conversion model; and mapping the two-dimensional grid to a three-dimensional coordinate space to generate initial building three-dimensional point cloud data. According to the method, a high-quality initial triangular mesh is constructed through a Delaunay triangulation algorithm, coordinate information of a sparse position is accurately captured, a Poisson surface reconstruction technology is combined, global curved surface fitting and smoothing processing are performed on point clouds of a sparse region, and density compensation and precision improvement of coordinate point distribution are realized. According to the optimization mode, the problem of model precision loss is effectively relieved in complex scenes such as building corners, special-shaped spaces and floor height changes.
Owner:北京北投智慧城市科技有限公司

Denoising diffusion model driven texture enhanced infrared and visible light image fusion method and system

The invention discloses a de-noising diffusion model driven texture enhanced infrared and visible light image fusion method and system, and relates to the technical field of image processing and computer vision. The method comprises the following steps: performing multi-scale space-time modeling on infrared and visible light images; enhancing high-frequency texture features of the infrared image through an edge detection convolutional network; based on a bidirectional multi-scale convolution module and a bidirectional attention fusion module, capturing a remote dependency relationship and encoding multi-scale information to ensure full utilization of global information and accurate capture of local details; and optimizing the structural fidelity and color intensity distribution of the fusion result based on an adaptive structural similarity loss function and multi-channel intensity and texture loss so as to improve the quality of the fused image. According to the method, the process of diffusion feature extraction is enhanced by fusing the de-noising diffusion model and the texture enhancement strategy. Meanwhile, a bidirectional multi-scale convolution technology and an attention mechanism are combined, so that comprehensive utilization of global information and accurate mastering of local details are ensured.
Owner:ZHEJIANG SCI-TECH UNIV

Monitoring video splicing method and device, equipment and storage medium

The invention relates to the technical field of video stitching, and discloses a monitoring video stitching method, device and equipment and a storage medium, and the method comprises the steps: carrying out the video framing of a monitoring video collected by a monitoring terminal, and obtaining a plurality of target video frames; performing human shape detection to obtain a human shape detection result; aligning and cutting a face region in the human shape detection result to obtain a standardized face image, and extracting a face feature vector; performing motion prediction and trajectory extrapolation to obtain a multi-target human shape tracking result; inputting the multi-target human shape tracking result into a distributed computing framework for task allocation and cross-node feature matching to obtain a global human shape tracking result; and performing double-flow network processing on the plurality of target video frames according to the global human shape tracking result, calculating to obtain video stitching parameters, and performing stitching operation on the plurality of target video frames to obtain a stitched video, thereby effectively improving the quality and visual effect of the stitched video.
Owner:SHENZHEN ANKED SHITONG ELECTRONICS CO LTD

Self-adaptive adjusting method and system for content refresh rate of LED display screen

The invention relates to the technical field of display screen refresh rate control, in particular to a self-adaptive adjusting method and system for the content refresh rate of an LED display screen. The method comprises the following steps: identifying an LED display screen image; detail convolution reconstruction is carried out on the LED display screen image, and dynamic region division is carried out, so that a dynamic region image and a static region image are generated; performing dynamic texture optical flow tracking on the dynamic region image, and performing optical flow change trend evolution so as to generate a dynamic optical flow trend feature map; performing dynamic gradual change smooth optimization on the dynamic area image and the static area image according to the dynamic optical flow trend feature map, and constructing a dynamic gradual change refresh rate image; identifying a current user eyeball monitoring image based on a display screen camera; and performing user flicker frequency sensitivity analysis on the eyeball monitoring image of the current user to obtain a dynamic refresh rate change amplitude. According to the invention, the refresh rate of the display screen is adjusted adaptively and efficiently according to a real-time environment, and the visual experience of a user is improved.
Owner:VISION JUMP (SHENZHEN) TECH CO LTD

Image-text retrieval method based on comparative learning and modal fusion

The invention discloses an image-text retrieval method based on comparative learning and modal fusion. The method comprises the following steps: giving an original image-text pair; the method comprises the following steps of: 1, respectively carrying out local coding and global coding on an input image based on a target detection model and a deep residual network, and coding an input text based on a pre-training language model; 2, generating more matched image-text pairs (positive sample pairs) and mismatched image-text pairs (negative sample pairs) by adopting a diversified data augmentation strategy; 3, establishing cross-modal hierarchical semantic fusion of the image and the text, and bridging a semantic gap between a visual mode and a language mode; 4, measuring the semantic similarity degree between the image and the text; and 5, based on positive and negative sample pairs generated by data augmentation, carrying out model training through comparative learning. The method solves the problem that an existing image-text retrieval method is insensitive to fine granularity difference between modes.
Owner:NANJING UNIV

Lottery store violation abnormity identification method and system

The invention provides a lottery store violation abnormity identification method and system, and relates to the technical field of image identification, and the method comprises the steps: collecting multi-source heterogeneous image data in real time through an edge computing device; preprocessing the collected multi-source heterogeneous image data to form a stereo image data set containing space, depth and thermodynamic information; constructing a multi-task deep learning model, wherein the multi-task deep learning model comprises a face recognition module, a behavior analysis module and an environment detection module; inputting the three-dimensional image data set into the trained multi-task deep learning model, and executing face recognition, behavior analysis and environment detection tasks at the same time; based on an execution result of the multi-task deep learning model, generating a violation score by applying a fuzzy comprehensive evaluation method, and weighting by considering historical violation records; and generating a lottery store site investigation plan based on the violation scoring result.
Owner:GUANGDONG CAIHUI INTELLIGENT TECH CO LTD

Diffusion model LoRA fine tuning optimization method and system based on CLIP loss and perception loss

The invention provides a diffusion model LoRA fine tuning optimization method and system based on CLIP loss and perception loss, and the method comprises the steps: 1, dynamically adjusting the weights of the CLIP loss and the perception loss in combination with the CLIP loss and the perception loss in a LoRA fine tuning process; 2, calculating the semantic similarity between the denoised intermediate image and the target text by using a CLIP model, and optimizing the noise prediction capability of a diffusion model according to the similarity difference; step 3, calculating the difference between the intermediate image and the target image in the feature space by using perception loss, optimizing the noise prediction capability of the diffusion model, and improving the visual quality and detail fidelity of the generated image; and step 4, adjusting whether to start CLIP loss and perception loss or not according to the training progress. By introducing the CLIP loss, the model can better align the image and the text in the fine tuning training process, so that the generated image better conforms to the description of the text prompt.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Cross-domain face anti-counterfeiting detection method and device based on multi-modal text enhancement

The invention discloses a cross-domain face anti-counterfeiting detection method and device based on multi-modal text enhancement, and relates to the technical field of network information security, and the method comprises the steps: inputting two types of description texts into a pre-trained text encoder, and extracting text type features representing reality / deception, inputting the image into a pre-trained visual encoder to extract visual features; a trainable text prompt is added to each layer of the text encoder, a trainable visual prompt is added to each layer of the visual encoder, and the visual prompt of each layer of the visual encoder is obtained by converting the text prompt of the current layer through a full connection layer; and embedding the PFT module and the TIM module into a middle layer of each layer of a text encoder and a visual encoder to realize feature interaction fusion, obtaining cosine similarity and masks between text category features and visual features, and performing face true and false classification. Based on the PFT module and the TIM module, modal feature interaction is completed in the feature extraction process at the same time, and the cross-domain detection performance is improved.
Owner:XIAMEN UNIV

Environment-aware intelligent lighting control system

The invention relates to an intelligent lighting control system with environmental perception, and aims to enhance the visual expressive force of artworks and improve the interactive experience of audiences by accurately controlling the lighting condition in an exhibition hall. The system comprises a system environment data acquisition unit, an intelligent control unit, a self-adaptive illumination execution unit and an interactive illumination adjustment unit. The environmental data acquisition unit is used for comprehensively monitoring environmental conditions in the exhibition hall. The intelligent control unit generates an optimized lighting strategy according to the collected data and artwork protection and display requirements. The self-adaptive illumination execution unit comprises a plurality of LED lamp sources capable of being independently adjusted, and light intensity, color temperature and light beam angles are adjusted according to the strategy of the control unit. And the interactive illumination adjusting unit is used for further optimizing the illumination setting. According to the system, the modern sensing technology and intelligent control are comprehensively utilized, an innovative solution is provided for art museums and museums, human cultural heritage is protected and displayed through science and technology, and meanwhile the sense of participation and educational value of the public are enhanced.
Owner:DOLIGHT OPTOELECTRONICS TECH CO LTD

Carton printing defect detection method and system based on visual identification

The invention relates to the technical field of image data processing, in particular to a carton printing defect detection method and system based on visual identification, and the method comprises the steps: obtaining a carton image through an image collection device, calculating the gray feature quantity of a pixel point based on the gray value of each pixel point in the image and the gray difference in the neighborhood of the pixel point, and calculating the gray feature quantity of the pixel point; the gray scale is used for reflecting gray scale change conditions of local areas; the change degree of the pixel points is calculated based on the gray feature quantity, the change degree represents the clutter degree of the pixel points, and a change degree co-occurrence matrix is constructed to describe the joint distribution characteristic between different change degrees. Calculating the defect degree of each pixel point according to the change degree co-occurrence matrix; the defect degree of each pixel point is calculated, and the pixel points with the defect degrees larger than a set threshold value are responded to be defective pixel points. The problem that the accuracy of carton printing defect detection is not high is solved.
Owner:GUANGZHOU LIANWANG PAPER

Image enhancement method and system of vehicle-mounted image sensor

The invention relates to the field of image enhancement, in particular to an image enhancement method and system of a vehicle-mounted image sensor. The method comprises the following steps: acquiring driving record images of a vehicle at multiple angles; dynamic scene self-adaptive exposure adjustment is carried out on the driving record images of the vehicle at the multiple angles, so that multiple self-adaptive exposure driving images are obtained; carrying out deep network noise identification on the plurality of adaptive exposure driving images, and carrying out dynamic filtering and noise reduction on sub-images one by one so as to generate a plurality of filtering and noise reduction optimized images; carrying out image texture analysis on the plurality of exposure sub-images, and carrying out texture distortion reconstruction to construct a plurality of texture reconstruction images; and road object visual identification is carried out on the plurality of texture reconstruction images, and adaptive contrast enhancement processing is carried out, so that a plurality of detail contrast enhancement images are constructed. According to the invention, a high-definition and stable panoramic vehicle-mounted image is realized.
Owner:DONGGUAN TSIMSAFE ELECTRONICS TECH

Three-dimensional model data management system and method for engineering surveying and mapping

The invention relates to the technical field of data processing and analysis, in particular to a three-dimensional model data management system and method for engineering surveying and mapping. The method comprises the following steps: acquiring engineering surveying and mapping data; preprocessing the engineering surveying and mapping data to obtain standard engineering surveying and mapping data; performing multi-dimensional feature recognition on the standard engineering surveying and mapping data to obtain multi-dimensional surveying and mapping feature data; performing key engineering surveying and mapping information extraction on the multi-dimensional surveying and mapping characteristic data to obtain key engineering surveying and mapping information; performing association analysis on the multi-dimensional surveying and mapping characteristic data and the key engineering surveying and mapping information to generate multi-dimensional engineering surveying and mapping associated data; monitoring the engineering surveying and mapping data in real time to obtain engineering surveying and mapping real-time monitoring data; through a data processing technology, a geographic information system technology and a three-dimensional mapping technology, integrated management of multi-source heterogeneous data is realized, and dynamic updating management of the data is realized, so that the presentation accuracy of the engineering surveying and mapping three-dimensional model is improved.
Owner:JINCHENG HEAVY IND MASCH (DALIAN) CO LTD

Robot visual touch perception method and system based on transformer and comparative learning

The invention discloses a robot visual touch sensing method and system based on transformer and comparative learning, and belongs to the technical field of robots. According to the method, an enhanced Swin Transform model is introduced to serve as a sensing model, the enhanced model takes Swin Transform as a backbone network, a coordinate attention mechanism is introduced into the backbone network, global information is extracted through a sliding window attention mechanism of the backbone network, local feature extraction is enhanced through the coordinate attention mechanism, and the global information is extracted through the sliding window attention mechanism. The global and local features in the visual and tactile data can be effectively extracted and fused. According to the enhanced Swin Transformer model, in-modal comparative learning and inter-modal comparative learning are specifically performed through multi-modal comparative learning training in a pre-training stage of an earlier stage, and richer and more accurate discrimination features are generated, so that the intelligent sensing and operation capability of the robot to the environment is effectively improved. According to the method, the features can be effectively extracted in multi-modal data fusion, and deeper multi-modal data fusion is realized by utilizing the correlation and synergistic effect of the features among different modals.
Owner:SHENZHEN INST OF ADVANCED TECH

Interactive projection optimization method for exhibition hall

The invention relates to an interactive projection optimization method for an exhibition hall, and the method comprises the following steps: before projection is started, sensing the change of ambient light in the exhibition hall through a sensor, and evaluating the illumination conditions of different regions; acquiring a spatial layout in the exhibition hall by using a spatial modeling technology, and identifying wall surface and object shielding information of a projection area; gestures, actions and watching directions of audiences are captured in real time through a camera or infrared induction equipment; dynamically adjusting the projection content according to the action and position of the audience; comprising the following steps: when an audience approaches a certain exhibit, amplifying related projection content or switching to a detailed display mode; collecting behavior data of each audience including stopping time and interaction times of the audience in front of an exhibit; interest points of audiences are predicted through a machine learning model, and projection content related to audience interests is recommended; and adjusting the brightness and color parameters of each projector according to the actual projection area and content of each projection device.
Owner:北京三月雨文化传播有限责任公司

Method for rendering large-scale point cloud at web end

The invention discloses a method for rendering a large-scale point cloud at a web end, and belongs to the technical field of large-scale point cloud rendering, and the method comprises the steps: S1, carrying out the data preprocessing of point cloud data, and carrying out the octree division of the whole point cloud; s2, on the basis of octree division, performing Lod hierarchical data division on leaf nodes of the whole octree; s3, data which needs to be rendered currently are screened out from the octree through view cone cutting; s4, high-level data and low-level data are separated from the screened data needing to be rendered, the low-level data are used for real-time rendering, and the high-level data are used for non-real-time rendering; and S5, combining the real-time rendering result and the non-real-time rendering result, and outputting all rendering results. According to the method, a similar double-buffer structure is used, and large-scale point clouds can be rendered in a real-time and non-real-time mixed mode at a web end.
Owner:LEICA GEOSYSTEMS (SHANGHAI) CO LTD

Intelligent rendering method and system for realizing animation picture

The invention relates to the field of animation rendering, and provides an intelligent rendering method for realizing an animation picture, which comprises the following steps of: firstly, collecting an initial animation picture, identifying a scene of the initial animation picture, analyzing an animation effect demand, carrying out picture analysis in combination with style characteristics to obtain a scene picture element, and detecting an element type to determine a special effect demand degree; a special effect rendering scheme is generated; an adaptive color mode is queried; visual atmosphere parameters are evaluated to calculate a color adjustment amount; a color optimization strategy is constructed; and determining a rendering target based on the special effect rendering scheme, the color optimization strategy and the visual angle adjustment plan, optimizing a picture to obtain a record, monitoring the rendering quality, and finally generating an intelligent rendering scheme. According to the invention, the efficiency and quality of animation picture rendering can be improved.
Owner:SHENZHEN MENGXIANG CULTURE COMM CO LTD

Cascade discrete wavelet multiband decomposition attention image denoising method and device

The invention discloses a cascaded discrete wavelet multiband decomposition attention image denoising method and device, and the method comprises the following steps: building a CDW-MDA image denoising network which employs an encoder-sub-network-decoder structure; inputting a noise image and extracting high and low frequency band characteristic patterns under multiple scales; global and local key feature information is enhanced; evaluating the importance of texture detail components and weighting noise features of different frequency bands; enhancing selective features of the processed high and low frequency band feature maps, and fusing the high and low frequency band feature maps; and converting the fused high-low frequency band feature map to obtain a residual image, and finally obtaining a target image. According to the image denoising method, clearer texture details can be generated, blurring is avoided, and more texture detail information is reserved in the restored image; noise can be reduced while image feature textures are kept, edge information is reserved, and a better visual effect is achieved.
Owner:SOUTHWEAT UNIV OF SCI & TECH +1

Infrared and visible light image fusion method for improving image details and textures

The invention relates to the technical field of digital image processing, and provides an infrared and visible light image fusion method for improving image details and textures, and the method comprises the steps: splicing the feature vectors of an original infrared image and an original visible light image; performing initial feature map extraction of different spatial scales on the obtained source image features by adopting a plurality of serial residual parallel visual Mama network models; taking the initial feature map obtained by the last iteration as a basic feature map, and identifying fusion feature information of the basic feature map by adopting a multi-channel parallel visual Mama network model; expanding the fusion feature information to the initial feature maps of different spatial scales to obtain initial fusion feature maps of different spatial scales; performing up-sampling on the initial fusion feature map on each spatial scale to the resolution of the original infrared image and generating a fusion image; and performing iterative optimization according to the feature loss of the fused image and the original image. According to the invention, the detail definition and texture expression in the fused image can be obviously improved.
Owner:GUANGZHOU NANSHA DISTRICT BEIKE PHOTON SENSING TECH RES INST +1

Small target detection method, system and device for medical image and storage medium

The invention discloses a small target detection method, system and device for a medical image and a storage medium, and the method comprises the steps: constructing a small target detection model of a bronchial medical image, which comprises a backbone network, a neck network and a prediction network, and introducing a residual network and a cavity space convolution pooling pyramid into the backbone network; introducing a global attention module into the neck network; inputting the preprocessed bronchial medical image into the backbone network, performing detail feature supplementation by adopting a residual network and enhancing a receptive field by adopting a void space convolution pooling pyramid to obtain feature maps of various scales output by the backbone network; inputting the multi-scale feature maps into a neck network, and performing global information enhancement by adopting a global attention module to obtain multi-scale tensor data output by the neck network; and carrying out feature fusion on the tensor data of multiple scales by adopting a prediction network, and carrying out small target detection on the fused features. According to the invention, the accuracy of small target detection can be improved.
Owner:CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Multi-focus image fusion method based on multilayer semantics and multi-scale self-attention

The invention relates to a multi-focus image fusion method based on multi-layer semantics and multi-scale self-attention, and the method is characterized in that the method comprises the steps: obtaining a source image, inputting the source image into an MSI-Dtrans model, carrying out the feature extraction of the source image through Haar wavelet transform, obtaining the feature information of different scales, and carrying out the fusion of the multi-focus image through the MSI-Dtrans model. Inputting the feature information of different scales into a dynamic Transform for processing, and obtaining an initial focus image; wherein the network architecture of the MSI-Dtrans model adopts a multi-stage up-down sampling structure of a U-shaped network and is obtained through training of a training set, and the training set comprises multiple image pairs generated based on blurred images of different degrees and training labels; and fusing the initial focus image with the source image to obtain a final fused image. According to the invention, image distortion is effectively avoided and a good visual effect is achieved.
Owner:CHONGQING NORMAL UNIVERSITY

High-compression-ratio image compression method based on optimal transmission mapping

The invention discloses a high-compression-ratio image compression method based on optimal transmission mapping, which is suitable for application scenes such as network transmission, image storage and image transmission, and can remarkably improve the image transmission efficiency and save network bandwidth and storage resources. Compression can be carried out based on generative adversarial learning or a diffusion model, and the generative adversarial learning is utilized by the generative adversarial learning to train an image compression model based on optimal transmission mapping. The model comprises a feature extraction layer, a mapping layer, a quantization coding layer and a decoding reconstruction layer. The mapping layer realizes mapping and optimization of image features through optimal transmission mapping based on convex mapping; an image compression model of the latter comprises a feature extraction layer, a mapping layer, a quantization coding layer and a decoding reconstruction layer, the feature extraction layer is responsible for coding the preprocessed image into low-dimensional feature representation, quantized features are restored into image features through a denoising network of a diffusion model, and the decoding reconstruction layer is responsible for decoding the image. And decoding the image into a high-quality compressed image close to the original image.
Owner:SHANGHAI INST FOR ADVANCED STUDY OF ZHEJIANG UNIV

Image enhancement optimization method based on multi-strategy improved sparrow search

The invention provides an image enhancement optimization method based on multi-strategy improved sparrow search. The method comprises the following steps: performing normalization processing on a gray value of each pixel point of an original image; initializing a sparrow population and parameters according to an elite chaos reverse learning strategy; the method comprises the following steps: preprocessing an input image by adopting a dual gamma function BiGA; calculating the value of the evaluation function; updating the optimal fitness value of the sparrow population; when an iteration stop condition is not met, updating the position of the sparrow population by adopting a probabilistic following strategy, a self-adaptive local search strategy and a Cauchy Gaussian mutation strategy, and updating parameters of a dual gamma function BiGA; otherwise, ending iteration, and calculating an optimal parameter; processing the image, and outputting an enhanced image; according to the method, the visual effect of the image can be improved, edge details and textures can be richer, and the enhanced image can have higher contrast and better definition. The method is best in overall enhancement effect, and the obtained image is better in quality.
Owner:ANQING NORMAL UNIV +1

Design scheme generation method based on information retrieval technology

The invention discloses a design scheme generation method based on an information retrieval technology, and belongs to the field of information retrieval and image-text generation. Collecting the text description and an image matched with the content of the text description, preprocessing the text description and the image respectively, and performing feature extraction processing to obtain extracted visual feature monk and semantic features: extracting the visual features in the image data; for character description data matched with the image, processing the character image by using a semantic segmentation network so as to identify and segment a character region, extracting uniformly distributed semantic feature points through a quadtree distribution algorithm, and integrating the semantic feature points of all the regions to form a complete semantic feature point set corresponding to the image data including characters; a multi-scale feature map is constructed by using a feature pyramid network, the extracted visual features and semantic features are mapped to a unified feature space in the multi-scale feature map, and it is ensured that key information of the respective features is reserved in the mapping process.
Owner:JIANGSU VOCATIONAL & TECHNICAL UNIVERSITY OF ARCHITECTURE

Point cloud fusion method based on image and laser and power grid model modeling method thereof

The invention discloses an image and laser-based point cloud fusion method and a power grid model modeling method thereof, and the method comprises the steps: S1, obtaining an image point cloud and a laser point cloud, and respectively extracting point cloud curvature feature points on the surfaces of the point clouds; s2, adopting a point cloud feature histogram algorithm, and performing coarse registration according to the point cloud curvature feature points of the point cloud surfaces of the image point cloud and the laser point cloud extracted in S1 to obtain an initial transformation relation between the image point cloud and the laser point cloud; s3, performing downsampling on the image point cloud and the laser point cloud obtained in the step S1, and performing fine registration on the downsampled image point cloud and laser point cloud by adopting an ICP registration algorithm based on point-to-surface according to the initial transformation relation obtained in the step S2; and S4, converting the image point cloud and the laser point cloud to be under the same reference according to the fine registration in the S3, and fusing the image point cloud and the laser point cloud. According to the method, the technical advantages of ground three-dimensional laser scanning and oblique photogrammetry are effectively combined, and the point cloud cavity problem caused by the technical characteristics of the oblique photogrammetry and the three-dimensional laser scanning is eliminated.
Owner:JIANG SU XUN HUI KE JI GU FEN YOU XIAN GONG SI

Image restoration method and system based on dynamic decomposition and fusion

The invention provides an image restoration method and system based on dynamic decomposition and fusion, and the method comprises the steps: decomposing a to-be-restored image with hybrid features according to a degradation mode, and extracting degradation features of which the number is the same as the type number of the degradation mode; respectively processing each degradation feature to obtain a recovery feature corresponding to each degradation mode; and the recovery features are dynamically fused to obtain a clear recovery image with the same size as the to-be-recovered image, so that the function of performing high-quality recovery on the complex hybrid image is realized. According to the method, the recovery feature map is decomposed, processed and fused under multiple scales, the recovery feature map fusing the recovery features of the multiple scales is obtained, and the visual effect of hybrid image recovery is improved. According to the method, the symmetric U-shaped network is constructed based on the corresponding model formed by the method, and the processing sub-module corresponding to the degradation mode is constructed, so that complex and diversified degraded images in a real environment are well dealt with, and an efficient and reliable solution is provided for the field of image restoration.
Owner:WUHAN INST OF TECH

Monocular vision tower span measuring method based on RTK correction

The invention relates to a monocular vision tower span measurement method based on RTK correction, and belongs to the technical field of space distance measurement. Comprising the following steps: acquiring ambient light intensity and quality in real time based on an environment where a power transmission and distribution tower is located, and obtaining ambient light adaptation parameters by analyzing ambient light data and adjusting ISO sensitivity and shutter speed of a camera. According to the method, real-time environment light data analysis and camera parameter automatic adjustment are introduced in the monocular vision tower span measurement process, the image quality is effectively improved, tower recognition is more accurate, background interference is reduced, the geographic position and the shooting angle of a shooting point are corrected through the RTK technology, and the measurement accuracy is improved. And perspective transformation correction is carried out on the image in cooperation with a perspective projection theory, and the accuracy of distance measurement data is improved to centimeter level.
Owner:STATE GRID FUJIAN ELECTRIC POWER RES INST +1

Electronic rearview mirror severe weather image visual enhancement method and device, equipment and storage medium

The invention discloses an electronic rearview mirror severe weather image visual enhancement method and device, equipment and a storage medium, and relates to the technical field of electronic rearview mirrors, and the method comprises the steps: obtaining an original input image; processing an original input image through a hyper-parameter estimation network in the end-to-end adaptive image enhancement model to obtain hyper-parameters of the image enhancement module; after the image enhancement module is adjusted based on the hyper-parameters, the original input image is subjected to image enhancement processing through the adjusted image enhancement module to obtain the target image, and enhancement processing of the electronic rearview mirror image under various severe weather conditions is achieved. The visual effect in a full severe weather scene is improved, and better observation experience is brought to a driver.
Owner:DONGFENG MOTOR GRP

Detergent putting device and clothes treatment equipment

The utility model provides a detergent putting device and clothes processing equipment. The detergent feeding device comprises a liquid outlet waterway, a first waterway, a second waterway and a turbulent flow structure. The liquid outlet waterway is provided with a water inlet end and a water outlet end; the first waterway and the second waterway are used for conveying fluid, the first waterway communicates with a water source and the water inlet end of the liquid outlet waterway, and the second waterway communicates with the water source and the water inlet end of the liquid outlet waterway; fluid in the first water path and fluid in the second water path converge in the liquid outlet water path, and the fluid in the first water path is a detergent mixed solution; the turbulent flow structure is arranged on the first water path or the second water path and used for providing circumferential velocity components for fluid in the first water path or the second water path. According to the detergent putting device and the clothes treatment equipment, the detergent, especially the powdery detergent, is put into the clothes treatment cavity after being fully dissolved, the dissolution degree and the cleaning effect of the detergent are improved, and the user experience is improved.
Owner:WUXI LITTLE SWAN ELECTRIC CO LTD

Efficient oil injection mechanism of aluminum plate cold-rolling mill

The invention discloses an efficient aluminum plate cold-rolling mill oil injection mechanism, and relates to the technical field of aluminum plate cold-rolling mill oil injection, the efficient aluminum plate cold-rolling mill oil injection mechanism comprises a machining table, a transmission roller is fixedly mounted on the inner wall of the machining table, a motor is fixedly mounted on the outer wall of the machining table, and a pressing roller is fixedly mounted at the output end of the motor; the anti-deviation device is arranged on the inner wall of the machining table and comprises a lubricating box, a spraying opening, a supporting frame, a linear motor, a sliding plate, a sensor, a servo motor, a conveying wheel, a push plate, a guide plate, a fixing frame, a trapezoidal block and a deburring rod. The servo motor moves in the direction close to the middle of the conveying roller to drive the conveying wheel to move in the direction close to the middle of the conveying roller, the conveying wheel moves in the direction close to the middle of the conveying roller to be matched with the conveying belt to correct the aluminum plate, and the situation that the aluminum plate deviates during oil injection, consequently, lubricating oil cannot effectively cover the aluminum plate, and follow-up pressing roller rolling is affected is prevented.
Owner:ANHUI MEIXIN ALUMINUM CO LTD