100 results about "Rain removal" patented technology

The invention discloses a multi-degraded image recovery method based on frequency domain decomposition, and aims to solve the problems that a single model is difficult to deal with various image degradation and recovery processes of different frequency domains are mutually coupled in the prior art. According to the method, a degraded image is decomposed into a high-frequency space and a low-frequency space through fast Fourier transform, and a double-branch network architecture is adopted for targeted processing: for the high-frequency part, a high-frequency feature adaptive processing module HFPM is designed, and detail texture features are effectively extracted and interference is suppressed through feature enhancement and cross-layer fusion technologies; and for the low-frequency part, constructing a low-frequency feature conversion enhancement module LTEM, and capturing global context information by using cyclic convolution to improve the integrity of the structure contour. According to the method, decoupling processing of frequency domain features is realized, and the image restoration performance of the model in various degradation scenes such as rain removal, noise removal and defogging is remarkably improved through the synergistic effect of high-frequency detail enhancement and low-frequency structure optimization. Experimental results show that the method has excellent recovery effect and robustness when a plurality of image degradation tasks are processed at the same time, and can be effectively applied to visual tasks such as traffic accidents with high image quality requirements.

The invention relates to the technical field of image rain and snow removal, in particular to a feature-driven GAN-based self-adaptive snow and rain removal method, which comprises the following steps: S1, constructing a feature extraction network architecture oriented to complex degradation features; s2, a spatial self-adaptive layered constraint loss system is established; s3, establishing a double-path reasoning framework of multi-stage collaborative optimization; and S4, constructing an industrial-grade credible evaluation system. The rain / snow removal frame based on the generative adversarial network is innovated in the aspects of generator architecture, loss function design and cooperative training of the generator and the discriminator, and by introducing a double-generator structure, an attention mechanism and space guide loss, the recovery performance of the rain and snow degraded image is remarkably improved; an effective solution is provided for practical application, and through the innovations, the model shows an excellent image recovery effect in a complex rain and snow scene.

The invention discloses an image rain removal method based on dual-channel fusion. The method comprises the following steps: establishing a data set containing an original rain image and a corresponding rain-free clear image; constructing a dual-channel fusion network for image rain removal; using loss, edge loss and frequency loss to form a mixed loss function for quantifying the difference between the rain-removed image and the rain-free clear image; training the dual-channel fusion network by adopting the data set; and the trained dual-channel fusion network is adopted to test a rain image to be subjected to rain removal, and a clear image after rain removal is obtained. According to the invention, a dual-channel fusion attention enhancement module, a mixed scale gating feedforward network module and the like are introduced into the model, so that the robustness and the feature extraction capability of the model are improved, and the model can better adapt to raindrop interference in different actual scenes.

The invention discloses a two-stage multi-task image restoration method based on an RDM-CS framework (see figure 1), which can process various image restoration tasks such as low illumination, rain removal, snow removal, defogging and the like at the same time. Comprising the following steps: 1) processing and dividing a data set; and 2) carrying out feature extraction by using a VQGAN encoder and completing forward diffusion on the feature zt. And 3) training the prediction noise network and the prediction residual network to obtain residual and noise, and then completing reverse generation. And (4) training a CS (Channel-Spatial Transform) network (Channel-Spatial Transform). And 5) testing in the test set of each data set, and evaluating the image restoration effect. According to the method, through the multi-stage feature extraction and diffusion process, the model can effectively process various image degradation problems, and the image restoration quality and efficiency are improved. The system has a unified model architecture, can adapt to different image recovery tasks, and has relatively high practicability and popularization value.

The invention discloses a hierarchical image rain removal method based on enhanced rain stripe perception. According to the method, for the problem of image quality degradation in a rainy day environment, an enhanced rain stripe perception feature enhancement module E-RAFEM is designed, two core components of a learnable direction filter and rain stripe texture modeling are integrated, and the directivity and linear texture features of rain stripes are accurately modeled. An encoder-decoder backbone network based on Transform is adopted, and E-RAFEM modules are embedded in the first three encoding levels, so that a hierarchical rain stripe processing mechanism is formed. A progressive multi-scale fusion mechanism is introduced, multi-scale features are captured through convolution kernels with different expansion rates, and gradual integration is carried out in a progressive mode to avoid information loss. According to the enhanced rain stripe sensing network ERA-Net provided by the invention, high-quality recovery of images under various complex rainy day conditions is realized through accurate rain stripe feature modeling and hierarchical processing strategies.

The invention discloses a multi-scale pulse gated image rain removal method and system with biological inspiration, and the method comprises the steps: firstly obtaining a synthetic data set of a rain removal task of a single image, and carrying out the preprocessing; secondly, a bionic driving color antagonism feature extraction mechanism is introduced, separation and enhanced expression of color degradation information in a rainy day image are achieved, and color antagonism features are obtained; then performing structure enhancement and multi-scale abstraction on the color antagonism features through bionic visual cortex multi-scale coding, and constructing visual cortex feature representation; and finally, for visual cortex feature representation, proposing a bionic visual cortex dual-channel prediction structure and a hybrid coding reconstruction structure, and outputting an image rain removal result graph. And constructing a multi-target mixed loss function, and carrying out reverse training and testing. According to the invention, the color information and the brightness information are accurately separated, the interference of background noise on the target color is reduced, and image rain removal is accurately and efficiently realized.

The invention discloses an image rain removal model, method and system, electronic equipment and a storage medium, and the image rain removal model employs a multi-output multi-scale architecture and has a plurality of scale branches operated under a plurality of resolutions; the encoder of each scale branch comprises a convolution layer which is used for receiving and extracting potential features of a to-be-processed rain image and obtaining a shallow feature map; the frequency feature enhancement unit is used for capturing multi-frequency information, acquiring context semantic information and acquiring a processing feature map; the multi-scale compensation Transform block is used for extracting global information and local detail features in each scale branch to obtain a deep feature map; a gating fusion module is arranged at the tail end of the encoder and is used for fusing depth features of all scale branches to obtain an enhanced feature map; a residual convolutional layer for outputting a residual image is arranged at the tail end of the decoder of each scale branch; the residual image is used for subtracting the received to-be-processed rain image to obtain a rain-removed image.

The invention belongs to the technical field of image processing, and relates to an image video rain removal method based on local perception modeling and multi-stage span fusion, which adopts parallel branch networks with three level scales to respectively and sequentially carry out feature extraction, feature extraction and multi-stage span fusion on raining images with corresponding resolution sizes, performing high-level semantic information mining on the input raining image to obtain a high-dimensional feature map; high-resolution image reconstruction: adopting a local set perception implicit representation module, mapping the high-dimensional feature map to a continuous RGB color space through linear coordinate projection, and compensating continuous textures and edges sheltered by rain in the image to obtain a reconstructed image; and cross-scale feature fusion: carrying out information fusion between stages and scales on the image through double branches, and aligning and enhancing multi-scale semantics to obtain a high-resolution rain-removed image. According to the method, artifacts of a raining image can be suppressed in a multi-domain and multi-scale level, and sharpness and consistency are enhanced.

The invention discloses an image rain removal method and device, which are used for solving the technical problem of poor image rain removal effect caused by difficulty in accurately balancing rain line removal and background detail recovery in the existing rain removal technology. The method comprises the following steps: acquiring a rain image, performing multi-scale down-sampling on the rain image, and outputting a multi-scale rain image; inputting the image with rain and the multi-scale image with rain into a preset multi-scale dual-domain collaborative rain removal network, wherein the preset multi-scale dual-domain collaborative rain removal network comprises an encoder, a multi-scale space interaction feature fusion module and a decoder; encoding the rain image and the multi-scale rain image by using an encoder, and outputting a plurality of target rain encoding features; carrying out feature fusion on the multiple target rain coding features through a multi-scale space interaction feature fusion module, and outputting target fusion features; and inputting the image with rain, the multi-scale image with rain, the target fusion feature and the target coding feature with rain into a decoder for decoding to generate a target rain-removed image.

The invention provides a low-illumination rainy day image enhancement method based on DEPMD-Net. Through heterogeneous double teachers and multi-stage distillation, polarized rain-light attention and implicit representation are introduced, separation and fusion of raindrop high-frequency information and illumination low-frequency information are realized, and an image with balanced brightness and without rain interference is generated. The method comprises the following steps: 1) synthesizing low-illumination rainy day data based on Rain100L and LOL-v1; 2) pre-training a brightness expert and a rain removal expert, and obtaining prior through bidirectional KL mutual learning; 3) utilizing brightness-rain mask statistics to construct joint priori, and adopting non-zero mean anchoring to simulate night rain distribution in diffusion noise scheduling; 4) proposing PiDNet-X to recover features through cooperation of a double-branch structure and rain-light attention, 5) performing staged distillation through a soft label and feature prompt, obtaining lightweight Student-C / F through a Born-Again strategy, and realizing night rain scene self-correction by double students in a reasoning stage through moving average and mutual learning.

The invention discloses an image processing method fusing frequency perception and a Mama network, and the method comprises the steps: collecting original data, carrying out the preprocessing, obtaining a sample set, training a constructed deep learning network, processing an input image in real time through the trained deep learning network at an online stage, and achieving a rainwater removal effect. On the basis of a fusion frequency perception and Mama network architecture, on one hand, discrete wavelet transform down-sampling operation, convolution operation, two wavelet domain recovery module feature extraction operation, convolution operation, two wavelet domain recovery module feature extraction operation, convolution operation and discrete wavelet inverse transform operation are sequentially carried out on a raindrop picture; and on the other hand, a high-frequency component is extracted from frequency information after wavelet transformation, and after frequency enhancement, a wavelet domain recovery module is sequentially guided to perform refined texture reconstruction, so that the rain removal effect is improved, and an image restoration result with higher quality is obtained.

The invention relates to the technical field of image processing, and provides an image rain removal method and system based on multi-scale prior injection, and the method comprises the steps: carrying out the subtraction of a gray image formed by a maximum pixel value and a minimum pixel value of a rainy day image along a channel dimension; extracting multi-scale potential background prior features of the initial rough rain-free image through a residual branch of a pre-trained U-Net network; under the guidance of the multi-scale potential background prior features, multi-scale rain stripe features of the rainy day image are extracted through a PITform branch, and first-scale decoder rain stripe features are obtained; and the image passes through a Tform module and a convolution module and then is added with a rainy day image to obtain a rain-removed image. According to the method, the U-Net network is adopted, the prior information is introduced into each scale layer, the network is guided to generate the rain-free image with rich texture details, accurate image recovery is realized, and the rain removal performance is improved.

The application discloses a kind of based on image rain-removing method of generative adversarial network and convolutional neural network, comprising: according to rain-free image, utilize random noise to synthesize rainy image;The pre-processing of synthesized rainy image, and the multiple rainy images after pre-processing constitute data set;The generator and discriminator in the generative adversarial network GAN are trained using the data set, and the rain-removed image generated using the generative adversarial network model is used to train convolutional neural network CNN;Generative adversarial network GAN and convolutional neural network CNN are alternately trained until reaching preset condition, and trained generative adversarial network GAN and trained convolutional neural network CNN are obtained;The image to be removed is input into the generator in trained generative adversarial network and is removed, to obtain the image after rain-removing;The image after rain-removing is input into trained convolutional neural network, to obtain the rain-removed image after final optimization.

The invention relates to the field of deep learning and image processing, and discloses an image rain removal method based on wavelet transform and digital filtering detail guidance, which comprises the step of processing an input rain image by applying a trained image rain removal model, and comprises the following steps of: obtaining the rain image, and inputting the rain image into the image rain removal model for processing, and then outputting a rain removal image. According to the method, different image rain removal tasks can be better adapted by introducing image priori knowledge, image noise is effectively suppressed in combination with digital filtering, so that the quality and precision of recovery are improved, and the accuracy and robustness of image rain removal are improved by fusing feature information of different scales.

The invention relates to the technical field of electric power scene image restoration, and discloses a novel layer normalization method, system and device for an electric power scene image restoration model, and a medium, and the method comprises the steps: obtaining a target electric power scene image for the electric power scene image restoration model, and extracting the image features of the target electric power scene image; calculating spatial channel overall statistical information of the image features; calculating a normalized parameter according to the overall statistical information of the space channel; generating an overall normalization model of the space channel of the image features according to the normalization parameters; and performing layer normalization on the power scene image input into the power scene image restoration model in real time according to the overall normalization model. The method is suitable for various image restoration tasks such as image super-resolution, denoising, JPEG compression artifact removal and rain removal, can be directly applied to an inspection system to remarkably improve the image quality and availability, and provides high-quality input for subsequent defect recognition and toughness analysis.

The present application relates to a rainy day image fault-tolerant model based on an improved convolutional long short-term memory network, comprising: a feature extraction module and a regional feature enhancement module; the feature extraction module is used to extract rain streak features in rainy day images and efficiently learn key areas of interest, outputting a feature map; the regional feature enhancement module captures and removes raindrop information of different scales based on the feature map, and outputs a rain-removed image; the present application can capture rain streaks of different scales, while removing basic rain lines, protecting important image details, textures, and background information, thereby obtaining a rain-free image with higher color saturation and quality, making the restored image cleaner and having better visual effects.

The application discloses a parallel single image rain removal method based on a residual prior attention mechanism, and comprises the following steps: 1) obtaining an image to be removed; 2) extracting picture detail feature information through an image detail extraction network; 3) extracting picture rain line feature information through a rain line feature extraction network; 4) fusing the detail feature information and the rain line feature information through a feature fusion network; and 5) completing rain removal. The application strengthens effective feature information and weakens irrelevant items through a residual prior attention module, thereby improving the rain removal performance of the model; and the rain removal performance of the model is improved through reasonable fusion and fine-tuning of the detail feature and the rain line feature.

The application discloses a low-illumination rain-added image enhancement method based on a PERM-Net (Physics-guided Event-driven Rain Modulation Network), and proposes a joint enhancement network integrating degradation prior, event-driven coding and state space recovery in view of the problems of serious image brightness attenuation, obvious continuous rain streak interference, texture detail loss and insufficient perception ability of the enhanced result. The method comprises the following steps: 1) improving an existing data set; 2) constructing a degradation prior estimation module to jointly model the brightness attenuation, rain streak density and direction structure information in the image; 3) designing an event rain streak coding module to dynamically code the continuous rain streak features and extract the direction structure; 4) constructing a physics-guided rain streak Mamba block to realize image brightness recovery, rain streak suppression and global structure reconstruction; and 5) combining an adaptive fusion module and a perception optimization head to improve the detail expression ability of the enhanced image. The method realizes excellent rain removal effect and can generate an image rich in details and visually realistic in a complex environment.

The present application relates to a kind of two-stage image rain removal methods based on rain physics model and deep learning, it is related to image rain removal technical field.The method includes: collecting original rain image;According to original rain image, corresponding atmospheric light graph A, transmissivity graph T and rain stripe graph S are predicted;Multiple rain removal images are generated following rain physics model;The weighted summation of multiple rain removal images is obtained by applying grouping weighting mechanism, and preliminary rain removal image J is obtained;The quality of preliminary rain removal image J is optimized by applying PromptFormer.The method, in the first stage, combines the rain physics model to optimize rain removal inference logic, in the second stage, a four-stage U-shaped network is introduced to optimize the output of the first stage, in addition, the robustness of the entire algorithm is further enhanced by combining grouping weighting mechanism.

The application discloses a single image rain removal method based on cyclic inner and outer dense connection and attention enhancement, comprising the following steps: constructing a cyclic inner and outer dense connection and attention enhancement network for single image rain removal, wherein the network comprises a cyclic subnetwork with multiple shared parameters; determining a loss function, wherein the loss function comprises a structural similarity and a perception loss; inputting training data; and training network parameters to obtain a cyclic rain removal model. The application establishes dense connection in the cycle, expands the channel of network information transmission, makes the shallow layer features containing more background detail information fully utilized by the deep layer and the subsequent convolution layer of the network through information transmission, and enables the network to retain more background details in the cyclic progressive rain removal process.

The application discloses an image rain removing method and system based on a discrete attention mechanism in the field of image rain removing, and comprises the following steps: collecting real-time monitoring images of a monitoring area, inputting the real-time monitoring images into a trained information distillation rain removing network model, removing rain streak features from the real-time monitoring images to obtain output images; the training process of the information distillation rain removing network model comprises the following steps: connecting a multi-space convolution pooling network module, a long short-term memory network module and a discrete attention information distillation network module in series to construct an information distillation rain removing network model; training the information distillation rain removing network model by using a training sample set S and outputting a training result; optimizing and iterating parameters of the information distillation rain removing network model by using a loss function, and repeating the iteration until a set maximum iteration number is reached to output the trained information distillation rain removing network model; and more fine rain streak features are extracted under high resolution, so that the rain streak features in the images are removed.

The application discloses a hierarchical image rain removal method based on enhanced rain streak perception. In view of the image quality degradation problem in rainy environment, an enhanced rain streak perception feature enhancement module E-RAFEM is designed, which integrates a learnable direction filter and a rain streak texture modeling two core components, and accurately models the directionality and linear texture features of rain streaks. A Transformer-based encoder-decoder backbone network is used, and the E-RAFEM module is embedded in the first three encoding levels to form a hierarchical rain streak processing mechanism. An incremental multi-scale fusion mechanism is introduced, multi-scale features are captured through different expansion rate convolution kernels, and an incremental method is used to gradually integrate to avoid information loss. The enhanced rain streak perception network ERA-Net proposed by the application realizes high-quality recovery of images under various complex rainy conditions through accurate rain streak feature modeling and hierarchical processing strategy.

The application provides a video rain removal method and system based on a space-time difference state space model, and belongs to the technical field of deep learning. The application solves the problem of how to ensure accurate rain removal while retaining the background texture to the greatest extent and breaking the trade-off between "rain removal completeness" and "background fidelity". The method comprises the following steps: S1: extracting shallow space-time features from an input video; S2: constructing anchor points and reference features by using multi-plane scanning, generating a gating map by calculating geometric consistency, and removing rain information in the features by using a difference mechanism; S3: during training, capturing local space-time details by using orthogonal plane convolution, during inference, enhancing the video background texture by using a single-stream convolution after reparameterization, and outputting a rain-removed video. The system comprises a 3D convolution layer module, a consistency-guided difference gating module, and a reparameterized three-plane feedforward network.

The application provides an image detection method and device and a computer readable storage medium. A current image in a video stream is obtained, and a reference image is obtained. The current image is input into a rain removal model to obtain a processed image processed by the rain removal model. A first frame difference image of the current image and the reference image is obtained, and a second frame difference image of the processed image and the reference image is obtained. Difference information of the first frame difference image and the second frame difference image is obtained, and it is determined whether the difference information meets a preset condition. In the manner, whether it is a rainy day can be accurately determined through the difference information of the current image and the current image processed by the rain removal, other factors in the image background can be excluded, the accuracy is improved, misjudgment is prevented, and robustness is improved.

The present application provides a kind of intelligent monitoring scene light weight image rain removal method and system, it is related to image processing technical field, the method includes: obtaining the image to be handled in rain day under intelligent monitoring scene;The image to be handled in rain day is input into pre-trained light weight rain removal model, and the processing image after rain removal is output;Light weight rain removal model is based on encoder-decoder architecture construction, and there is attention mechanism based on channel statistical characteristics and cross-domain feature alignment module in model network configuration;Light weight rain removal model is obtained by using training data set, and is trained by progressive hybrid training strategy;Training data set includes optimization synthetic data set generated by physical model simulation and frequency domain confrontation alignment, the feature expression learned by model on optimization synthesis data is effectively migrated to real data domain, so as to ensure the real-time computing efficiency required by intelligent monitoring scene, while significantly improving the rain removal effect and generalization performance of model in real complex rain environment.

The application discloses an image rain removal method based on learnable prior distillation and frequency domain cross attention, and relates to the field of image processing, comprising: based on rainy image data, performing degradation analysis on the rainy image data through a prior representation network to extract a rain streak degradation mode, wherein the rain streak degradation mode contains prior knowledge; inputting the rainy image data into a pre-trained teacher network to extract teacher knowledge; constructing a student model based on a cross attention mechanism, taking the prior knowledge as a query, taking the teacher knowledge as a key and a value to perform prior distillation, and generating prior features; introducing a frequency domain feature extraction module to perform spatiotemporal feature fusion on the rainy image data to generate fused features; and performing image reconstruction and recovery based on the prior features and the fused features to generate clear image data. The application solves the technical problems of poor rain streak removal effect and limited model practicability of existing single-image rain removal technology, and achieves the technical effects of accurate rain streak separation and enhanced model generalization ability.

The application discloses an image rain removal method and system based on an expert model and multi-stage rain streak extraction. The method comprises the following steps: performing preprocessing on an input rainy image to obtain a separated image, inputting the separated image into a trained rain removal model for processing, wherein the separated image is input into a mixed rain streak prior module for processing to obtain mixed prior features; the mixed prior features are input into a multi-stage rain feature extraction module for step-by-step feature extraction to obtain rain streak layer features; and details of the image are recovered by using a detail recovery enhancement module based on the rainy image and the rain streak layer features to generate a final rain removal image. The application comprises two parts of training of a rain removal model and image rain removal by using the rain removal model, can realize accurate separation of rain streak features and fine recovery of background details by using an adaptive prior combined with a recursive extraction strategy, can effectively process diversified rain streak patterns and complex backgrounds, and improves the accuracy and robustness of image rain removal.

The invention belongs to the technical field of computer vision, and discloses a video rain removal architecture and method based on hierarchical feature cascade purification and a frame difference long-short term memory neural network, and the architecture comprises a hierarchical feature cascade purification module, a time difference perception module, and a video quality improvement module. The hierarchical feature cascade purification module adopts an encoder-decoder structure, and captures spatial features of rain lines through multi-scale feature extraction and cascade fusion; the time difference sensing module identifies the time characteristics of the rain line by analyzing the difference characteristics of adjacent frames by using a frame difference long-short-term memory network; the video quality enhancement module further recovers details and reduces artifacts through residual dense blocks and short-circuit connections. A frame difference long-short-term memory network is provided for the first time, and high-frequency changes of raindrops are effectively captured; a video quality improving module is introduced, so that the visual quality after rain removal is remarkably improved; according to the method, the video rain removal effect and efficiency are remarkably improved while the time consistency is kept.

The present invention discloses a single-image rain removal method and system based on image prior and gated attention learning. The method comprises: constructing a network model based on image prior and gated attention learning, the network model comprising a sequentially connected feature extractor, a codec, and a gater with an attention mechanism; obtaining training samples; forming a training dataset of rainy-rainy image pairs; preprocessing the training dataset of rainy-rainy image pairs, inputting the preprocessed data into the network model based on image prior and gated attention learning for training, and obtaining a trained network model based on image prior and gated attention learning; inputting the image to be rained into the trained network model based on image prior and gated attention learning, and finally obtaining the image data after rain removal. The present invention effectively extracts detailed information of the image and identifies more rain streaks, thereby enhancing the rain removal effect of the rain image.

The invention discloses a continuous image rain removal method based on a complementary mechanism. The method comprises the following steps: 1, constructing a series of paired rainwater picture data sets; 2, training the generation network and the rain removal network in stages; 3, generating a playback data extension training set by using the generative network; and 4, introducing multiple losses to jointly optimize the rain removal network. According to the method, the rain removal network can have the capability of continuously learning a plurality of rainwater data sets, so that the generalization capability of the network in a real rainwater scene can be improved.