217 results about "Pyramid (image processing)" patented technology

The invention belongs to the technical field of image processing, and discloses a frame image and event stream feature fusion-based target detection method, which comprises the following steps of: acquiring RGB (Red, Green, Blue) images and event stream data, and constructing a time-space synchronous multi-modal data pair; constructing a double-flow feature extraction backbone network to extract events and RGB features; based on a cross attention mechanism, multi-head attention is utilized to realize semantic alignment; the fusion weight is adaptively adjusted according to the statistical distribution; a multi-level fusion network is constructed, cross-scale fusion is performed by using an FPN pyramid, and target positioning and classification feature expression are cooperatively enhanced through a spatial semantic aggregation module. According to the target detection method based on frame image and event stream feature fusion, through a multi-modal data collaborative perception and self-adaptive feature optimization mechanism, the detection robustness in a complex scene is remarkably improved, the dynamic target omission ratio and the error recognition rate are effectively reduced, and the target detection efficiency is improved. And an all-weather high-precision environment perception capability is provided for an automatic driving system.

The invention discloses a visible light and infrared fusion target detection method and system for an all-time unmanned aerial vehicle scene, and belongs to the technical field of unmanned aerial vehicle aviation and intelligent image processing. The method comprises the following steps: analyzing an original visible light image to calculate average brightness and root-mean-square contrast, and quantifying scene illumination conditions; distortion correction and registration are carried out on the original image; a parallel backbone network is adopted to extract visible light and infrared twinborn feature maps, the number of channels allocated to two modal features is dynamically adjusted through 1 * 1 convolution according to illumination condition parameters, and then a dual-light fusion network containing a gated convolution block is utilized to perform weighted fusion; and target prediction is carried out through the progressive feature pyramid network. Through an illumination adaptive fusion strategy and targeted data enhancement, the precision and robustness of target detection in a complex all-day scene are significantly improved, and the method is suitable for real-time target detection tasks of the unmanned aerial vehicle.

The invention discloses a marine litter intelligent identification and classification method based on a multispectral unmanned aerial vehicle remote sensing image, and relates to the technical field of image processing, and the method comprises the steps: collecting and preprocessing a remote sensing image of a preset sea area, constructing a color correction network, and carrying out the color correction of the preprocessed remote sensing image; multiband features and spectral indexes of enhanced garbage detection are obtained, and multispectral features are generated through multi-scale feature pyramid structure fusion; training a conditional generative adversarial network, inputting a remote sensing image and multispectral features, and performing pixel-by-pixel fusion on the enhanced remote sensing image and the remote sensing image after color correction to obtain a multiband fusion feature map; and constructing a lightweight detection network based on the OfficientDet-Lite, taking the multi-band fusion feature map as input, and outputting a bounding box and a garbage category of garbage by adopting a joint detection-classification architecture. According to the method, the problems of color distortion, contour fuzziness, small target missing detection and the like in marine litter identification are solved, and meanwhile, the real-time performance of marine litter identification and classification is ensured.

The invention belongs to the technical field of computer vision and image processing, and discloses a remote sensing small sample target detection method based on double-attention guided transfer learning, and the method comprises the steps: obtaining a remote sensing image data set, and carrying out the preprocessing; taking the preprocessed remote sensing image training set as input, constructing a basic detection model by using a ResNet-101 backbone network, a feature pyramid network and a content awareness upsampling and regional proposal network, and obtaining basic model parameters; basic model parameters are used as input, a DA-FSDET network is trained based on a content awareness strip pyramid and a deformable attention area proposal network, and the trained DA-FSDET network is used to acquire a category detection frame containing small sample categories and confidence. Through cascading and cooperative work of the content awareness stripe pyramid and the deformable attention area proposal network, the detection precision and robustness of the multi-scale target in the remote sensing image are effectively improved.

The invention relates to the technical field of remote sensing image processing, in particular to an end-to-end neural network InSAR (Interferometric Synthetic Aperture Radar) phase unwrapping method based on mixed attention, which takes U-Net as a basic framework, extracts key features and improves resolution through down-sampling and up-sampling operations, thereby effectively recovering detail information. Specifically, a convolutional block attention module (CBAM) and two receptive field modules, namely cavity spatial pyramid pooling (ASPP) and a receptive field module (RFB) are combined to construct an RFAUNet network model, and then simulation data sets generated by two methods of digital elevation inversion and random matrix generation are used for training a neural network until a good unwrapping effect is obtained. And finally, carrying out a phase unwrapping experiment on simulation data and real data to verify the effectiveness and robustness of the RFAUNet network model.

The invention provides a multi-scale pyramid weighted fusion underwater image enhancement method based on double prior, and the method comprises the steps: obtaining a degraded underwater image, and carrying out the global and local cooperation body color calibration of the degraded underwater image; decomposing the color correction image into a base layer, a detail layer and a noise layer by adopting a variational decomposition algorithm; performing spectral prior and transmissivity loss constraint on the base layer image to obtain a defogged image; fusing the detail layer image and the noise layer image to obtain a filtered image; performing enhancement processing on the filtered image by adopting a nonlinear mapping and contrast enhancement strategy to obtain an enhanced image; performing multi-level feature integration and reconstruction on the defogged image and the enhanced image by adopting a multi-scale pyramid adaptive weighted fusion method to obtain an underwater image with natural color and high visual definition; according to the method, the traditional image processing and variational optimization thought is combined to effectively correct the color deviation of the degraded underwater image, the image contrast and the detail definition are improved, and the visualization effect of the underwater image is improved.

The invention relates to the technical field of image processing and information retrieval, and discloses an image feature extraction and appearance trademark retrieval method based on deep learning, which comprises a feature extraction unit, a cross-modal fusion module, a retrieval strategy module and a dynamic weight distribution unit. The feature extraction unit extracts multi-level semantic information through a multi-branch convolutional network and multi-scale pyramid pooling; the cross-modal fusion module integrates vision, text and color information by using space attention, channel attention and cross attention mechanisms; the retrieval strategy module adopts Hash coding and global self-attention to realize rapid screening and fine matching; the dynamic weight allocation unit suppresses background interference through learnable parameters. The trademark retrieval precision and efficiency can be effectively improved, and the method is suitable for a multi-modal data processing scene.

A method, apparatus, non-transitory computer readable medium, apparatus, and system for image processing include obtaining a text prompt; generating, using a generator of an image generation model, a feature embedding based on the text prompt, wherein the feature embedding includes a first set of channels that encodes a first value of an image characteristic and a second set of channels that encodes a residual between the first value of the image characteristic and a second value of the image characteristic; and generating, using a decoder of the image generation model, a synthetic image corresponding to the second value of the image characteristic based on the feature embedding.

The invention discloses an intelligent storage environment lightweight efficient target detection method based on YOLO11 improvement, and belongs to the technical field of image processing. Aiming at the problems of target shielding, illumination change and limitation of computing resources and storage space on mobile equipment deployment in carton detection in a storage environment, target detection image data is loaded by using a database and is converted into a YOLO format, and a training set and a test set are divided; performance optimization is realized through the following improvements: a multi-dimensional cooperative attention module is introduced before a spatial pyramid pooling module of a backbone network; the neck network is fused with a weighted bidirectional feature pyramid network and a multi-dimensional cooperative attention module, and feature interaction between levels is enhanced; an original large detection head is removed from the detection head, medium and small targets are focused, parameter quantity and background interference are reduced, feature representation is optimized, detection precision and calculation efficiency in a storage scene are balanced, and the method is suitable for real-time detection and efficient operation of a mobile device on cartons in a storage environment.

The invention discloses an ultrahigh-definition panoramic image adaptive HDR fusion method based on data driving, and relates to the technical field of digital image processing, and the method comprises the steps: carrying out the coarse alignment and high dynamic range fusion of a low-resolution line graph sequence, and generating a low-resolution HDR panoramic image; carrying out sharpening processing on the low-resolution HDR panoramic image to obtain a low-resolution sharpened HDR image, and meanwhile, obtaining a multi-scale residual spectrum generated by sharpening; performing up-sampling on the multi-scale residual spectrum, and performing small-sample element learning fine tuning on the weight prediction network in combination with the low-resolution sharpened HDR graph to obtain a fine-tuned weight prediction network; performing weight prediction and layer-by-layer fusion on the registered high-resolution tile sequence on a multi-scale pyramid based on a fine tuning weight prediction network model; according to the method, the sharpening processing is implemented on the low-resolution HDR panorama, and the multi-scale residual spectrum is extracted, so that the detail sensitivity and adaptability in a complex scene are improved.

The invention discloses a ship bollard identification method and system based on adaptive multi-scale multi-grid division, and belongs to the technical field of computer vision and image processing. The system divides an image foreground region and a background region through a visual saliency calculation module, carries out dense sampling in the foreground region and sparse sampling in the background region by adopting a non-uniform grid generation module, screens candidate grids in combination with gradient direction consistency and texture features, fuses candidate frames of different scales through a multi-scale image pyramid, and finally obtains a multi-scale image. And accurate positioning of the bollard is realized through the fine grid accurate positioning module. The method solves the problem that the prior art is insufficient in adaptability to ship size, shooting distance and resolution change, improves the precision and generalization ability of bollard positioning in a complex scene, and is suitable for bollard detection scenes of various ship images.

The invention belongs to the technical field of medical image processing, and particularly relates to a linear Transform general focus recognition method based on multiple perception and context guidance, and the method comprises the steps: extracting the multi-scale features of a medical CT image through a backbone network, obtaining the edge gradient features in parallel, making up the missing of focus boundary information through an edge perception feature enhancement module, and carrying out the recognition of the focus. And then global feature modeling under linear complexity is realized through a polarity perception feature interaction module, a high-discrimination-force multi-scale feature map is generated by using a context-guided feature pyramid network, and finally the model is optimized by combining a Hungary algorithm and a joint loss function based on an end-to-end detection architecture of set prediction. The problems that the focus boundary is fuzzy, feature interaction and calculation efficiency are balanced, and the focus and background separation degree is weak are effectively solved, double improvement of calculation efficiency and detection precision on massive medical image data is achieved, and reliable support is provided for clinical precise auxiliary diagnosis.

The invention relates to the technical field of computer image processing and medical image analysis, in particular to a cervical cancer MRI (Magnetic Resonance Imaging) image segmentation method for improving a U-Net structure based on a feed-forward channel double-attention mechanism. In order to solve the problems that a traditional U-Net structure is weak in multi-scale information extraction capability, inaccurate in boundary fuzzy region recognition and the like in processing female abdominal cervical cancer MRI images, the method proposes that a feedforward connection mechanism and a double-attention mechanism are embedded into an encoder and a bottleneck module to form a novel U-Net segmentation model; the recognition and segmentation precision of the cervical cancer focus area is improved, and a high-quality image basis is provided for subsequent clinical diagnosis and treatment. A double-attention mechanism is integrated into a plurality of key nodes of the model, a joint channel-space attention module is added to the tail of each convolution module in an encoder, a cavity space pyramid pooling structure is introduced to a bottleneck position, a channel attention mechanism is embedded, and joint modeling of cross-scale, multi-channel and space context information is achieved.

The invention relates to the technical field of image processing, in particular to an aerial image small target detection method and system based on deep learning, and the method comprises the steps: obtaining an aerial original image, carrying out the preprocessing of the aerial original image, inputting the preprocessed image into a multi-scale feature enhancement input model, and obtaining a multi-scale feature enhancement model; the method comprises the steps of obtaining an enhanced image containing multi-scale features, performing feature extraction by using a channel-space attention backbone network, generating a multi-scale feature map of a space attention mask, performing fusion by using a bidirectional recursive feature pyramid network to generate fusion features, performing target detection by using an adaptive receptive field detection head, and outputting a result. According to the technical scheme, through multi-stage enhancement and recursive fusion, the problem of small target information loss is effectively relieved, and the detection precision and robustness are improved.

The invention provides a medical image registration method and equipment. The method is applied to the technical field of medical image processing. The method comprises the steps that a to-be-registered image pair used for medical image registration is acquired, the to-be-registered image pair comprises a floating image and a fixed image, the floating image is an image needing spatial transformation in the registration operation, and the fixed image is a reference standard correspondingly consistent with the spatial position and feature of the floating image in the registration operation; performing hierarchical feature extraction on the floating image and the fixed image through a registration model to obtain a first multi-scale feature pyramid and a second multi-scale feature pyramid, and performing correlation perception registration on multi-scale features in the first multi-scale feature pyramid and the second multi-scale feature pyramid to obtain deformation field data; and performing spatial transformation on the floating image based on the deformation field data to obtain a target registration image. According to the invention, efficient and accurate medical image registration is realized.

The invention belongs to the technical field of medical image processing, and particularly relates to a prostate MRI-TRUS deformable image registration method based on structure perception decoupling learning. The method comprises the following steps: designing an anatomical maintenance intensity disturbance module, simulating intensity and artifact differences between different modes on the premise of keeping an anatomical structure unchanged, and generating diversified appearance samples to improve the adaptability of the model to mode changes; a double-flow encoder structure is constructed, space attention latent consistency loss is introduced into a multi-layer feature space, the structure consistency is restrained from the feature level, and deep structure representation learning with the unchanged appearance is achieved; and an enhanced pyramid decoder is adopted to fuse multi-scale structural features layer by layer to predict a registration deformation field, so that high-precision cross-modal alignment is realized. According to the method, structural consistency constraint is carried out on the hidden space level, so that the influence of modal difference and artifacts can be effectively reduced, and the registration precision is improved.

The invention relates to the technical field of computer vision and image processing, and particularly discloses an unmanned aerial vehicle identification and detection method under a target part feature missing condition. The method comprises the following steps: (1) making an initial data set by adopting aerial pictures of an unmanned aerial vehicle; (2) performing labeling and data enhancement processing on the initial data set to obtain a training set and a verification set; (3) a YOLOv8 target detection model is improved, a standard convolution module (Conv) of a backbone network (Backbone) is replaced by dynamic deformable convolution (DEConv), a SimAM attention mechanism is introduced behind a last C2f module of the backbone network and in front of a spatial pyramid pooling layer (SPPF), and in a neck network (Neck), the C2f module is replaced by a C2f-SimAM module, and the standard convolution module is replaced by the dynamic deformable convolution; an additional branch for capturing key features is added in an output branch of a detection head (Head). According to the method, the recognition and detection capability of a target with partial feature missing can be remarkably improved.

The invention discloses a monitoring image multi-target tracking method based on deep learning, and relates to the technical field of digital image processing, and the method comprises the following steps: S1, generating a multi-scale feature pyramid; s2, extracting causal feature vectors; s3, generating a discrete codebook index; s4, constructing a dynamic graph; s5, inputting the dynamic graph into an improved ASTGCN network, iteratively fusing space-time attention weights and Hamilton dynamics evolution characteristics between nodes through cascaded Hamilton space-time blocks, and generating a final prediction state of each historical track node; s6, solving an optimal correlation matching matrix by using a Hungary algorithm; and S7, extracting all active track information. According to the method, the limitations of identity drift caused by variable appearance characteristics and inaccurate prediction caused by lack of physical priori in a traditional multi-target tracking method are overcome, and an efficient, accurate and robust solution is provided for intelligent video monitoring.

The invention provides an image registration method and an image registration device, which are applied to the technical field of image processing. Comprising the following steps: acquiring a target reference image and a first target to-be-registered image of a to-be-detected area containing FOD; constructing an optimal affine transformation model according to the target reference image and the N preset pitch angles, and further performing linear transformation on the first target to-be-registered image to obtain a second target to-be-registered image; according to a Gaussian difference pyramid of a second target to-be-registered image, screening an extreme point of which the principal curvature does not exceed a preset principal curvature threshold as a first feature point, and further screening a first feature point of which the re-projection error and the sampling probability meet a preset condition as a second feature point; and solving a homogeneous linear equation set of the pixel point pairs matched with the second feature points by adopting an SVD method to obtain a transformation homography matrix, and then registering the first target to-be-registered image to obtain a target image. The contradictory closed loop of low efficiency-insufficient precision is broken through, and the aviation operation safety is guaranteed.

The invention provides a multi-scale context aggregation and dynamic supervision medical image segmentation method and application thereof, and belongs to the technical field of medical image processing. In order to solve the problems of weak non-linear feature fitting ability, global context missing and unstable training convergence in the prior art, the ResUKAN + network is constructed. According to the method, a residual KAN convolution module is embedded in a full level of an encoder, and nonlinear feature extraction is enhanced by using a B-spline function; a multi-scale context aggregation module is arranged on a bottleneck layer, and dynamic pyramid pooling and a double attention mechanism are fused to capture global dependency; a dynamic auxiliary supervision head is introduced at the tail end of a decoder, complementary features are extracted through a heterogeneous receptive field, and loss calculation is optimized in combination with a dynamic weight mechanism which is exponentially attenuated along with a training period. According to the method, the segmentation precision and robustness of the fuzzy boundary and the multi-scale focus are remarkably improved, and the method is suitable for medical image intelligent diagnosis.

The invention provides a non-uniform fog image defogging method and system based on multi-scale feature constraint, relates to the field of image processing and computer vision, and aims to solve the problems of unbalanced defogging, detail loss and the like caused by non-uniform and complex haze distribution in a non-uniform fog image. According to the method, a feature extraction and reconstruction module and a feature enhancement module are constructed, the feature extraction and reconstruction module is combined with a Laplacian pyramid up-down sampling and self-attention mechanism, and multi-scale features of an image are utilized to realize high-precision defogging; and a state space model is introduced through a feature enhancement module to extract and fuse shallow features and deep semantic features of the image so as to enhance and supplement detail and structure information of the defogged image. According to the method, the problems of unbalanced defogging, detail loss and the like are solved, the problem that the model only depends on single spatial domain characteristics or single physical priori knowledge is solved, and the defogging precision and generalization ability of the model are improved.

The invention belongs to the technical field of image processing, and particularly relates to a motor assembly defect detection system based on image recognition, which comprises a highlight area segmentation module, a multi-scale highlight repair module, a reflectivity decomposition module and a defect detection module, and is characterized in that a stator magnetic steel potting image is acquired, a highlight area is segmented, and a highlight mask is obtained; constructing a multi-scale pyramid based on the brightness component and the saturation component of the stator magnetic steel potting image, and generating a mixed weight map according to the highlight intensity and the detail significance under each scale; according to the multi-scale pyramid, the mixed weight map and the highlight mask, carrying out layered restoration on the brightness component to obtain a synthetic substrate image, and according to the synthetic substrate image, carrying out guided filtering and reflectivity decomposition to obtain an inherent reflectivity map; and carrying out encapsulation defect detection according to the inherent reflectivity graph. According to the invention, the interference of highlight reflection on encapsulation defect detection is eliminated, and the accuracy and robustness of encapsulation defect detection are improved.

The invention belongs to the technical field of remote sensing image processing and computer vision, and discloses an adaptive feature enhancement contrast learning method for remote sensing image detection. The method comprises the steps of obtaining and preprocessing a remote sensing image target detection data set, constructing a self-supervised feature enhancement module, constructing a self-adaptive bidirectional feature fusion pyramid, constructing a self-adaptive feature enhancement contrast learning network, deploying the network, detecting a real-time remote sensing target, and outputting and displaying a detection result. The invention provides a self-adaptive feature enhancement contrast learning method for remote sensing image detection, which not only can accurately identify a multi-scale target, but also has remarkable advantages in the aspects of small target detection and complex background interference resistance, and can effectively improve the precision and efficiency of remote sensing image target detection.

The invention relates to the technical field of image analysis, in particular to an efficient image processing system for external naked-eye 3D display equipment. Clustering is carried out according to position features and color features of pixel points in the image, and different areas are obtained; obtaining a matching degree according to shape difference features and color difference features of the region and any region in the associated frame image; obtaining the overall motion degree according to the position difference characteristics and the matching degree of the region and all regions in the associated frame image; obtaining texture richness according to the texture features; and obtaining a proportionality coefficient according to the overall motion degree and the texture richness. According to the method, the number of layers of an image pyramid is adjusted according to a proportionality coefficient to obtain the number of adaptive layers; alignment and consistency correction are carried out on the image and the associated frame image according to the adaptive layer number and the optical flow algorithm, the calculation efficiency and precision of the optical flow algorithm are met at the same time, and the use effect of the 3D display device is improved.

The invention relates to a lightweight multi-scene disease and pest detection method and system based on RT-DETR. According to the scheme, firstly, a standardized image processing link is constructed, multi-band feature extraction is carried out on an input image by using a convolutional backbone network introduced with wavelet transform, an effective receptive field is expanded in a frequency domain through wavelet decomposition and an inverse reconstruction mechanism, and feature capture of a tiny insect pest target is enhanced while calculation redundancy is reduced. Furthermore, a bidirectional feature pyramid network including global and local double-branch collaborative modeling is adopted, cross-level dynamic interaction and gating fusion are performed on multi-scale features, and environmental noise interference such as veins and illumination under a complex farmland background is effectively inhibited. And finally, establishing a homography mapping model from a pixel plane to a geographic space according to camera calibration parameters, converting a visual detection result into a spatial distribution diagram layer with latitude and longitude information, and realizing dimension crossing of pest and disease damage monitoring from single-point identification to region-level risk assessment.

The invention discloses a skin lesion segmentation method and system based on dual-path perception multi-stage fusion, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the block division of a skin image, inputting into an encoder, and filtering a key lesion region through employing a region sparse attention mechanism; performing down-sampling on the feature map by using a block merging operation, and constructing a multi-scale feature pyramid; skin image features are processed by using a dual-path sensing multi-stage fusion network, deepest features generated by an encoder are processed by a spatial frequency dual-path cascade sensing module, and two-stage space-frequency collaborative optimization is executed; the method comprises the following steps: establishing jump connection between an encoder and a corresponding decoder through a space channel double-path parallel sensing module, recovering spatial resolution through block expansion operation in combination with modulated encoder characteristics, and generating a pixel-level lesion probability graph. According to the method, the context sensing capability across the space domain and the frequency domain is remarkably enhanced, and an accurate and detailed skin lesion segmentation result is obtained.

The invention discloses a panoramic image splicing method, system and device, and relates to the technical field of image processing, and the method comprises the steps: collecting images around a vehicle at different visual angles; using the MASK masks to generate overlapping region masks of the different view angle images, and performing local feature detection on the overlapping region masks to generate a transformation matrix; aligning the images of different visual angles according to the transformation matrix; a Canny edge detection operator is fused in splicing seam energy detection, the energy weight of the image edge area of the aligned image is enhanced, and a splicing seam is guided to actively avoid an object with remarkable structural features; b spline interpolation is introduced to optimize an initial splicing seam path; constructing a Laplacian pyramid along Gaussian blur of a splicing seam, and sequentially carrying out gradual fusion to generate a seamless panoramic image; according to the method, the basic function of eliminating the visual blind area is realized, a clear and visual panoramic view can be provided for a driver, and the driving safety is effectively improved.

The invention relates to the technical field of image processing and intelligent identification, and discloses an image segmentation method for identifying a mineral boundary in a table ore zone. The method comprises the steps of constructing a multi-branch single-output enhancement unit based on gating enhancement and multi-head attention combined dynamic fusion, constructing a multi-scale fusion module of a split-level fusion pyramid structure based on multi-head attention and residual fusion, constructing a trunk module based on convolutional layer and enhancement unit stacking, and constructing a multi-scale fusion module of a split-level fusion pyramid structure based on multi-head attention and residual fusion. Constructing an image recognition segmentation model by combining step-by-step down-sampling, a multi-scale fusion module and a prediction head; and obtaining an ore zone image of a shaking table operation site of the reselection workshop, inputting the ore zone image into the image recognition segmentation model to obtain a recognition result, and completing shaking table separation of the mineral particles based on the recognition result. The problem of insufficient segmentation precision caused by particle size difference, illumination interference, fuzzy boundary and real-time requirement in the existing industrial mineral separation process is solved.

The invention provides a gun calibration method based on automatic bullet hole detection, a medium, equipment and a product, and relates to the technical field of infrared image processing, and the method comprises the steps: capturing an infrared image of a bullet hole in real time through an infrared thermal imager, carrying out the preprocessing, and constructing a bullet hole detection data set; constructing a bullet hole detection model based on the YOLOv5 network, adding a multi-scale feature fusion module in the YOLOv5 network, and fusing the shallow-layer features, the middle-layer features and the deep-layer features extracted by the backbone network into new deep-layer features; spatial pyramid pooling is replaced by hollow spatial pyramid pooling; inputting the bullet hole detection data set into the model to obtain bullet hole position data; according to the position data of the bullet hole, converting the coordinates of the bullet hole, and calculating the offset of the bullet hole; and according to the bullet hole offset, ballistic deviation is analyzed, and ballistic deviation is corrected. The method can break through environmental limitation, realizes real-time bullet hole detection, and improves gun calibration precision.

The invention relates to the technical field of digital image processing, in particular to a real-time image quality enhancement method for a vehicle-mounted camera EMC test, and the method comprises the steps: obtaining real-time image data and historical image data; and performing multi-branch collaborative decoupling processing on the real-time image data to generate a frequency domain purification graph, a core structure graph, a space domain purification graph and a time domain stability graph. And performing local statistical analysis on the real-time image data to generate an artifact intensity map and a perception saliency map. Under a multi-resolution Laplacian pyramid framework, fusing the frequency domain purification graph and the space domain purification graph; the weight of the fusion process is intelligently regulated and controlled spatially and hierarchically by an artifact intensity graph, a perception saliency graph and a time domain stabilization graph which are constructed based on a Gaussian pyramid, and finally a high-quality enhanced image is reconstructed and generated. According to the invention, through a multi-branch cooperative decoupling and intelligent fusion method, real-time enhancement of the vehicle-mounted camera image under EMC interference is realized.