186 results about "Image degradation" patented technology

The invention discloses an image video super-resolution enhancement method based on a degradation generative adversarial network, and relates to the field of image processing, and the method comprises the steps: carrying out the image collection and preprocessing; building and training a super-resolution enhancement model; and carrying out super-resolution enhancement on the image based on the degradation generative adversarial network model. According to the method, an image content self-adaptive dynamic degradation kernel generation mechanism is adopted, the degradation process of the image under different equipment and organization structures is truly simulated, a dynamic up-sampling and residual error correction network guided by the degradation kernel is adopted, the detail reduction capability and the structure fidelity of the super-resolution image are remarkably improved, and the super-resolution image quality is improved. The image texture authenticity and key organization density consistency are effectively enhanced, the balance of training games between a generator and a discriminator is realized, and the model stability and convergence quality are improved.

The invention provides a laryngeal cancer multi-mode prognosis prediction method and a laryngeal cancer multi-mode prognosis prediction system fusing a CT (Computed Tomography) image and a ViT model. Relates to the technical field of biomedical images. The method comprises the following steps: acquiring and preprocessing multi-modal data of a laryngocarcinoma patient; carrying out lightweight compression, redundant information screening and robustness training on the ViT model to obtain an optimized ViT model; extracting depth features of the CT image data based on the optimized ViT model, and performing multi-stage fusion on the depth features and clinical and genome data to construct a prognosis prediction model; and performing risk stratification on the patient according to a prognosis prediction result predicted by the prognosis prediction model, and outputting treatment guidance suggestions based on the risk stratification. Through ViT model optimization, multi-modal data fusion and clinical adaptation design, precise prediction and personalized treatment guidance of laryngocarcinoma prognosis are realized, and the problems of insufficient image degradation processing, low model deployment efficiency and the like in existing laryngocarcinoma prognosis prediction are solved.

The invention provides a ship target detection method based on nonlinear network enhancement, a medium and equipment, and belongs to the field of artificial intelligence. The method comprises the following steps of: performing type conversion, data division and enhancement on image data in a data set by adopting the ship data set acquired in a real river channel scene; a nonlinear network enhanced YOLO ship detection model is constructed; adopting a multi-task joint loss function to train the YOLO ship detection model; and inputting a port monitoring image and a sea surface aerial image into the trained YOLO ship detection model, outputting a category number, a confidence value and bounding box coordinates of each prediction box, and forming a visual image. According to the method, a nonlinear network enhanced YOLO ship detection model is constructed, and the modeling expression capability of the network on a ship target in a complex scene is effectively improved, so that the robustness and the accuracy of target detection are enhanced, and particularly, the performance is better under the conditions of small target detection and image degradation.

The invention discloses an underground structure leakage intelligent detection system based on multi-modal image fusion and deep learning recognition. The system comprises an image acquisition and preprocessing module, a significance guide image fusion module, a bimodal target detection module and a feature fusion and output module. Compared with the prior art, the method has the following advantages: saliency guidance, channel attention and multi-modal joint training are combined, an information closed loop is constructed by a triple mechanism, and the image fusion quality is improved; bimodal parallel recognition and ANN fusion judgment are adopted to adapt to the image degradation condition in a complex environment, and the recognition accuracy of a weak signal area is improved; the system can be deployed in various underground structure scenes such as subways, tunnels, underground garages and pipe galleries, and is compatible with various hardware terminals; a lightweight feature extraction and rapid fusion module is provided, and the real-time processing requirement of edge computing nodes is met; a closed-loop detection system of image acquisition, fusion enhancement, depth identification and intelligent output is formed, the overall efficiency is high, and the false detection rate is low.

The invention discloses a real haze image defogging method based on a haze degradation model. The method comprises the following steps: constructing a haze degradation model fusing multiple scattering effects and multiple image degradation factors; using the haze degradation model to construct a training data set including the clear image and the corresponding pseudo haze image; constructing a defogging network for a real haze scene; training the defogging network by adopting the training data set until a preset loss function is converged; and inputting a to-be-defogged image into the trained defogging network to obtain a defogging result. According to the haze degradation model constructed by the invention, the difference between a synthetic domain and a real domain is effectively relieved; a designed space-frequency hybrid module improves the adaptability of the model to complex degradation characteristics; the prior-guided feed-forward network fully excavates and fuses dark channel prior information, and the sensing and modeling capability of the model to the haze area is effectively enhanced.

Systems are provided for dynamically splitting input images into a plurality of input tiles for processing by a super-resolution model. The size and halo region of the input tiles is based on a degradation associated with the convolutional operations of the super-resolution model. The input tiles are processed by the super-resolution model to generate output tiles that are stitched together into output images that are of a higher or different resolution than the input images.

The invention discloses an underwater image degradation diffusion self-supervised enhancement model and a building and training method, and relates to the technical field of underwater image enhancement. The invention provides an underwater image degradation diffusion self-supervised enhancement model and a building and training method for the problem of target detection performance reduction caused by underwater image quality degradation, the model built by the method is combined with the differential thought of a Koschmieder illumination scattering degradation model and a diffusion model, the degradation process of a real underwater environment is simulated, and the target detection performance is improved. Self-supervised training data is generated, dependence of a traditional method on manual annotation data is avoided, image features are extracted through a ResNet50 backbone network, global background light and transmission rate are predicted in parallel, a clear image is reversely recovered by using a physical formula, transmission rate consistency loss, background light consistency loss and reconstruction loss are also proposed, an unsupervised optimization target is constructed, and the self-supervised training data is obtained. And the accuracy and stability of model training are ensured.

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 embodiment of the invention provides a model training and image processing method and device, a storage medium and a program product. In the embodiment of the invention, the target degradation parameter is obtained by optimizing the initial degradation parameter with the target that the texture loss after image degradation processing is smaller than or equal to the set texture loss threshold value, so that the target degradation parameter is obtained according to the target degradation parameter obtained through optimization. The texture loss of the input image of the model obtained by carrying out degradation processing on the target image is smaller than the texture loss threshold compared with the target image, so that a moderately degraded training sample is generated, and the degraded image still keeps some texture information to provide reliable context clues for the model; and texture reasoning can be carried out based on real observation instead of generating some artifacts, so that texture enhancement is effectively realized.

The invention relates to the technical field of image processing, and discloses a low-quality chromosome image segmentation enhancement system, which extracts features and perceives degradation through a multi-scale degradation perception coding module, separates a structure from noise through a frequency domain feature intelligent decoupling module, and generates an enhanced image and a segmentation mask through a joint decoding and contour enhancement module. And finally, the whole system is optimized through a composite loss function by an adversarial discrimination and loss optimization module, so that high-quality enhancement and accurate segmentation of a low-quality chromosome image are realized. By accurately sensing and separating image degradation information, specially enhancing the continuity and definition of chromosome contours, adopting an end-to-end optimization framework which is tightly coupled with enhancement and segmentation tasks, and introducing an antagonism discrimination mechanism containing various targeted losses, the ability of extracting pure structural features from low-quality images is significantly improved, and the method has the advantages of being high in robustness and high in robustness. Contour defects are effectively repaired, the overall performance is optimized, and an enhanced image and a segmentation mask with high reality and high precision are generated.

The invention is suitable for the technical field of radar signal processing, and provides a sparse-neighborhood joint constraint-based deep expansion ISAR super-resolution imaging method, which comprises the steps of firstly constructing an ISAR image degradation model, constructing an ISAR super-resolution imaging problem based on the ISAR degradation model and a compressed sensing theory, and solving the ISAR super-resolution imaging problem by using an ADMM (Amplitude Division Multiplexing). The process of solving the ISAR super-resolution imaging problem by the ADMM is expanded into a multi-stage neural network, and finally, the low-resolution ISAR echo is input into the trained neural network to obtain an ISAR super-resolution imaging result. According to the method, the sparsity constraint and the neighborhood amplitude constraint are combined, the corresponding signal model and the ADMM solving algorithm are deduced, the reconstruction capability of the algorithm on complex target details and the representation capability on structural information are effectively improved, and effective super-resolution imaging can be realized based on narrow-band short-aperture echoes.

The invention relates to image processing, in particular to a complex environment-oriented power transmission line inspection image processing method, which comprises the following steps of: screening key frames with high geometric information content by quantitatively evaluating inter-frame motion amplitude and feature tracking quality; extracting features of each key frame by using a pre-trained visual model; performing intra-frame feature aggregation on the features of each key frame by using an intra-frame self-attention mechanism to obtain corresponding intra-frame feature representation; performing global feature aggregation on the intra-frame feature representations of all the key frames by using a global self-attention layer to obtain inter-frame feature representations; constructing a multi-task learning network, and carrying out end-to-end collaborative optimization on depth estimation, image defogging and high-level semantic segmentation; inputting the inter-frame feature representation into a multi-task learning network, and obtaining a restored clear image through deep fusion of scene depth information and image degradation priori; according to the method, the defect that the dual requirements of quality improvement and feature retention of the power transmission line inspection image in a complex environment cannot be met can be overcome.

The invention relates to the technical field of image processing, and discloses an image deblurring method, which comprises the following steps of: performing fuzzy detection and classification: constructing a fuzzy image classification module by adopting a fuzzy recognition mechanism based on dark channel prior, generating an auxiliary channel with fuzzy perception capability by an input image through a dark channel feature extraction module, and performing fuzzy detection and classification on the auxiliary channel; and then the original image and the dark channel image are spliced and then input to a fuzzy recognition module, whether the image is obviously fuzzy or not is quickly judged, and redundant processing on the clear image is avoided. Through the structural design of a multi-stage multi-task joint model, the problem that the performance and efficiency in the vehicle-mounted image deblurring and super-resolution reconstruction tasks are difficult to consider at the same time is effectively solved, and meanwhile, the defects of traditional synthetic data in the aspects of fuzzy diversity and perception consistency are effectively overcome through a diversified data set construction method; the trained model can adapt to various image degradation conditions in an actual vehicle-mounted scene, and the robustness and adaptability of the model in the real scene are improved.

The invention provides a multi-scene image degradation integrated recovery method based on a visual language model, which realizes high-quality image reconstruction under various weather degradation conditions, and comprises the following steps: inputting a given degraded image into an encoder for encoding to obtain encoding features; querying the pre-trained visual language model through a cross-modal prompt generator to generate a multi-scale degradation perception cross-modal prompt; the pre-trained visual language model takes a problem and a degraded image as input; the degeneration perception cross-modal prompt is input into the restoration trunk through a guide attention alignment module to be aligned and fused with the coding features, and final output of the guide attention alignment module is obtained; refining and fusing the degraded image and the final output of the attention alignment guiding module through a double feature compensation module to obtain the final total output; and carrying out decoding processing and image reconstruction on the final total output through a decoder to obtain a high-quality output image.

The application discloses a remote sensing image super-resolution reconstruction method based on spatial variable degradation perception, and comprises the following steps: S1, acquiring a high-resolution remote sensing image dataset; S2, constructing an image degradation model; S3, constructing a spatial variable degradation perception blind super-resolution model; S4, training a remote sensing image blind super-resolution model based on spatial variable degradation perception; and S5, reconstructing a high-resolution remote sensing image through the trained blind super-resolution model. The blind super-resolution reconstruction task is decomposed into a degradation process and a reconstruction process, on the one hand, the complex degradation process of an image is simulated, and on the other hand, the degradation conditions of different spatial positions of the image are considered, the degradation kernel closer to the real world is evaluated while the perception degradation range is expanded, serious kernel estimation deviation is avoided, and more accurate remote sensing image super-resolution reconstruction is realized.

The invention relates to the technical field of computer vision, solves the technical problem that an image captured by current computer vision is easy to be influenced by the environment to cause image degradation, and particularly relates to a defogging and recognition combined network and a target detection method thereof, and features extracted from a target recognition network are shared to an image restoration network. And image restoration processing is carried out through the UNet structure. Clean features generated by the image restoration network are shared to the target recognition network. According to the method, the image restoration network based on the diffusion probability model is introduced, the target recognition network of the YOLOX model and the feature information provided by the feature enhancement module are matched, the defogging restoration task of the image is better completed, two deformable convolutions are introduced, the sensory domain of each convolution layer is effectively expanded, the output features are enriched, and the image defogging restoration efficiency is improved. Therefore, the influence of the specific weather information on the detection precision is reduced, and the defogging and target detection accuracy is good.

The application is suitable for the technical field of radar signal processing, and provides a deep unfolding ISAR super-resolution imaging method based on sparse-neighborhood joint constraint, comprising: firstly, constructing an ISAR image degradation model, constructing an ISAR super-resolution imaging problem based on the ISAR degradation model and the compressed sensing theory, using ADMM to solve the ISAR super-resolution imaging problem, unfolding the process of solving the ISAR super-resolution imaging problem by ADMM into a multi-level neural network, and finally inputting low-resolution ISAR echoes into the trained neural network to obtain an ISAR super-resolution imaging result. The application combines sparse constraint and neighborhood amplitude constraint, deduces a corresponding signal model and an ADMM solving algorithm, effectively improves the reconstruction ability of the algorithm to complex target details and the representation ability of the algorithm to structural information, and can realize effective super-resolution imaging based on narrowband short-aperture echoes.

This invention discloses a detail-learning-based low-light image enhancement method and apparatus for smart home sensing, relating to the field of image processing. The method includes: constructing and training a detail-learning-based low-light image enhancement model to obtain a trained low-light image enhancement model. The detail-learning attention module of the feature enhancement module in the low-light image enhancement model includes a channel detail attention module and a spatial detail attention module connected in sequence. The method involves acquiring low-light images collected by smart home sensing devices and inputting them into the trained low-light image enhancement model. The low-light images first pass through a feature extraction module to obtain initial image features. These initial image features are then input into a feature enhancement module, sequentially passing through N detail enhancement modules to obtain the Nth detail enhancement feature. The Nth detail enhancement feature is then processed by a feature mapping module and residually connected to the low-light image to obtain the corresponding enhanced image. This invention addresses the problem of prominent low-light image degradation.

The application discloses a GAN neural network multiple distortion suppression model based on a coordinate attention mechanism, obtains an original neutron radiographic image from a neutron source; proposes a brand-new neutron radiographic image degradation model; adds Gaussian blur, Gaussian noise, Poisson noise and noise obeying gamma distribution to the clear neutron radiographic image; uses real white spot noise to train the GAN neural network, simulates white spot noise and randomly adds the white spot noise to the clear neutron radiographic image; constructs a multiple distortion suppression model of the GAN neural network based on the coordinate attention mechanism; uses Huber loss to train the constructed GAN neural network based on the coordinate attention mechanism; inputs a real neutron radiographic image containing multiple distortions into the trained multiple distortion suppression model as input, predicts the original image of the real neutron radiographic image containing multiple distortions, and obtains a target result.

The invention discloses a space target material identification method based on a cross attention residual mechanism, and the method comprises the steps: firstly constructing a data set, and building a space target material identification model based on the cross attention residual mechanism; thirdly, the data set is input into a material recognition model, an adaptive MTF filtering module in the model carries out image correction, and a corrected feature map and a shallow layer feature map are obtained; the space-spectral feature combined extraction module processes the corrected feature map and outputs a deep feature map; a multi-scale feature fusion module based on cross attention carries out feature fusion to obtain a fused feature map; performing model training based on the fused feature map and the loss function; and after training is completed, inputting a to-be-detected image into the model, and outputting material information of the space target by the model. According to the method, the degradation effect of the image is effectively dealt with through the three modules, the fusion of the spectral features and the spatial structure features is realized, and the recognition accuracy when the target is deformed or the illumination condition is changed is ensured.

The invention discloses a mulberry leaf picking and positioning method and device based on machine vision, and relates to the technical field of machine vision. The method comprises the following steps: acquiring calibrated and synchronized multi-modal image data of a mulberry target area, wherein the data can be a binocular sequence or a depth camera color-depth pair; performing preprocessing including brightness color normalization and image degradation compensation on the data to obtain an enhanced frame; inputting the enhanced frame into a target detection and maturity evaluation joint network, identifying each mulberry leaf instance, and outputting an instance segmentation mask defining the contour of the mulberry leaf instance and a probability vector representing the maturity; based on the instance segmentation mask and depth information, pixels in the mask are converted into a three-dimensional leaf surface point cloud; according to the point cloud, the six-degree-of-freedom pose of each mulberry leaf target is obtained, and at least one candidate picking site is determined; and finally, performing priority ranking on the candidate picking sites according to a preset comprehensive scoring function, and generating a scheduling queue containing timestamps, six-degree-of-freedom poses and priorities.

The invention discloses an underwater target detection method based on multi-modal feature fusion and time sequence context sensing, and aims to solve the problem of low detection precision caused by image degradation, target shielding and limitation of a single sensing mode in an underwater environment. According to the method, an MFTC-Net model is constructed, and the MFTC-Net model comprises a dynamic multi-modal feature fusion module which carries out adaptive alignment and weighted fusion on optical image features and simulated sonar features through deformable convolution and a double-path attention mechanism so as to enhance perception of a fuzzy target; the lightweight time sequence context sensing module is used for carrying out alignment and time-dependent modeling based on motion information on fusion features of continuous frames by using an optical flow estimation network and a convolution gating cycle unit so as to improve the recognition robustness of an occluded target; the context decoupling detection head introduces a large receptive field context module and a detail keeping context module for classification and positioning branches through a task decoupling structure so as to optimize feature representation. According to the method, deep complementation of optical and sonar modes and effective utilization of time sequence information are realized, and the precision and stability of target detection in a complex underwater scene are remarkably improved.

The application provides a degenerated infrared image restoration method and system, which comprises the following steps: applying an image degradation factor corresponding to an image degradation mechanism and adapted to each infrared image in an infrared image sample to construct different types of degraded images based on different image degradation mechanisms; training a super-resolution processing model based on at least one type of degraded image to obtain a degenerated infrared image restoration model; inputting a current infrared image with the image degradation factor into the degenerated infrared image restoration model to perform image restoration processing on the current infrared image by the degenerated infrared image restoration model. The application corresponds to obtain different types of degraded images by multiple modeling methods, and further trains the super-resolution processing model by the combination of different types of degraded images to restore the infrared image acquired under diversified meteorological environments with high quality.

The invention relates to the technical field of image processing, and discloses an image optimization method and device, equipment and a medium, and the method comprises the steps: recognizing the degradation information of a target image, carrying out the image transformation processing of the target image according to the image degradation information and a preset image transformation process, and obtaining an optimized image, performing multi-type visual task detection on the optimized image, generating a quantized image quality index, judging whether the image reaches a quality standard by comparing a detection parameter with a preset threshold value, if not, calculating a reward signal of a reinforcement learning agent model according to a detection result, and updating an image transformation process by using the signal, so as to improve the quality of the image. And then returning to the optimization step to process the image again, if the current strategy reaches the standard, indicating that the current strategy is effective, directly processing the subsequent to-be-processed image by the agent by using the updated strategy, and finally outputting a high-quality target optimized image. According to the invention, the efficiency and precision of image processing are improved.

The invention relates to the technical field of atmosphere image degradation simulation, in particular to an image degradation simulation method for atmosphere turbulence space-time blurring and aerosol multiple scattering, and the method comprises the steps: obtaining an atmosphere turbulence data set, and generating a three-dimensional space-time refractive index fluctuation field; constructing an atmospheric turbulence influence operator, and respectively constructing a real-time turbulence influence operator and an atmospheric turbulence influence distortion operator; constructing a multi-scattering influence operator, obtaining aerosol scattering parameters, and simulating a multi-scattering process through Monte Carlo ray tracing; fusing the atmospheric turbulence influence operator and the multiple scattering influence operator to form a composite atmospheric degradation model; and inputting the clear image into the composite atmospheric degradation model, and outputting a degraded image. According to the method, the Monte Carlo multiple scattering simulation and the dynamic turbulence operator are fused, the complex atmosphere comprehensive degradation effect can be efficiently and vividly reproduced, and continuous degradation processing of the video frame can be carried out due to the fact that the turbulence operator has space-time continuity.

The application discloses a marine organism image processing method and device, electronic equipment and a readable storage medium, and is applied to the technical field of digital image processing. The method comprises the following steps: performing step-by-step down-sampling on a to-be-processed optical image by using a convolution module with different convolution kernels, so as to obtain a plurality of initial images with different scales. Global feature extraction is performed on each initial image under different scales, so as to obtain a plurality of multi-level feature maps; the multi-level feature maps are input into a Transformer encoder, and multi-level detail feature extraction is performed on the multi-level feature maps by adopting a multi-level feature deepening extraction fusion mode. The output features of the Transformer decoder and the multi-level detail features are up-sampled, so as to obtain an enhanced optical image. The application can solve the problem that the underwater image degradation phenomenon is serious or the details are blurred, and effectively improve the image enhancement effect of the marine organism image.

This disclosure provides an image detection method, apparatus, electronic device, storage medium, and program product. Specific implementations include: acquiring an image to be detected; processing the image to be detected using an image detection model; determining image quality quantification information of the image to be detected, image degradation regions in the image to be detected, and textual description information associated with the image degradation regions. The image quality quantification information includes information characterizing whether a predetermined anomaly exists in the image to be detected; the image degradation regions include areas in the image to be detected where predetermined anomalies exist; and the textual description information includes descriptive information about the predetermined anomalies corresponding to the image degradation regions. The image detection method provided by this disclosure improves the accuracy of image detection by processing the acquired image to be detected using an image detection model. By using the image quality quantification information output by the image detection model, the image degradation regions in the image to be detected, and the textual description information associated with the image degradation regions, the image quality quantification information, the anomalies, and the degradation regions of the image to be detected are determined, achieving accurate multi-dimensional image detection.

The invention relates to an intelligent aiming design method and system based on deep learning. According to the method and system, infrared and visible light bimodal video streams are synchronously collected, and weather types and grades are recognized in real time in combination with meteorological sensor data; carrying out image enhancement by adopting a physical constraint self-adaptive denoising network; constructing a target trajectory by using a target detection and tracking algorithm; high-precision prediction of a target motion track is realized based on a double-flow neural network and a time sequence prediction model; fusing the real-time meteorological data and the trajectory model to carry out trajectory compensation calculation; finally, the dynamic aiming point coordinates are calculated; according to the method, the technical problems of serious image degradation and misalignment of target prediction in severe weather are effectively solved, and the first hit rate and task efficiency of an aiming system in a complex environment are remarkably improved.

The invention provides an image enhancement method and device, equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a to-be-processed video stream carrying a foreground mask; the foreground mask comprises a first foreground mask of the robot and a second foreground mask of the task object; the second foreground masks of other frames of to-be-processed images except the first frame of to-be-processed image are obtained by taking the second foreground mask of the first frame of to-be-processed image as prior information; and according to the foreground mask, separating an original foreground image and an original background image in each frame of to-be-processed image in the to-be-processed video stream: respectively carrying out image enhancement on the original foreground image and the original background image, and carrying out image degradation operation on the foreground and background fusion image after image enhancement to obtain a target image, therefore, the stability of foreground segmentation is realized, the difference between an enhanced image and an image acquired in actual deployment in visual details is reduced, and the generalization ability of imitation learning of a robot in a real environment is improved.

The invention discloses a multi-weather target detection method based on degraded category perception image restoration, and relates to the field of computer vision and artificial intelligence. The method comprises the following steps: (1) adopting a training normal form of restoration and detection combined learning, simultaneously carrying out restoration and detection decoupling by utilizing features extracted by a single feature encoder, and extracting clear image features from images of various weather types when a model is trained by using various different types of degraded images, therefore, different weather conditions can be adapted; (2) image degradation information is introduced, coding features of the clear image and the degradation image are distinguished, only the degradation image is subjected to image restoration, and mutual influence between the clear image and a restoration module is avoided; and (3) introducing a degradation category predictor to predict the degradation category of the image, and making a detector have the degradation category perception capability through degradation classification loss.